Add shared_memory_type GUC.

Since 9.3 we have used anonymous shared mmap for our main shared memory
region, except in EXEC_BACKEND builds.  Provide a GUC so that users
can opt for System V shared memory once again, like in 9.2 and earlier.

A later patch proposes to add huge/large page support for AIX, which
requires System V shared memory and provided the motivation to revive
this possibility.  It may also be useful on some BSDs.

Author: Andres Freund (revived and documented by Thomas Munro)
Discussion: https://postgr.es/m/HE1PR0202MB28126DB4E0B6621CC6A1A91286D90%40HE1PR0202MB2812.eurprd02.prod.outlook.com
Discussion: https://postgr.es/m/2AE143D2-87D3-4AD1-AC78-CE2258230C05%40FreeBSD.org

7 files changed, 101 insertions, 33 deletions

diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index b6f5822b847..9b7a7388d5a 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -1694,6 +1694,31 @@ include_dir 'conf.d'
       </listitem>
      </varlistentry>
 
+     <varlistentry id="guc-shared-memory-type" xreflabel="shared_memory_type">
+      <term><varname>shared_memory_type</varname> (<type>enum</type>)
+      <indexterm>
+       <primary><varname>shared_memory_type</varname> configuration parameter</primary>
+      </indexterm>
+      </term>
+      <listitem>
+       <para>
+        Specifies the shared memory implementation that the server
+        should use for the main shared memory region that holds
+        <productname>PostgreSQL</productname>'s shared buffers and other
+        shared data.  Possible values are <literal>mmap</literal> (for
+        anonymous shared memory allocated using <function>mmap</function>),
+        <literal>sysv</literal> (for System V shared memory allocated via
+        <function>shmget</function>) and <literal>windows</literal> (for Windows
+        shared memory).  Not all values are supported on all platforms; the
+        first supported option is the default for that platform.  The use of
+        the <literal>sysv</literal> option, which is not the default on any
+        platform, is generally discouraged because it typically requires
+        non-default kernel settings to allow for large allocations (see <xref
+        linkend="sysvipc"/>).
+       </para>
+      </listitem>
+     </varlistentry>
+
      <varlistentry id="guc-dynamic-shared-memory-type" xreflabel="dynamic_shared_memory_type">
       <term><varname>dynamic_shared_memory_type</varname> (<type>enum</type>)
       <indexterm>
diff --git a/doc/src/sgml/runtime.sgml b/doc/src/sgml/runtime.sgml
index 333adda4086..1f78f6c9569 100644
--- a/doc/src/sgml/runtime.sgml
+++ b/doc/src/sgml/runtime.sgml
@@ -638,9 +638,12 @@ psql: could not connect to server: No such file or directory
    </para>
 
    <para>
-    Upon starting the server, <productname>PostgreSQL</productname> normally allocates
+    By default, <productname>PostgreSQL</productname> allocates
     a very small amount of System V shared memory, as well as a much larger
-    amount of POSIX (<function>mmap</function>) shared memory.
+    amount of anonymous <function>mmap</function> shared memory.
+    Alternatively, a single large System V shared memory region can be used
+    (see <xref linkend="guc-shared-memory-type"/>).
+    
     In addition a significant number of semaphores, which can be either
     System V or POSIX style, are created at server startup.  Currently,
     POSIX semaphores are used on Linux and FreeBSD systems while other
@@ -752,8 +755,10 @@ psql: could not connect to server: No such file or directory
     <productname>PostgreSQL</productname> requires a few bytes of System V shared memory
     (typically 48 bytes, on 64-bit platforms) for each copy of the server.
     On most modern operating systems, this amount can easily be allocated.
-    However, if you are running many copies of the server, or if other
-    applications are also using System V shared memory, it may be necessary to
+    However, if you are running many copies of the server or you explicitly
+    configure the server to use large amounts of System V shared memory (see
+    <xref linkend="guc-shared-memory-type"/> and <xref
+    linkend="guc-dynamic-shared-memory-type"/>), it may be necessary to
     increase <varname>SHMALL</varname>, which is the total amount of System V shared
     memory system-wide.  Note that <varname>SHMALL</varname> is measured in pages
     rather than bytes on many systems.
@@ -879,7 +884,7 @@ kern.ipc.semmns=512
        </para>
 
        <para>
-        You might also want to configure your kernel to lock shared
+        You might also want to configure your kernel to lock System V shared
         memory into RAM and prevent it from being paged out to swap.
         This can be accomplished using the <command>sysctl</command>
         setting <literal>kern.ipc.shm_use_phys</literal>.
@@ -928,7 +933,7 @@ kern.ipc.semmns=512
        </para>
 
        <para>
-        You might also want to configure your kernel to lock shared
+        You might also want to configure your kernel to lock System V shared
         memory into RAM and prevent it from being paged out to swap.
         This can be accomplished using the <command>sysctl</command>
         setting <literal>kern.ipc.shm_use_phys</literal>.
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 49b3416640d..1511a61bc56 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -62,10 +62,11 @@
  * to a process after exec().  Since EXEC_BACKEND is intended only for
  * developer use, this shouldn't be a big problem.  Because of this, we do
  * not worry about supporting anonymous shmem in the EXEC_BACKEND cases below.
+ *
+ * As of PostgreSQL 12, we regained the ability to use a large System V shared
+ * memory region even in non-EXEC_BACKEND builds, if shared_memory_type is set
+ * to sysv (though this is not the default).
  */
-#ifndef EXEC_BACKEND
-#define USE_ANONYMOUS_SHMEM
-#endif
 
 
 typedef key_t IpcMemoryKey;		/* shared memory key passed to shmget(2) */
@@ -75,10 +76,8 @@ typedef int IpcMemoryId;		/* shared memory ID returned by shmget(2) */
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-#ifdef USE_ANONYMOUS_SHMEM
 static Size AnonymousShmemSize;
 static void *AnonymousShmem = NULL;
-#endif
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -370,8 +369,6 @@ PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2)
 	return true;
 }
 
-#ifdef USE_ANONYMOUS_SHMEM
-
 #ifdef MAP_HUGETLB
 
 /*
@@ -534,8 +531,6 @@ AnonymousShmemDetach(int status, Datum arg)
 	}
 }
 
-#endif							/* USE_ANONYMOUS_SHMEM */
-
 /*
  * PGSharedMemoryCreate
  *
@@ -566,7 +561,7 @@ PGSharedMemoryCreate(Size size, bool makePrivate, int port,
 	Size		sysvsize;
 
 	/* Complain if hugepages demanded but we can't possibly support them */
-#if !defined(USE_ANONYMOUS_SHMEM) || !defined(MAP_HUGETLB)
+#if !defined(MAP_HUGETLB)
 	if (huge_pages == HUGE_PAGES_ON)
 		ereport(ERROR,
 				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
@@ -576,18 +571,19 @@ PGSharedMemoryCreate(Size size, bool makePrivate, int port,
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
 
-#ifdef USE_ANONYMOUS_SHMEM
-	AnonymousShmem = CreateAnonymousSegment(&size);
-	AnonymousShmemSize = size;
+	if (shared_memory_type == SHMEM_TYPE_MMAP)
+	{
+		AnonymousShmem = CreateAnonymousSegment(&size);
+		AnonymousShmemSize = size;
 
-	/* Register on-exit routine to unmap the anonymous segment */
-	on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
+		/* Register on-exit routine to unmap the anonymous segment */
+		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
 
-	/* Now we need only allocate a minimal-sized SysV shmem block. */
-	sysvsize = sizeof(PGShmemHeader);
-#else
-	sysvsize = size;
-#endif
+		/* Now we need only allocate a minimal-sized SysV shmem block. */
+		sysvsize = sizeof(PGShmemHeader);
+	}
+	else
+		sysvsize = size;
 
 	/* Make sure PGSharedMemoryAttach doesn't fail without need */
 	UsedShmemSegAddr = NULL;
@@ -687,14 +683,10 @@ PGSharedMemoryCreate(Size size, bool makePrivate, int port,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-#ifdef USE_ANONYMOUS_SHMEM
 	if (AnonymousShmem == NULL)
 		return hdr;
 	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
 	return (PGShmemHeader *) AnonymousShmem;
-#else
-	return hdr;
-#endif
 }
 
 #ifdef EXEC_BACKEND
@@ -801,7 +793,6 @@ PGSharedMemoryDetach(void)
 		UsedShmemSegAddr = NULL;
 	}
 
-#ifdef USE_ANONYMOUS_SHMEM
 	if (AnonymousShmem != NULL)
 	{
 		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
@@ -809,7 +800,6 @@ PGSharedMemoryDetach(void)
 				 AnonymousShmem, AnonymousShmemSize);
 		AnonymousShmem = NULL;
 	}
-#endif
 }
 
 
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2849e47d99b..5965d3620f7 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -46,6 +46,8 @@
 #include "storage/spin.h"
 #include "utils/snapmgr.h"
 
+/* GUCs */
+int			shared_memory_type = DEFAULT_SHARED_MEMORY_TYPE;
 
 shmem_startup_hook_type shmem_startup_hook = NULL;
 
diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c
index 98d75be2929..8681ada33a4 100644
--- a/src/backend/utils/misc/guc.c
+++ b/src/backend/utils/misc/guc.c
@@ -453,6 +453,19 @@ const struct config_enum_entry ssl_protocol_versions_info[] = {
 	{NULL, 0, false}
 };
 
+static struct config_enum_entry shared_memory_options[] = {
+#ifndef WIN32
+	{ "sysv", SHMEM_TYPE_SYSV, false},
+#endif
+#ifndef EXEC_BACKEND
+	{ "mmap", SHMEM_TYPE_MMAP, false},
+#endif
+#ifdef WIN32
+	{ "windows", SHMEM_TYPE_WINDOWS, false},
+#endif
+	{NULL, 0, false}
+};
+
 /*
  * Options for enum values stored in other modules
  */
@@ -4328,6 +4341,16 @@ static struct config_enum ConfigureNamesEnum[] =
 	},
 
 	{
+		{"shared_memory_type", PGC_POSTMASTER, RESOURCES_MEM,
+			gettext_noop("Selects the shared memory implementation used for the main shared memory region."),
+			NULL
+		},
+		&shared_memory_type,
+		DEFAULT_SHARED_MEMORY_TYPE, shared_memory_options,
+		NULL, NULL, NULL
+	},
+
+	{
 		{"wal_sync_method", PGC_SIGHUP, WAL_SETTINGS,
 			gettext_noop("Selects the method used for forcing WAL updates to disk."),
 			NULL
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index a21865a77fa..c7f53470df4 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -129,6 +129,12 @@
 #maintenance_work_mem = 64MB		# min 1MB
 #autovacuum_work_mem = -1		# min 1MB, or -1 to use maintenance_work_mem
 #max_stack_depth = 2MB			# min 100kB
+#shared_memory_type = mmap		# the default is the first option
+					# supported by the operating system:
+					#   mmap
+					#   sysv
+					#   windows
+					# (change requires restart)
 #dynamic_shared_memory_type = posix	# the default is the first option
 					# supported by the operating system:
 					#   posix
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 1247fdf3e68..57d3107a89f 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -41,7 +41,8 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
-/* GUC variable */
+/* GUC variables */
+extern int	shared_memory_type;
 extern int	huge_pages;
 
 /* Possible values for huge_pages */
@@ -52,6 +53,14 @@ typedef enum
 	HUGE_PAGES_TRY
 }			HugePagesType;
 
+/* Possible values for shared_memory_type */
+typedef enum
+{
+	SHMEM_TYPE_WINDOWS,
+	SHMEM_TYPE_SYSV,
+	SHMEM_TYPE_MMAP
+}			PGShmemType;
+
 #ifndef WIN32
 extern unsigned long UsedShmemSegID;
 #else
@@ -59,6 +68,14 @@ extern HANDLE UsedShmemSegID;
 #endif
 extern void *UsedShmemSegAddr;
 
+#if !defined(WIN32) && !defined(EXEC_BACKEND)
+#define DEFAULT_SHARED_MEMORY_TYPE SHMEM_TYPE_MMAP
+#elif !defined(WIN32)
+#define DEFAULT_SHARED_MEMORY_TYPE SHMEM_TYPE_SYSV
+#else
+#define DEFAULT_SHARED_MEMORY_TYPE SHMEM_TYPE_WINDOWS
+#endif
+
 #ifdef EXEC_BACKEND
 extern void PGSharedMemoryReAttach(void);
 extern void PGSharedMemoryNoReAttach(void);