Start background writer during archive recovery. Background writer now performs

its usual buffer cleaning duties during archive recovery, and it's responsible
for performing restartpoints.

This requires some changes in postmaster. When the startup process has done
all the initialization and is ready to start WAL redo, it signals the
postmaster to launch the background writer. The postmaster is signaled again
when the point in recovery is reached where we know that the database is in
consistent state. Postmaster isn't interested in that at the moment, but
that's the point where we could let other backends in to perform read-only
queries. The postmaster is signaled third time when the recovery has ended,
so that postmaster knows that it's safe to start accepting connections.

The startup process now traps SIGTERM, and performs a "clean" shutdown. If
you do a fast shutdown during recovery, a shutdown restartpoint is performed,
like a shutdown checkpoint, and postmaster kills the processes cleanly. You
still have to continue the recovery at next startup, though.

Currently, the background writer is only launched during archive recovery.
We could launch it during crash recovery as well, but it seems better to keep
that codepath as simple as possible, for the sake of robustness. And it
couldn't do any restartpoints during crash recovery anyway, so it wouldn't be
that useful.

log_restartpoints is gone. Use log_checkpoints instead. This is yet to be
documented.

This whole operation is a pre-requisite for Hot Standby, but has some value of
its own whether the hot standby patch makes 8.4 or not.

Simon Riggs, with lots of modifications by me.

src/backend/bootstrap/bootstrap.c

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/bootstrap/bootstrap.c,v 1.249 2009/01/22 20:16:00 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/bootstrap/bootstrap.c,v 1.250 2009/02/18 15:58:41 heikki Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -37,7 +37,6 @@
 #include "storage/proc.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
-#include "utils/flatfiles.h"
 #include "utils/fmgroids.h"
 #include "utils/memutils.h"
 #include "utils/ps_status.h"
@@ -416,14 +415,12 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			bootstrap_signals();
-			StartupXLOG();
-			BuildFlatFiles(false);
-			proc_exit(0);		/* startup done */
+			/* don't set signals, startup process has its own agenda */
+			StartupProcessMain();
+			proc_exit(1);		/* should never return */
 
 		case BgWriterProcess:
 			/* don't set signals, bgwriter has its own agenda */
-			InitXLOGAccess();
 			BackgroundWriterMain();
 			proc_exit(1);		/* should never return */
 

src/backend/postmaster/bgwriter.c

@@ -37,7 +37,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/postmaster/bgwriter.c,v 1.55 2009/01/01 17:23:46 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/postmaster/bgwriter.c,v 1.56 2009/02/18 15:58:41 heikki Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -49,6 +49,7 @@
 #include <unistd.h>
 
 #include "access/xlog_internal.h"
+#include "catalog/pg_control.h"
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
@@ -423,9 +424,19 @@ BackgroundWriterMain(void)
 		 */
 		if (do_checkpoint)
 		{
+			bool	ckpt_performed = false;
+			bool	do_restartpoint;
+
 			/* use volatile pointer to prevent code rearrangement */
 			volatile BgWriterShmemStruct *bgs = BgWriterShmem;
 
+			/*
+			 * Check if we should perform a checkpoint or a restartpoint.
+			 * As a side-effect, RecoveryInProgress() initializes
+			 * TimeLineID if it's not set yet.
+			 */
+			do_restartpoint = RecoveryInProgress();
+
 			/*
 			 * Atomically fetch the request flags to figure out what kind of a
 			 * checkpoint we should perform, and increase the started-counter
@@ -444,7 +455,8 @@ BackgroundWriterMain(void)
 			 * implementation will not generate warnings caused by
 			 * CheckPointTimeout < CheckPointWarning.
 			 */
-			if ((flags & CHECKPOINT_CAUSE_XLOG) &&
+			if (!do_restartpoint &&
+				(flags & CHECKPOINT_CAUSE_XLOG) &&
 				elapsed_secs < CheckPointWarning)
 				ereport(LOG,
 						(errmsg("checkpoints are occurring too frequently (%d seconds apart)",
@@ -455,6 +467,7 @@ BackgroundWriterMain(void)
 			 * Initialize bgwriter-private variables used during checkpoint.
 			 */
 			ckpt_active = true;
+			if (!do_restartpoint)
 				ckpt_start_recptr = GetInsertRecPtr();
 			ckpt_start_time = now;
 			ckpt_cached_elapsed = 0;
@@ -462,7 +475,13 @@ BackgroundWriterMain(void)
 			/*
 			 * Do the checkpoint.
 			 */
+			if (!do_restartpoint)
+			{
 				CreateCheckPoint(flags);
+				ckpt_performed = true;
+			}
+			else
+				ckpt_performed = CreateRestartPoint(flags);
 
 			/*
 			 * After any checkpoint, close all smgr files.	This is so we
@@ -477,15 +496,28 @@ BackgroundWriterMain(void)
 			bgs->ckpt_done = bgs->ckpt_started;
 			SpinLockRelease(&bgs->ckpt_lck);
 
-			ckpt_active = false;
-
+			if (ckpt_performed)
+			{
 				/*
 				 * Note we record the checkpoint start time not end time as
-			 * last_checkpoint_time.  This is so that time-driven checkpoints
-			 * happen at a predictable spacing.
+				 * last_checkpoint_time.  This is so that time-driven
+				 * checkpoints happen at a predictable spacing.
 				 */
 				last_checkpoint_time = now;
 			}
+			else
+			{
+				/*
+				 * We were not able to perform the restartpoint (checkpoints
+				 * throw an ERROR in case of error).  Most likely because we
+				 * have not received any new checkpoint WAL records since the
+				 * last restartpoint. Try again in 15 s.
+				 */
+				last_checkpoint_time = now - CheckPointTimeout + 15;
+			}
+
+			ckpt_active = false;
+		}
 		else
 			BgBufferSync();
 
@@ -507,7 +539,7 @@ CheckArchiveTimeout(void)
 	pg_time_t	now;
 	pg_time_t	last_time;
 
-	if (XLogArchiveTimeout <= 0)
+	if (XLogArchiveTimeout <= 0 || RecoveryInProgress())
 		return;
 
 	now = (pg_time_t) time(NULL);
@@ -714,6 +746,8 @@ IsCheckpointOnSchedule(double progress)
 	 * However, it's good enough for our purposes, we're only calculating an
 	 * estimate anyway.
 	 */
+	if (!RecoveryInProgress())
+	{
 		recptr = GetInsertRecPtr();
 		elapsed_xlogs =
 			(((double) (int32) (recptr.xlogid - ckpt_start_recptr.xlogid)) * XLogSegsPerFile +
@@ -725,6 +759,7 @@ IsCheckpointOnSchedule(double progress)
 			ckpt_cached_elapsed = elapsed_xlogs;
 			return false;
 		}
+	}
 
 	/*
 	 * Check progress against time elapsed and checkpoint_timeout.

src/backend/storage/buffer/README

-$PostgreSQL: pgsql/src/backend/storage/buffer/README,v 1.15 2008/11/06 20:51:14 tgl Exp $
+$PostgreSQL: pgsql/src/backend/storage/buffer/README,v 1.16 2009/02/18 15:58:41 heikki Exp $
 
 Notes About Shared Buffer Access Rules
 ======================================
@@ -268,3 +268,8 @@ out (and anyone else who flushes buffer contents to disk must do so too).
 This ensures that the page image transferred to disk is reasonably consistent.
 We might miss a hint-bit update or two but that isn't a problem, for the same
 reasons mentioned under buffer access rules.
+
+As of 8.4, background writer starts during recovery mode when there is
+some form of potentially extended recovery to perform. It performs an
+identical service to normal processing, except that checkpoints it
+writes are technically restartpoints.

src/backend/utils/init/postinit.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/init/postinit.c,v 1.187 2009/01/01 17:23:51 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/init/postinit.c,v 1.188 2009/02/18 15:58:41 heikki Exp $
  *
  *
  *-------------------------------------------------------------------------
@@ -324,7 +324,7 @@ InitCommunication(void)
  * If you're wondering why this is separate from InitPostgres at all:
  * the critical distinction is that this stuff has to happen before we can
  * run XLOG-related initialization, which is done before InitPostgres --- in
- * fact, for cases such as checkpoint creation processes, InitPostgres may
+ * fact, for cases such as the background writer process, InitPostgres may
  * never be done at all.
  */
 void

src/include/access/xlog.h

@@ -6,7 +6,7 @@
  * Portions Copyright (c) 1996-2009, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/access/xlog.h,v 1.90 2009/01/20 18:59:37 heikki Exp $
+ * $PostgreSQL: pgsql/src/include/access/xlog.h,v 1.91 2009/02/18 15:58:41 heikki Exp $
  */
 #ifndef XLOG_H
 #define XLOG_H
@@ -199,6 +199,8 @@ extern void RestoreBkpBlocks(XLogRecPtr lsn, XLogRecord *record, bool cleanup);
 extern void xlog_redo(XLogRecPtr lsn, XLogRecord *record);
 extern void xlog_desc(StringInfo buf, uint8 xl_info, char *rec);
 
+extern bool RecoveryInProgress(void);
+
 extern void UpdateControlFile(void);
 extern Size XLOGShmemSize(void);
 extern void XLOGShmemInit(void);
@@ -207,9 +209,12 @@ extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
 extern void InitXLOGAccess(void);
 extern void CreateCheckPoint(int flags);
+extern bool CreateRestartPoint(int flags);
 extern void XLogPutNextOid(Oid nextOid);
 extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern void GetNextXidAndEpoch(TransactionId *xid, uint32 *epoch);
 
+extern void StartupProcessMain(void);
+
 #endif   /* XLOG_H */

src/include/storage/pmsignal.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2009, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/storage/pmsignal.h,v 1.21 2009/01/01 17:24:01 momjian Exp $
+ * $PostgreSQL: pgsql/src/include/storage/pmsignal.h,v 1.22 2009/02/18 15:58:41 heikki Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -22,6 +22,9 @@
  */
 typedef enum
 {
+	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
+	PMSIGNAL_RECOVERY_CONSISTENT, /* recovery has reached consistent state */
+	PMSIGNAL_RECOVERY_COMPLETED, /* recovery has completed */
 	PMSIGNAL_PASSWORD_CHANGE,	/* pg_auth file has changed */
 	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */