Just-in-time background writing strategy. This code avoids re-scanning

buffers that cannot possibly need to be cleaned, and estimates how many
buffers it should try to clean based on moving averages of recent allocation
requests and density of reusable buffers.  The patch also adds a couple
more columns to pg_stat_bgwriter to help measure the effectiveness of the
bgwriter.

Greg Smith, building on his own work and ideas from several other people,
in particular a much older patch from Itagaki Takahiro.

doc/src/sgml/config.sgml

-<!-- $PostgreSQL: pgsql/doc/src/sgml/config.sgml,v 1.146 2007/09/24 03:12:23 tgl Exp $ -->
+<!-- $PostgreSQL: pgsql/doc/src/sgml/config.sgml,v 1.147 2007/09/25 20:03:37 tgl Exp $ -->
 
 <chapter Id="runtime-config">
   <title>Server Configuration</title>
@@ -1205,35 +1205,42 @@ SET ENABLE_SEQSCAN TO OFF;
        </listitem>
       </varlistentry>
 
-      <varlistentry id="guc-bgwriter-lru-percent" xreflabel="bgwriter_lru_percent">
-       <term><varname>bgwriter_lru_percent</varname> (<type>floating point</type>)</term>
+      <varlistentry id="guc-bgwriter-lru-maxpages" xreflabel="bgwriter_lru_maxpages">
+       <term><varname>bgwriter_lru_maxpages</varname> (<type>integer</type>)</term>
        <indexterm>
-        <primary><varname>bgwriter_lru_percent</> configuration parameter</primary>
+        <primary><varname>bgwriter_lru_maxpages</> configuration parameter</primary>
        </indexterm>
        <listitem>
         <para>
-         To reduce the probability that server processes will need to issue
-         their own writes, the background writer tries to write buffers that
-         are likely to be recycled soon.  In each round, it examines up to
-         <varname>bgwriter_lru_percent</> of the buffers that are nearest to
-         being recycled, and writes any that are dirty.
-         The default value is 1.0 (1% of the total number of shared buffers).
+         In each round, no more than this many buffers will be written
+         by the background writer.  Setting this to zero disables
+         background writing (except for checkpoint activity).
+         The default value is 100 buffers.
          This parameter can only be set in the <filename>postgresql.conf</>
          file or on the server command line.
         </para>
        </listitem>
       </varlistentry>
 
-      <varlistentry id="guc-bgwriter-lru-maxpages" xreflabel="bgwriter_lru_maxpages">
-       <term><varname>bgwriter_lru_maxpages</varname> (<type>integer</type>)</term>
+      <varlistentry id="guc-bgwriter-lru-multiplier" xreflabel="bgwriter_lru_multiplier">
+       <term><varname>bgwriter_lru_multiplier</varname> (<type>floating point</type>)</term>
        <indexterm>
-        <primary><varname>bgwriter_lru_maxpages</> configuration parameter</primary>
+        <primary><varname>bgwriter_lru_multiplier</> configuration parameter</primary>
        </indexterm>
        <listitem>
         <para>
-         In each round, no more than this many buffers will be written
-         as a result of scanning soon-to-be-recycled buffers.
-         The default value is five buffers.
+         Unless limited by <varname>bgwriter_lru_maxpages</>, the number
+         of dirty buffers written in each round is determined by reference
+         to the number of new buffers that have been needed by server
+         processes during recent rounds.  This number is multiplied by
+         <varname>bgwriter_lru_multiplier</> to arrive at the estimate
+         of the number of buffers that will be needed during the next round.
+         Thus, a setting of 1.0 represents a <quote>just in time</> policy
+         of writing exactly the number of buffers predicted to be needed.
+         Larger values provide some cushion against spikes in demand,
+         while smaller values intentionally leave writes to be done by
+         server processes.
+         The default is 2.0.
          This parameter can only be set in the <filename>postgresql.conf</>
          file or on the server command line.
         </para>
@@ -1242,8 +1249,8 @@ SET ENABLE_SEQSCAN TO OFF;
      </variablelist>
 
      <para>
-      Smaller values of <varname>bgwriter_lru_percent</varname> and
-      <varname>bgwriter_lru_maxpages</varname> reduce the extra I/O load
+      Smaller values of <varname>bgwriter_lru_maxpages</varname> and
+      <varname>bgwriter_lru_multiplier</varname> reduce the extra I/O load
       caused by the background writer, but make it more likely that server
       processes will have to issue writes for themselves, delaying interactive
       queries.

doc/src/sgml/monitoring.sgml

-<!-- $PostgreSQL: pgsql/doc/src/sgml/monitoring.sgml,v 1.53 2007/09/24 03:12:23 tgl Exp $ -->
+<!-- $PostgreSQL: pgsql/doc/src/sgml/monitoring.sgml,v 1.54 2007/09/25 20:03:37 tgl Exp $ -->
 
 <chapter id="monitoring">
  <title>Monitoring Database Activity</title>
@@ -237,7 +237,10 @@ postgres: <replaceable>user</> <replaceable>database</> <replaceable>host</> <re
       background writer: number of scheduled checkpoints, requested
       checkpoints, buffers written by checkpoints and cleaning scans,
       and the number of times the bgwriter stopped a cleaning scan
-      because it had written too many buffers.
+      because it had written too many buffers.  Also includes
+      statistics about the shared buffer pool, including buffers written
+      by backends (that is, not by the background writer) and total buffers
+      allocated.
      </entry>
      </row>
 
@@ -817,6 +820,23 @@ postgres: <replaceable>user</> <replaceable>database</> <replaceable>host</> <re
       </entry>
      </row>
 
+     <row>
+      <entry><literal><function>pg_stat_get_buf_written_backend</function>()</literal></entry>
+      <entry><type>bigint</type></entry>
+      <entry>
+       The number of buffers written by backends because they needed
+       to allocate a new buffer
+      </entry>
+     </row>
+
+     <row>
+      <entry><literal><function>pg_stat_get_buf_alloc</function>()</literal></entry>
+      <entry><type>bigint</type></entry>
+      <entry>
+       The total number of buffer allocations
+      </entry>
+     </row>
+
      <row>
       <entry><literal><function>pg_stat_clear_snapshot</function>()</literal></entry>
       <entry><type>void</type></entry>

src/backend/catalog/system_views.sql

@@ -3,7 +3,7 @@
  *
  * Copyright (c) 1996-2007, PostgreSQL Global Development Group
  *
- * $PostgreSQL: pgsql/src/backend/catalog/system_views.sql,v 1.45 2007/09/20 17:56:30 tgl Exp $
+ * $PostgreSQL: pgsql/src/backend/catalog/system_views.sql,v 1.46 2007/09/25 20:03:37 tgl Exp $
  */
 
 CREATE VIEW pg_roles AS 
@@ -382,7 +382,9 @@ CREATE VIEW pg_stat_bgwriter AS
         pg_stat_get_bgwriter_requested_checkpoints() AS checkpoints_req,
         pg_stat_get_bgwriter_buf_written_checkpoints() AS buffers_checkpoint,
         pg_stat_get_bgwriter_buf_written_clean() AS buffers_clean,
-        pg_stat_get_bgwriter_maxwritten_clean() AS maxwritten_clean;
+        pg_stat_get_bgwriter_maxwritten_clean() AS maxwritten_clean,
+        pg_stat_get_buf_written_backend() AS buffers_backend,
+        pg_stat_get_buf_alloc() AS buffers_alloc;
 
 -- Tsearch debug function. Defined here because it'd be pretty unwieldy
 -- to put it into pg_proc.h

src/backend/postmaster/bgwriter.c

@@ -37,7 +37,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/postmaster/bgwriter.c,v 1.43 2007/09/16 16:33:04 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/postmaster/bgwriter.c,v 1.44 2007/09/25 20:03:37 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -98,8 +98,14 @@
  * requesting backends since the last checkpoint start.  The flags are
  * chosen so that OR'ing is the correct way to combine multiple requests.
  *
+ * num_backend_writes is used to count the number of buffer writes performed
+ * by non-bgwriter processes.  This counter should be wide enough that it
+ * can't overflow during a single bgwriter cycle.
+ *
  * The requests array holds fsync requests sent by backends and not yet
- * absorbed by the bgwriter.  Unlike the checkpoint fields, the requests
+ * absorbed by the bgwriter.
+ *
+ * Unlike the checkpoint fields, num_backend_writes and the requests
  * fields are protected by BgWriterCommLock.
  *----------
  */
@@ -122,6 +128,8 @@ typedef struct
 
 	int			ckpt_flags;		/* checkpoint flags, as defined in xlog.h */
 
+	uint32		num_backend_writes;	/* counts non-bgwriter buffer writes */
+
 	int			num_requests;	/* current # of requests */
 	int			max_requests;	/* allocated array size */
 	BgWriterRequest requests[1];	/* VARIABLE LENGTH ARRAY */
@@ -566,8 +574,7 @@ BgWriterNap(void)
 	 *
 	 * We absorb pending requests after each short sleep.
 	 */
-	if ((bgwriter_lru_percent > 0.0 && bgwriter_lru_maxpages > 0) ||
-		ckpt_active)
+	if (bgwriter_lru_maxpages > 0 || ckpt_active)
 		udelay = BgWriterDelay * 1000L;
 	else if (XLogArchiveTimeout > 0)
 		udelay = 1000000L;	/* One second */
@@ -648,12 +655,13 @@ CheckpointWriteDelay(int flags, double progress)
 			got_SIGHUP = false;
 			ProcessConfigFile(PGC_SIGHUP);
 		}
-		BgBufferSync();
-		CheckArchiveTimeout();
-		BgWriterNap();
 
 		AbsorbFsyncRequests();
 		absorb_counter = WRITES_PER_ABSORB;
+
+		BgBufferSync();
+		CheckArchiveTimeout();
+		BgWriterNap();
 	}
 	else if (--absorb_counter <= 0)
 	{
@@ -963,7 +971,8 @@ RequestCheckpoint(int flags)
  * Whenever a backend is compelled to write directly to a relation
  * (which should be seldom, if the bgwriter is getting its job done),
  * the backend calls this routine to pass over knowledge that the relation
- * is dirty and must be fsync'd before next checkpoint.
+ * is dirty and must be fsync'd before next checkpoint.  We also use this
+ * opportunity to count such writes for statistical purposes.
  *
  * segno specifies which segment (not block!) of the relation needs to be
  * fsync'd.  (Since the valid range is much less than BlockNumber, we can
@@ -987,7 +996,13 @@ ForwardFsyncRequest(RelFileNode rnode, BlockNumber segno)
 	if (!IsUnderPostmaster)
 		return false;			/* probably shouldn't even get here */
 
+	Assert(!am_bg_writer);
+
 	LWLockAcquire(BgWriterCommLock, LW_EXCLUSIVE);
+
+	/* we count non-bgwriter writes even when the request queue overflows */
+	BgWriterShmem->num_backend_writes++;
+
 	if (BgWriterShmem->bgwriter_pid == 0 ||
 		BgWriterShmem->num_requests >= BgWriterShmem->max_requests)
 	{
@@ -1035,6 +1050,10 @@ AbsorbFsyncRequests(void)
 	 */
 	LWLockAcquire(BgWriterCommLock, LW_EXCLUSIVE);
 
+	/* Transfer write count into pending pgstats message */
+	BgWriterStats.m_buf_written_backend += BgWriterShmem->num_backend_writes;
+	BgWriterShmem->num_backend_writes = 0;
+
 	n = BgWriterShmem->num_requests;
 	if (n > 0)
 	{

src/backend/postmaster/pgstat.c

@@ -13,7 +13,7 @@
  *
  *	Copyright (c) 2001-2007, PostgreSQL Global Development Group
  *
- *	$PostgreSQL: pgsql/src/backend/postmaster/pgstat.c,v 1.165 2007/09/24 03:12:23 tgl Exp $
+ *	$PostgreSQL: pgsql/src/backend/postmaster/pgstat.c,v 1.166 2007/09/25 20:03:37 tgl Exp $
  * ----------
  */
 #include "postgres.h"
@@ -3165,4 +3165,6 @@ pgstat_recv_bgwriter(PgStat_MsgBgWriter *msg, int len)
 	globalStats.buf_written_checkpoints += msg->m_buf_written_checkpoints;
 	globalStats.buf_written_clean += msg->m_buf_written_clean;
 	globalStats.maxwritten_clean += msg->m_maxwritten_clean;
+	globalStats.buf_written_backend += msg->m_buf_written_backend;
+	globalStats.buf_alloc += msg->m_buf_alloc;
 }

src/backend/storage/buffer/freelist.c

@@ -9,7 +9,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/storage/buffer/freelist.c,v 1.60 2007/06/08 18:23:52 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/storage/buffer/freelist.c,v 1.61 2007/09/25 20:03:38 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -34,6 +34,13 @@ typedef struct
 	 * NOTE: lastFreeBuffer is undefined when firstFreeBuffer is -1 (that is,
 	 * when the list is empty)
 	 */
+
+	/*
+	 * Statistics.  These counters should be wide enough that they can't
+	 * overflow during a single bgwriter cycle.
+	 */
+	uint32		completePasses;		/* Complete cycles of the clock sweep */
+	uint32		numBufferAllocs;	/* Buffers allocated since last reset */
 } BufferStrategyControl;
 
 /* Pointers to shared state */
@@ -118,6 +125,13 @@ StrategyGetBuffer(BufferAccessStrategy strategy, bool *lock_held)
 	*lock_held = true;
 	LWLockAcquire(BufFreelistLock, LW_EXCLUSIVE);
 
+	/*
+	 * We count buffer allocation requests so that the bgwriter can estimate
+	 * the rate of buffer consumption.  Note that buffers recycled by a
+	 * strategy object are intentionally not counted here.
+	 */
+	StrategyControl->numBufferAllocs++;
+
 	/*
 	 * Try to get a buffer from the freelist.  Note that the freeNext fields
 	 * are considered to be protected by the BufFreelistLock not the
@@ -157,7 +171,10 @@ StrategyGetBuffer(BufferAccessStrategy strategy, bool *lock_held)
 		buf = &BufferDescriptors[StrategyControl->nextVictimBuffer];
 
 		if (++StrategyControl->nextVictimBuffer >= NBuffers)
+		{
 			StrategyControl->nextVictimBuffer = 0;
+			StrategyControl->completePasses++;
+		}
 
 		/*
 		 * If the buffer is pinned or has a nonzero usage_count, we cannot use
@@ -226,18 +243,26 @@ StrategyFreeBuffer(volatile BufferDesc *buf)
  *
  * The result is the buffer index of the best buffer to sync first.
  * BufferSync() will proceed circularly around the buffer array from there.
+ *
+ * In addition, we return the completed-pass count (which is effectively
+ * the higher-order bits of nextVictimBuffer) and the count of recent buffer
+ * allocs if non-NULL pointers are passed.  The alloc count is reset after
+ * being read.
  */
 int
-StrategySyncStart(void)
+StrategySyncStart(uint32 *complete_passes, uint32 *num_buf_alloc)
 {
 	int			result;
 
-	/*
-	 * We could probably dispense with the locking here, but just to be safe
-	 * ...
-	 */
 	LWLockAcquire(BufFreelistLock, LW_EXCLUSIVE);
 	result = StrategyControl->nextVictimBuffer;
+	if (complete_passes)
+		*complete_passes = StrategyControl->completePasses;
+	if (num_buf_alloc)
+	{
+		*num_buf_alloc = StrategyControl->numBufferAllocs;
+		StrategyControl->numBufferAllocs = 0;
+	}
 	LWLockRelease(BufFreelistLock);
 	return result;
 }
@@ -313,6 +338,10 @@ StrategyInitialize(bool init)
 
 		/* Initialize the clock sweep pointer */
 		StrategyControl->nextVictimBuffer = 0;
+
+		/* Clear statistics */
+		StrategyControl->completePasses = 0;
+		StrategyControl->numBufferAllocs = 0;
 	}
 	else
 		Assert(!init);

src/backend/utils/adt/pgstatfuncs.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/adt/pgstatfuncs.c,v 1.45 2007/09/20 17:56:31 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/adt/pgstatfuncs.c,v 1.46 2007/09/25 20:03:38 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -67,6 +67,8 @@ extern Datum pg_stat_get_bgwriter_requested_checkpoints(PG_FUNCTION_ARGS);
 extern Datum pg_stat_get_bgwriter_buf_written_checkpoints(PG_FUNCTION_ARGS);
 extern Datum pg_stat_get_bgwriter_buf_written_clean(PG_FUNCTION_ARGS);
 extern Datum pg_stat_get_bgwriter_maxwritten_clean(PG_FUNCTION_ARGS);
+extern Datum pg_stat_get_buf_written_backend(PG_FUNCTION_ARGS);
+extern Datum pg_stat_get_buf_alloc(PG_FUNCTION_ARGS);
 
 extern Datum pg_stat_clear_snapshot(PG_FUNCTION_ARGS);
 extern Datum pg_stat_reset(PG_FUNCTION_ARGS);
@@ -813,6 +815,18 @@ pg_stat_get_bgwriter_maxwritten_clean(PG_FUNCTION_ARGS)
 	PG_RETURN_INT64(pgstat_fetch_global()->maxwritten_clean);
 }
 
+Datum
+pg_stat_get_buf_written_backend(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_INT64(pgstat_fetch_global()->buf_written_backend);
+}
+
+Datum
+pg_stat_get_buf_alloc(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_INT64(pgstat_fetch_global()->buf_alloc);
+}
+
 
 /* Discard the active statistics snapshot */
 Datum

src/backend/utils/misc/guc.c

@@ -10,7 +10,7 @@
  * Written by Peter Eisentraut <peter_e@gmx.net>.
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/misc/guc.c,v 1.421 2007/09/24 03:12:23 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/misc/guc.c,v 1.422 2007/09/25 20:03:38 tgl Exp $
  *
  *--------------------------------------------------------------------
  */
@@ -1574,7 +1574,7 @@ static struct config_int ConfigureNamesInt[] =
 			NULL
 		},
 		&bgwriter_lru_maxpages,
-		5, 0, 1000, NULL, NULL
+		100, 0, 1000, NULL, NULL
 	},
 
 	{
@@ -1821,12 +1821,12 @@ static struct config_real ConfigureNamesReal[] =
 	},
 
 	{
-		{"bgwriter_lru_percent", PGC_SIGHUP, RESOURCES,
-			gettext_noop("Background writer percentage of LRU buffers to flush per round."),
+		{"bgwriter_lru_multiplier", PGC_SIGHUP, RESOURCES,
+			gettext_noop("Background writer multiplier on average buffers to scan per round."),
 			NULL
 		},
-		&bgwriter_lru_percent,
-		1.0, 0.0, 100.0, NULL, NULL
+		&bgwriter_lru_multiplier,
+		2.0, 0.0, 10.0, NULL, NULL
 	},
 
 	{

src/backend/utils/misc/postgresql.conf.sample

@@ -138,8 +138,8 @@
 # - Background writer -
 
 #bgwriter_delay = 200ms			# 10-10000ms between rounds
-#bgwriter_lru_percent = 1.0		# 0-100% of LRU buffers scanned/round
-#bgwriter_lru_maxpages = 5		# 0-1000 buffers max written/round
+#bgwriter_lru_maxpages = 100		# 0-1000 max buffers written/round
+#bgwriter_lru_multiplier = 2.0		# 0-10.0 multipler on buffers scanned/round
 
 
 #---------------------------------------------------------------------------

src/include/catalog/catversion.h

@@ -37,7 +37,7 @@
  * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/catversion.h,v 1.427 2007/09/21 21:25:42 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/catversion.h,v 1.428 2007/09/25 20:03:38 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -53,6 +53,6 @@
  */
 
 /*							yyyymmddN */
-#define CATALOG_VERSION_NO	200709211
+#define CATALOG_VERSION_NO	200709241
 
 #endif

src/include/catalog/pg_proc.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/pg_proc.h,v 1.472 2007/09/24 01:29:29 adunstan Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/pg_proc.h,v 1.473 2007/09/25 20:03:38 tgl Exp $
  *
  * NOTES
  *	  The script catalog/genbki.sh reads this file and generates .bki
@@ -2942,6 +2942,11 @@ DATA(insert OID = 2772 ( pg_stat_get_bgwriter_buf_written_clean PGNSP PGUID 12 1
 DESCR("statistics: number of buffers written by the bgwriter for cleaning dirty buffers");
 DATA(insert OID = 2773 ( pg_stat_get_bgwriter_maxwritten_clean PGNSP PGUID 12 1 0 f f t f s 0 20 "" _null_ _null_ _null_ pg_stat_get_bgwriter_maxwritten_clean - _null_ _null_ ));
 DESCR("statistics: number of times the bgwriter stopped processing when it had written too many buffers while cleaning");
+DATA(insert OID = 2775 ( pg_stat_get_buf_written_backend PGNSP PGUID 12 1 0 f f t f s 0 20 "" _null_ _null_ _null_ pg_stat_get_buf_written_backend - _null_ _null_ ));
+DESCR("statistics: number of buffers written by backends");
+DATA(insert OID = 2859 ( pg_stat_get_buf_alloc			PGNSP PGUID 12 1 0 f f t f s 0 20 "" _null_ _null_ _null_ pg_stat_get_buf_alloc - _null_ _null_ ));
+DESCR("statistics: number of buffer allocations");
+
 DATA(insert OID = 2230 (  pg_stat_clear_snapshot		PGNSP PGUID 12 1 0 f f f f v 0 2278  "" _null_ _null_ _null_	pg_stat_clear_snapshot - _null_ _null_ ));
 DESCR("statistics: discard current transaction's statistics snapshot");
 DATA(insert OID = 2274 (  pg_stat_reset					PGNSP PGUID 12 1 0 f f f f v 0 2278  "" _null_ _null_ _null_	pg_stat_reset - _null_ _null_ ));

src/include/pgstat.h

@@ -5,7 +5,7 @@
  *
  *	Copyright (c) 2001-2007, PostgreSQL Global Development Group
  *
- *	$PostgreSQL: pgsql/src/include/pgstat.h,v 1.67 2007/09/24 03:12:23 tgl Exp $
+ *	$PostgreSQL: pgsql/src/include/pgstat.h,v 1.68 2007/09/25 20:03:38 tgl Exp $
  * ----------
  */
 #ifndef PGSTAT_H
@@ -294,6 +294,8 @@ typedef struct PgStat_MsgBgWriter
 	PgStat_Counter	m_buf_written_checkpoints;
 	PgStat_Counter	m_buf_written_clean;
 	PgStat_Counter	m_maxwritten_clean;
+	PgStat_Counter  m_buf_written_backend;
+	PgStat_Counter  m_buf_alloc;
 } PgStat_MsgBgWriter;
 
 
@@ -394,6 +396,8 @@ typedef struct PgStat_GlobalStats
 	PgStat_Counter  buf_written_checkpoints;
 	PgStat_Counter  buf_written_clean;
 	PgStat_Counter  maxwritten_clean;
+	PgStat_Counter  buf_written_backend;
+	PgStat_Counter  buf_alloc;
 } PgStat_GlobalStats;
 
 

src/include/storage/buf_internals.h

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/storage/buf_internals.h,v 1.92 2007/07/25 12:22:53 mha Exp $
+ * $PostgreSQL: pgsql/src/include/storage/buf_internals.h,v 1.93 2007/09/25 20:03:38 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -188,7 +188,7 @@ extern void StrategyFreeBuffer(volatile BufferDesc *buf);
 extern bool StrategyRejectBuffer(BufferAccessStrategy strategy,
 								 volatile BufferDesc *buf);
 
-extern int	StrategySyncStart(void);
+extern int	StrategySyncStart(uint32 *complete_passes, uint32 *num_buf_alloc);
 extern Size StrategyShmemSize(void);
 extern void StrategyInitialize(bool init);
 

src/include/storage/bufmgr.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/storage/bufmgr.h,v 1.107 2007/09/20 17:56:32 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/storage/bufmgr.h,v 1.108 2007/09/25 20:03:38 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -32,8 +32,8 @@ extern PGDLLIMPORT int NBuffers;
 
 /* in bufmgr.c */
 extern bool zero_damaged_pages;
-extern double bgwriter_lru_percent;
 extern int	bgwriter_lru_maxpages;
+extern double bgwriter_lru_multiplier;
 
 /* in buf_init.c */
 extern PGDLLIMPORT char *BufferBlocks;

src/test/regress/expected/rules.out

@@ -1292,7 +1292,7 @@ SELECT viewname, definition FROM pg_views WHERE schemaname <> 'information_schem
  pg_stat_activity         | SELECT d.oid AS datid, d.datname, pg_stat_get_backend_pid(s.backendid) AS procpid, pg_stat_get_backend_userid(s.backendid) AS usesysid, u.rolname AS usename, pg_stat_get_backend_activity(s.backendid) AS current_query, pg_stat_get_backend_waiting(s.backendid) AS waiting, pg_stat_get_backend_xact_start(s.backendid) AS xact_start, pg_stat_get_backend_activity_start(s.backendid) AS query_start, pg_stat_get_backend_start(s.backendid) AS backend_start, pg_stat_get_backend_client_addr(s.backendid) AS client_addr, pg_stat_get_backend_client_port(s.backendid) AS client_port FROM pg_database d, (SELECT pg_stat_get_backend_idset() AS backendid) s, pg_authid u WHERE ((pg_stat_get_backend_dbid(s.backendid) = d.oid) AND (pg_stat_get_backend_userid(s.backendid) = u.oid));
  pg_stat_all_indexes      | SELECT c.oid AS relid, i.oid AS indexrelid, n.nspname AS schemaname, c.relname, i.relname AS indexrelname, pg_stat_get_numscans(i.oid) AS idx_scan, pg_stat_get_tuples_returned(i.oid) AS idx_tup_read, pg_stat_get_tuples_fetched(i.oid) AS idx_tup_fetch FROM (((pg_class c JOIN pg_index x ON ((c.oid = x.indrelid))) JOIN pg_class i ON ((i.oid = x.indexrelid))) LEFT JOIN pg_namespace n ON ((n.oid = c.relnamespace))) WHERE (c.relkind = ANY (ARRAY['r'::"char", 't'::"char"]));
  pg_stat_all_tables       | SELECT c.oid AS relid, n.nspname AS schemaname, c.relname, pg_stat_get_numscans(c.oid) AS seq_scan, pg_stat_get_tuples_returned(c.oid) AS seq_tup_read, (sum(pg_stat_get_numscans(i.indexrelid)))::bigint AS idx_scan, ((sum(pg_stat_get_tuples_fetched(i.indexrelid)))::bigint + pg_stat_get_tuples_fetched(c.oid)) AS idx_tup_fetch, pg_stat_get_tuples_inserted(c.oid) AS n_tup_ins, pg_stat_get_tuples_updated(c.oid) AS n_tup_upd, pg_stat_get_tuples_deleted(c.oid) AS n_tup_del, pg_stat_get_tuples_hot_updated(c.oid) AS n_tup_hot_upd, pg_stat_get_live_tuples(c.oid) AS n_live_tup, pg_stat_get_dead_tuples(c.oid) AS n_dead_tup, pg_stat_get_last_vacuum_time(c.oid) AS last_vacuum, pg_stat_get_last_autovacuum_time(c.oid) AS last_autovacuum, pg_stat_get_last_analyze_time(c.oid) AS last_analyze, pg_stat_get_last_autoanalyze_time(c.oid) AS last_autoanalyze FROM ((pg_class c LEFT JOIN pg_index i ON ((c.oid = i.indrelid))) LEFT JOIN pg_namespace n ON ((n.oid = c.relnamespace))) WHERE (c.relkind = ANY (ARRAY['r'::"char", 't'::"char"])) GROUP BY c.oid, n.nspname, c.relname;
- pg_stat_bgwriter         | SELECT pg_stat_get_bgwriter_timed_checkpoints() AS checkpoints_timed, pg_stat_get_bgwriter_requested_checkpoints() AS checkpoints_req, pg_stat_get_bgwriter_buf_written_checkpoints() AS buffers_checkpoint, pg_stat_get_bgwriter_buf_written_clean() AS buffers_clean, pg_stat_get_bgwriter_maxwritten_clean() AS maxwritten_clean;
+ pg_stat_bgwriter         | SELECT pg_stat_get_bgwriter_timed_checkpoints() AS checkpoints_timed, pg_stat_get_bgwriter_requested_checkpoints() AS checkpoints_req, pg_stat_get_bgwriter_buf_written_checkpoints() AS buffers_checkpoint, pg_stat_get_bgwriter_buf_written_clean() AS buffers_clean, pg_stat_get_bgwriter_maxwritten_clean() AS maxwritten_clean, pg_stat_get_buf_written_backend() AS buffers_backend, pg_stat_get_buf_alloc() AS buffers_alloc;
  pg_stat_database         | SELECT d.oid AS datid, d.datname, pg_stat_get_db_numbackends(d.oid) AS numbackends, pg_stat_get_db_xact_commit(d.oid) AS xact_commit, pg_stat_get_db_xact_rollback(d.oid) AS xact_rollback, (pg_stat_get_db_blocks_fetched(d.oid) - pg_stat_get_db_blocks_hit(d.oid)) AS blks_read, pg_stat_get_db_blocks_hit(d.oid) AS blks_hit, pg_stat_get_db_tuples_returned(d.oid) AS tup_returned, pg_stat_get_db_tuples_fetched(d.oid) AS tup_fetched, pg_stat_get_db_tuples_inserted(d.oid) AS tup_inserted, pg_stat_get_db_tuples_updated(d.oid) AS tup_updated, pg_stat_get_db_tuples_deleted(d.oid) AS tup_deleted FROM pg_database d;
  pg_stat_sys_indexes      | SELECT pg_stat_all_indexes.relid, pg_stat_all_indexes.indexrelid, pg_stat_all_indexes.schemaname, pg_stat_all_indexes.relname, pg_stat_all_indexes.indexrelname, pg_stat_all_indexes.idx_scan, pg_stat_all_indexes.idx_tup_read, pg_stat_all_indexes.idx_tup_fetch FROM pg_stat_all_indexes WHERE ((pg_stat_all_indexes.schemaname = ANY (ARRAY['pg_catalog'::name, 'information_schema'::name])) OR (pg_stat_all_indexes.schemaname ~ '^pg_toast'::text));
  pg_stat_sys_tables       | SELECT pg_stat_all_tables.relid, pg_stat_all_tables.schemaname, pg_stat_all_tables.relname, pg_stat_all_tables.seq_scan, pg_stat_all_tables.seq_tup_read, pg_stat_all_tables.idx_scan, pg_stat_all_tables.idx_tup_fetch, pg_stat_all_tables.n_tup_ins, pg_stat_all_tables.n_tup_upd, pg_stat_all_tables.n_tup_del, pg_stat_all_tables.n_tup_hot_upd, pg_stat_all_tables.n_live_tup, pg_stat_all_tables.n_dead_tup, pg_stat_all_tables.last_vacuum, pg_stat_all_tables.last_autovacuum, pg_stat_all_tables.last_analyze, pg_stat_all_tables.last_autoanalyze FROM pg_stat_all_tables WHERE ((pg_stat_all_tables.schemaname = ANY (ARRAY['pg_catalog'::name, 'information_schema'::name])) OR (pg_stat_all_tables.schemaname ~ '^pg_toast'::text));