Don't use O_DIRECT when writing WAL files if archiving or streaming is

enabled. Bypassing the kernel cache is counter-productive in that case,
because the archiver/walsender process will read from the WAL file
soon after it's written, and if it's not cached the read will cause
a physical read, eating I/O bandwidth available on the WAL drive.

Also, walreceiver process does unaligned writes, so disable O_DIRECT
in walreceiver process for that reason too.

4 files changed, 47 insertions, 26 deletions

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 106d39b7601..046d80fa95d 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2010, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/backend/access/transam/xlog.c,v 1.376 2010/02/19 01:04:03 itagaki Exp $
+ * $PostgreSQL: pgsql/src/backend/access/transam/xlog.c,v 1.377 2010/02/19 10:51:03 heikki Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -2686,13 +2686,10 @@ XLogFileClose(void)
 	 * WAL segment files will not be re-read in normal operation, so we advise
 	 * the OS to release any cached pages.	But do not do so if WAL archiving
 	 * or streaming is active, because archiver and walsender process could use
-	 * the cache to read the WAL segment.  Also, don't bother with it if we
-	 * are using O_DIRECT, since the kernel is presumably not caching in that
-	 * case.
+	 * the cache to read the WAL segment.
 	 */
 #if defined(USE_POSIX_FADVISE) && defined(POSIX_FADV_DONTNEED)
-	if (!XLogIsNeeded() &&
-		(get_sync_bit(sync_method) & PG_O_DIRECT) == 0)
+	if (!XLogIsNeeded())
 		(void) posix_fadvise(openLogFile, 0, 0, POSIX_FADV_DONTNEED);
 #endif
 
@@ -7652,10 +7649,29 @@ xlog_outrec(StringInfo buf, XLogRecord *record)
 static int
 get_sync_bit(int method)
 {
+	int o_direct_flag = 0;
+
 	/* If fsync is disabled, never open in sync mode */
 	if (!enableFsync)
 		return 0;
 
+	/*
+	 * Optimize writes by bypassing kernel cache with O_DIRECT when using
+	 * O_SYNC, O_DSYNC or O_FSYNC. But only if archiving and streaming are
+	 * disabled, otherwise the archive command or walsender process will
+	 * read the WAL soon after writing it, which is guaranteed to cause a
+	 * physical read if we bypassed the kernel cache. We also skip the
+	 * posix_fadvise(POSIX_FADV_DONTNEED) call in XLogFileClose() for the
+	 * same reason.
+	 *
+	 * Never use O_DIRECT in walreceiver process for similar reasons; the WAL
+	 * written by walreceiver is normally read by the startup process soon
+	 * after its written. Also, walreceiver performs unaligned writes, which
+	 * don't work with O_DIRECT, so it is required for correctness too.
+	 */
+	if (!XLogIsNeeded() && !am_walreceiver)
+		o_direct_flag = PG_O_DIRECT;
+
 	switch (method)
 	{
 			/*
@@ -7670,11 +7686,11 @@ get_sync_bit(int method)
 			return 0;
 #ifdef OPEN_SYNC_FLAG
 		case SYNC_METHOD_OPEN:
-			return OPEN_SYNC_FLAG;
+			return OPEN_SYNC_FLAG | o_direct_flag;
 #endif
 #ifdef OPEN_DATASYNC_FLAG
 		case SYNC_METHOD_OPEN_DSYNC:
-			return OPEN_DATASYNC_FLAG;
+			return OPEN_DATASYNC_FLAG | o_direct_flag;
 #endif
 		default:
 			/* can't happen (unless we are out of sync with option array) */
diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c
index 0e57611da42..3f82693dcea 100644
--- a/src/backend/replication/walreceiver.c
+++ b/src/backend/replication/walreceiver.c
@@ -29,7 +29,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/replication/walreceiver.c,v 1.4 2010/02/17 04:19:39 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/replication/walreceiver.c,v 1.5 2010/02/19 10:51:04 heikki Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -50,6 +50,9 @@
 #include "utils/ps_status.h"
 #include "utils/resowner.h"
 
+/* Global variable to indicate if this process is a walreceiver process */
+bool am_walreceiver;
+
 /* libpqreceiver hooks to these when loaded */
 walrcv_connect_type walrcv_connect = NULL;
 walrcv_receive_type walrcv_receive = NULL;
@@ -158,6 +161,8 @@ WalReceiverMain(void)
 	/* use volatile pointer to prevent code rearrangement */
 	volatile WalRcvData *walrcv = WalRcv;
 
+	am_walreceiver = true;
+
 	/*
 	 * WalRcv should be set up already (if we are a backend, we inherit
 	 * this by fork() or EXEC_BACKEND mechanism from the postmaster).
@@ -424,16 +429,18 @@ XLogWalRcvWrite(char *buf, Size nbytes, XLogRecPtr recptr)
 			bool	use_existent;
 
 			/*
-			 * XLOG segment files will be re-read in recovery operation soon,
-			 * so we don't need to advise the OS to release any cache page.
+			 * fsync() and close current file before we switch to next one.
+			 * We would otherwise have to reopen this file to fsync it later
 			 */
 			if (recvFile >= 0)
 			{
+				XLogWalRcvFlush();
+
 				/*
-				 * fsync() before we switch to next file. We would otherwise
-				 * have to reopen this file to fsync it later
+				 * XLOG segment files will be re-read by recovery in startup
+				 * process soon, so we don't advise the OS to release cache
+				 * pages associated with the file like XLogFileClose() does.
 				 */
-				XLogWalRcvFlush();
 				if (close(recvFile) != 0)
 					ereport(PANIC,
 							(errcode_for_file_access(),
@@ -445,8 +452,7 @@ XLogWalRcvWrite(char *buf, Size nbytes, XLogRecPtr recptr)
 			/* Create/use new log file */
 			XLByteToSeg(recptr, recvId, recvSeg);
 			use_existent = true;
-			recvFile = XLogFileInit(recvId, recvSeg,
-									&use_existent, true);
+			recvFile = XLogFileInit(recvId, recvSeg, &use_existent, true);
 			recvOff = 0;
 		}
 
diff --git a/src/include/access/xlogdefs.h b/src/include/access/xlogdefs.h
index 8ecc3a21b1c..0760b259308 100644
--- a/src/include/access/xlogdefs.h
+++ b/src/include/access/xlogdefs.h
@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2010, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/access/xlogdefs.h,v 1.25 2010/01/15 09:19:06 heikki Exp $
+ * $PostgreSQL: pgsql/src/include/access/xlogdefs.h,v 1.26 2010/02/19 10:51:04 heikki Exp $
  */
 #ifndef XLOG_DEFS_H
 #define XLOG_DEFS_H
@@ -106,23 +106,20 @@ typedef uint32 TimeLineID;
  * configure determined whether fdatasync() is.
  */
 #if defined(O_SYNC)
-#define BARE_OPEN_SYNC_FLAG		O_SYNC
+#define OPEN_SYNC_FLAG		O_SYNC
 #elif defined(O_FSYNC)
-#define BARE_OPEN_SYNC_FLAG		O_FSYNC
-#endif
-#ifdef BARE_OPEN_SYNC_FLAG
-#define OPEN_SYNC_FLAG			(BARE_OPEN_SYNC_FLAG | PG_O_DIRECT)
+#define OPEN_SYNC_FLAG		O_FSYNC
 #endif
 
 #if defined(O_DSYNC)
 #if defined(OPEN_SYNC_FLAG)
 /* O_DSYNC is distinct? */
-#if O_DSYNC != BARE_OPEN_SYNC_FLAG
-#define OPEN_DATASYNC_FLAG		(O_DSYNC | PG_O_DIRECT)
+#if O_DSYNC != OPEN_SYNC_FLAG
+#define OPEN_DATASYNC_FLAG		O_DSYNC
 #endif
 #else							/* !defined(OPEN_SYNC_FLAG) */
 /* Win32 only has O_DSYNC */
-#define OPEN_DATASYNC_FLAG		(O_DSYNC | PG_O_DIRECT)
+#define OPEN_DATASYNC_FLAG		O_DSYNC
 #endif
 #endif
 
diff --git a/src/include/replication/walreceiver.h b/src/include/replication/walreceiver.h
index bf7ad41b068..56af60560e7 100644
--- a/src/include/replication/walreceiver.h
+++ b/src/include/replication/walreceiver.h
@@ -5,7 +5,7 @@
  *
  * Portions Copyright (c) 2010-2010, PostgreSQL Global Development Group
  *
- * $PostgreSQL: pgsql/src/include/replication/walreceiver.h,v 1.6 2010/02/03 09:47:19 heikki Exp $
+ * $PostgreSQL: pgsql/src/include/replication/walreceiver.h,v 1.7 2010/02/19 10:51:04 heikki Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -15,6 +15,8 @@
 #include "access/xlogdefs.h"
 #include "storage/spin.h"
 
+extern bool am_walreceiver;
+
 /*
  * MAXCONNINFO: maximum size of a connection string.
  *