Track total amounts of times spent writing and syncing WAL data to disk.

This commit adds new GUC track_wal_io_timing. When this is enabled,
the total amounts of time XLogWrite writes and issue_xlog_fsync syncs
WAL data to disk are counted in pg_stat_wal. This information would be
useful to check how much WAL write and sync affect the performance.

Enabling track_wal_io_timing will make the server query the operating
system for the current time every time WAL is written or synced,
which may cause significant overhead on some platforms. To avoid such
additional overhead in the server with track_io_timing enabled,
this commit introduces track_wal_io_timing as a separate parameter from
track_io_timing.

Note that WAL write and sync activity by walreceiver has not been tracked yet.

This commit makes the server also track the numbers of times XLogWrite
writes and issue_xlog_fsync syncs WAL data to disk, in pg_stat_wal,
regardless of the setting of track_wal_io_timing. This counters can be
used to calculate the WAL write and sync time per request, for example.

Bump PGSTAT_FILE_FORMAT_ID.

Bump catalog version.

Author: Masahiro Ikeda
Reviewed-By: Japin Li, Hayato Kuroda, Masahiko Sawada, David Johnston, Fujii Masao
Discussion: https://postgr.es/m/0509ad67b585a5b86a83d445dfa75392@oss.nttdata.com

1 files changed, 53 insertions, 1 deletions

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 377afb87324..18af3d41209 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -110,6 +110,7 @@ int			CommitDelay = 0;	/* precommit delay in microseconds */
 int			CommitSiblings = 5; /* # concurrent xacts needed to sleep */
 int			wal_retrieve_retry_interval = 5000;
 int			max_slot_wal_keep_size_mb = -1;
+bool		track_wal_io_timing = false;
 
 #ifdef WAL_DEBUG
 bool		XLOG_DEBUG = false;
@@ -2533,6 +2534,7 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible)
 			Size		nbytes;
 			Size		nleft;
 			int			written;
+			instr_time	start;
 
 			/* OK to write the page(s) */
 			from = XLogCtl->pages + startidx * (Size) XLOG_BLCKSZ;
@@ -2541,9 +2543,30 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible)
 			do
 			{
 				errno = 0;
+
+				/* Measure I/O timing to write WAL data */
+				if (track_wal_io_timing)
+					INSTR_TIME_SET_CURRENT(start);
+
 				pgstat_report_wait_start(WAIT_EVENT_WAL_WRITE);
 				written = pg_pwrite(openLogFile, from, nleft, startoffset);
 				pgstat_report_wait_end();
+
+				/*
+				 * Increment the I/O timing and the number of times WAL data
+				 * were written out to disk.
+				 */
+				if (track_wal_io_timing)
+				{
+					instr_time	duration;
+
+					INSTR_TIME_SET_CURRENT(duration);
+					INSTR_TIME_SUBTRACT(duration, start);
+					WalStats.m_wal_write_time += INSTR_TIME_GET_MICROSEC(duration);
+				}
+
+				WalStats.m_wal_write++;
+
 				if (written <= 0)
 				{
 					char		xlogfname[MAXFNAMELEN];
@@ -10524,6 +10547,20 @@ void
 issue_xlog_fsync(int fd, XLogSegNo segno)
 {
 	char	   *msg = NULL;
+	instr_time	start;
+
+	/*
+	 * Quick exit if fsync is disabled or write() has already synced the WAL
+	 * file.
+	 */
+	if (!enableFsync ||
+		sync_method == SYNC_METHOD_OPEN ||
+		sync_method == SYNC_METHOD_OPEN_DSYNC)
+		return;
+
+	/* Measure I/O timing to sync the WAL file */
+	if (track_wal_io_timing)
+		INSTR_TIME_SET_CURRENT(start);
 
 	pgstat_report_wait_start(WAIT_EVENT_WAL_SYNC);
 	switch (sync_method)
@@ -10546,7 +10583,8 @@ issue_xlog_fsync(int fd, XLogSegNo segno)
 #endif
 		case SYNC_METHOD_OPEN:
 		case SYNC_METHOD_OPEN_DSYNC:
-			/* write synced it already */
+			/* not reachable */
+			Assert(false);
 			break;
 		default:
 			elog(PANIC, "unrecognized wal_sync_method: %d", sync_method);
@@ -10568,6 +10606,20 @@ issue_xlog_fsync(int fd, XLogSegNo segno)
 	}
 
 	pgstat_report_wait_end();
+
+	/*
+	 * Increment the I/O timing and the number of times WAL files were synced.
+	 */
+	if (track_wal_io_timing)
+	{
+		instr_time	duration;
+
+		INSTR_TIME_SET_CURRENT(duration);
+		INSTR_TIME_SUBTRACT(duration, start);
+		WalStats.m_wal_sync_time += INSTR_TIME_GET_MICROSEC(duration);
+	}
+
+	WalStats.m_wal_sync++;
 }
 
 /*