Introduce io_max_combine_limit.

macdice · macdice · commit 10f664684751 · 2025-03-19T15:23:54.000+13:00
The existing io_combine_limit can be changed by users. The new io_max_combine_limit is fixed at server startup time, and functions as a silent clamp on the user setting. That in itself is probably quite useful, but the primary motivation is: aio_init.c allocates shared memory for all asynchronous IOs including some per-block data, and we didn't want to waste memory you'd never used by assuming they could be up to PG_IOV_MAX. This commit already halves the size of 'AioHandleIov' and 'AioHandleData'. A follow-up commit can now expand PG_IOV_MAX without affecting that. Since our GUC system doesn't support dependencies or cross-checks between GUCs, the user-settable one now assigns a "raw" value to io_combine_limit_guc, and the lower of io_combine_limit_guc and io_max_combine_limit is maintained in io_combine_limit. Reviewed-by: Andres Freund <andres@anarazel.de> (earlier version) Discussion: https://postgr.es/m/CA%2BhUKG%2B2T9p-%2BzM6Eeou-RAJjTML6eit1qn26f9twznX59qtCA%40mail.gmail.com
diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
@@ -2625,6 +2625,24 @@ include_dir 'conf.d'
        </listitem>
       </varlistentry>
 
+      <varlistentry id="guc-io-max-combine-limit" xreflabel="io_max_combine_limit">
+       <term><varname>io_max_combine_limit</varname> (<type>integer</type>)
+       <indexterm>
+        <primary><varname>io_max_combine_limit</varname> configuration parameter</primary>
+       </indexterm>
+       </term>
+       <listitem>
+        <para>
+         Controls the largest I/O size in operations that combine I/O, and silently
+         limits the user-settable parameter <varname>io_combine_limit</varname>.
+         This parameter can only be set in
+         the <filename>postgresql.conf</filename> file or on the server
+         command line.
+         The default is 128kB.
+        </para>
+       </listitem>
+      </varlistentry>
+
       <varlistentry id="guc-io-combine-limit" xreflabel="io_combine_limit">
        <term><varname>io_combine_limit</varname> (<type>integer</type>)
        <indexterm>
@@ -2633,7 +2651,10 @@ include_dir 'conf.d'
        </term>
        <listitem>
         <para>
-         Controls the largest I/O size in operations that combine I/O.
+         Controls the largest I/O size in operations that combine I/O.  If set
+         higher than the <varname>io_max_combine_limit</varname> parameter, the
+         lower value will silently be used instead, so both may need to be raised
+         to increase the I/O size.
          The default is 128kB.
         </para>
        </listitem>
diff --git a/src/backend/commands/variable.c b/src/backend/commands/variable.c
@@ -1156,6 +1156,24 @@ assign_maintenance_io_concurrency(int newval, void *extra)
 #endif
 }
 
+/*
+ * GUC assign hooks that recompute io_combine_limit whenever
+ * io_combine_limit_guc and io_max_combine_limit are changed.  These are needed
+ * because the GUC subsystem doesn't support dependencies between GUCs, and
+ * they may be assigned in either order.
+ */
+void
+assign_io_max_combine_limit(int newval, void *extra)
+{
+	io_max_combine_limit = newval;
+	io_combine_limit = Min(io_max_combine_limit, io_combine_limit_guc);
+}
+void
+assign_io_combine_limit(int newval, void *extra)
+{
+	io_combine_limit_guc = newval;
+	io_combine_limit = Min(io_max_combine_limit, io_combine_limit_guc);
+}
 
 /*
  * These show hooks just exist because we want to show the values in octal.
diff --git a/src/backend/storage/aio/aio_init.c b/src/backend/storage/aio/aio_init.c
@@ -18,6 +18,7 @@
 #include "storage/aio.h"
 #include "storage/aio_internal.h"
 #include "storage/aio_subsys.h"
+#include "storage/bufmgr.h"
 #include "storage/io_worker.h"
 #include "storage/ipc.h"
 #include "storage/proc.h"
@@ -72,15 +73,9 @@ AioHandleShmemSize(void)
 static Size
 AioHandleIOVShmemSize(void)
 {
-	/*
-	 * Each IO handle can have an PG_IOV_MAX long iovec.
-	 *
-	 * XXX: Right now the amount of space available for each IO is PG_IOV_MAX.
-	 * While it's tempting to use the io_combine_limit GUC, that's
-	 * PGC_USERSET, so we can't allocate shared memory based on that.
-	 */
+	/* each IO handle can have up to io_max_combine_limit iovec objects */
 	return mul_size(sizeof(struct iovec),
-					mul_size(mul_size(PG_IOV_MAX, AioProcs()),
+					mul_size(mul_size(io_max_combine_limit, AioProcs()),
 							 io_max_concurrency));
 }
 
@@ -89,7 +84,7 @@ AioHandleDataShmemSize(void)
 {
 	/* each buffer referenced by an iovec can have associated data */
 	return mul_size(sizeof(uint64),
-					mul_size(mul_size(PG_IOV_MAX, AioProcs()),
+					mul_size(mul_size(io_max_combine_limit, AioProcs()),
 							 io_max_concurrency));
 }
 
@@ -160,7 +155,7 @@ AioShmemInit(void)
 	bool		found;
 	uint32		io_handle_off = 0;
 	uint32		iovec_off = 0;
-	uint32		per_backend_iovecs = io_max_concurrency * PG_IOV_MAX;
+	uint32		per_backend_iovecs = io_max_concurrency * io_max_combine_limit;
 
 	pgaio_ctl = (PgAioCtl *)
 		ShmemInitStruct("AioCtl", AioCtlShmemSize(), &found);
@@ -213,7 +208,7 @@ AioShmemInit(void)
 			ConditionVariableInit(&ioh->cv);
 
 			dclist_push_tail(&bs->idle_ios, &ioh->node);
-			iovec_off += PG_IOV_MAX;
+			iovec_off += io_max_combine_limit;
 		}
 	}
 
diff --git a/src/backend/storage/buffer/bufmgr.c b/src/backend/storage/buffer/bufmgr.c
@@ -160,9 +160,12 @@ int			maintenance_io_concurrency = DEFAULT_MAINTENANCE_IO_CONCURRENCY;
 /*
  * Limit on how many blocks should be handled in single I/O operations.
  * StartReadBuffers() callers should respect it, as should other operations
- * that call smgr APIs directly.
+ * that call smgr APIs directly.  It is computed as the minimum of underlying
+ * GUCs io_combine_limit_guc and io_max_combine_limit.
  */
 int			io_combine_limit = DEFAULT_IO_COMBINE_LIMIT;
+int			io_combine_limit_guc = DEFAULT_IO_COMBINE_LIMIT;
+int			io_max_combine_limit = DEFAULT_IO_COMBINE_LIMIT;
 
 /*
  * GUC variables about triggering kernel writeback for buffers written; OS
diff --git a/src/backend/utils/misc/guc_tables.c b/src/backend/utils/misc/guc_tables.c
@@ -3252,6 +3252,20 @@ struct config_int ConfigureNamesInt[] =
 		NULL
 	},
 
+	{
+		{"io_max_combine_limit",
+			PGC_POSTMASTER,
+			RESOURCES_IO,
+			gettext_noop("Server-wide limit that clamps io_combine_limit."),
+			NULL,
+			GUC_UNIT_BLOCKS
+		},
+		&io_max_combine_limit,
+		DEFAULT_IO_COMBINE_LIMIT,
+		1, MAX_IO_COMBINE_LIMIT,
+		NULL, assign_io_max_combine_limit, NULL
+	},
+
 	{
 		{"io_combine_limit",
 			PGC_USERSET,
@@ -3263,7 +3277,7 @@ struct config_int ConfigureNamesInt[] =
 		&io_combine_limit,
 		DEFAULT_IO_COMBINE_LIMIT,
 		1, MAX_IO_COMBINE_LIMIT,
-		NULL, NULL, NULL
+		NULL, assign_io_combine_limit, NULL
 	},
 
 	{
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
@@ -200,6 +200,8 @@
 #backend_flush_after = 0		# measured in pages, 0 disables
 #effective_io_concurrency = 16		# 1-1000; 0 disables prefetching
 #maintenance_io_concurrency = 16	# 1-1000; 0 disables prefetching
+#io_max_combine_limit = 128kB		# usually 1-32 blocks (depends on OS)
+					# (change requires restart)
 #io_combine_limit = 128kB		# usually 1-32 blocks (depends on OS)
 
 #io_method = worker			# worker, sync (change requires restart)
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
@@ -163,7 +163,9 @@ extern PGDLLIMPORT int maintenance_io_concurrency;
 
 #define MAX_IO_COMBINE_LIMIT PG_IOV_MAX
 #define DEFAULT_IO_COMBINE_LIMIT Min(MAX_IO_COMBINE_LIMIT, (128 * 1024) / BLCKSZ)
-extern PGDLLIMPORT int io_combine_limit;
+extern PGDLLIMPORT int io_combine_limit;	/* min of the two GUCs below */
+extern PGDLLIMPORT int io_combine_limit_guc;
+extern PGDLLIMPORT int io_max_combine_limit;
 
 extern PGDLLIMPORT int checkpoint_flush_after;
 extern PGDLLIMPORT int backend_flush_after;
diff --git a/src/include/utils/guc_hooks.h b/src/include/utils/guc_hooks.h
@@ -86,6 +86,8 @@ extern const char *show_log_timezone(void);
 extern bool check_maintenance_io_concurrency(int *newval, void **extra,
 											 GucSource source);
 extern void assign_maintenance_io_concurrency(int newval, void *extra);
+extern void assign_io_max_combine_limit(int newval, void *extra);
+extern void assign_io_combine_limit(int newval, void *extra);
 extern bool check_max_slot_wal_keep_size(int *newval, void **extra,
 										 GucSource source);
 extern void assign_max_wal_size(int newval, void *extra);
