Track IO times in pg_stat_io

a9c70b4 and 8aaa04b32S added counting of IO operations to a new view,
pg_stat_io. Now, add IO timing for reads, writes, extends, and fsyncs to
pg_stat_io as well.

This combines the tracking for pgBufferUsage with the tracking for pg_stat_io
into a new function pgstat_count_io_op_time(). This should make it a bit
easier to avoid the somewhat costly instr_time conversion done for
pgBufferUsage.

Author: Melanie Plageman <melanieplageman@gmail.com>
Reviewed-by: Andres Freund <andres@anarazel.de>
Reviewed-by: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Discussion: https://postgr.es/m/flat/CAAKRu_ay5iKmnbXZ3DsauViF3eMxu4m1oNnJXqV_HyqYeg55Ww%40mail.gmail.com

Author: anarazel

doc/src/sgml/monitoring.sgml

@@ -3814,6 +3814,18 @@ SELECT pid, wait_event_type, wait_event FROM pg_stat_activity WHERE wait_event i
       </entry>
      </row>
 
+     <row>
+      <entry role="catalog_table_entry">
+       <para role="column_definition">
+        <structfield>read_time</structfield> <type>double precision</type>
+       </para>
+       <para>
+        Time spent in read operations in milliseconds (if
+        <xref linkend="guc-track-io-timing"/> is enabled, otherwise zero)
+       </para>
+      </entry>
+     </row>
+
      <row>
       <entry role="catalog_table_entry">
        <para role="column_definition">
@@ -3826,6 +3838,18 @@ SELECT pid, wait_event_type, wait_event FROM pg_stat_activity WHERE wait_event i
       </entry>
      </row>
 
+     <row>
+      <entry role="catalog_table_entry">
+       <para role="column_definition">
+        <structfield>write_time</structfield> <type>double precision</type>
+       </para>
+       <para>
+        Time spent in write operations in milliseconds (if
+        <xref linkend="guc-track-io-timing"/> is enabled, otherwise zero)
+       </para>
+      </entry>
+     </row>
+
      <row>
       <entry role="catalog_table_entry">
        <para role="column_definition">
@@ -3838,6 +3862,18 @@ SELECT pid, wait_event_type, wait_event FROM pg_stat_activity WHERE wait_event i
       </entry>
      </row>
 
+     <row>
+      <entry role="catalog_table_entry">
+       <para role="column_definition">
+        <structfield>extend_time</structfield> <type>double precision</type>
+       </para>
+       <para>
+        Time spent in extend operations in milliseconds (if
+        <xref linkend="guc-track-io-timing"/> is enabled, otherwise zero)
+       </para>
+      </entry>
+     </row>
+
      <row>
       <entry role="catalog_table_entry">
        <para role="column_definition">
@@ -3913,6 +3949,18 @@ SELECT pid, wait_event_type, wait_event FROM pg_stat_activity WHERE wait_event i
       </entry>
      </row>
 
+     <row>
+      <entry role="catalog_table_entry">
+       <para role="column_definition">
+        <structfield>fsync_time</structfield> <type>double precision</type>
+       </para>
+       <para>
+        Time spent in fsync operations in milliseconds (if
+        <xref linkend="guc-track-io-timing"/> is enabled, otherwise zero)
+       </para>
+      </entry>
+     </row>
+
      <row>
       <entry role="catalog_table_entry">
        <para role="column_definition">
@@ -3978,6 +4026,17 @@ SELECT pid, wait_event_type, wait_event FROM pg_stat_activity WHERE wait_event i
    </itemizedlist>
   </para>
 
+  <note>
+   <para>
+    Columns tracking I/O time will only be non-zero when
+    <xref linkend="guc-track-io-timing"/> is enabled. The user should be
+    careful when referencing these columns in combination with their
+    corresponding IO operations in case <varname>track_io_timing</varname>
+    was not enabled for the entire time since the last stats reset.
+   </para>
+  </note>
+
+
 
  </sect2>
 

src/backend/catalog/system_views.sql

@@ -1125,13 +1125,17 @@ SELECT
        b.io_object,
        b.io_context,
        b.reads,
+       b.read_time,
        b.writes,
+       b.write_time,
        b.extends,
+       b.extend_time,
        b.op_bytes,
        b.hits,
        b.evictions,
        b.reuses,
        b.fsyncs,
+       b.fsync_time,
        b.stats_reset
 FROM pg_stat_get_io() b;
 

src/backend/storage/buffer/bufmgr.c

@@ -1112,23 +1112,12 @@ ReadBuffer_common(SMgrRelation smgr, char relpersistence, ForkNumber forkNum,
 		MemSet((char *) bufBlock, 0, BLCKSZ);
 	else
 	{
-		instr_time	io_start,
-					io_time;
-
-		if (track_io_timing)
-			INSTR_TIME_SET_CURRENT(io_start);
+		instr_time	io_start = pgstat_prepare_io_time();
 
 		smgrread(smgr, forkNum, blockNum, bufBlock);
 
-		if (track_io_timing)
-		{
-			INSTR_TIME_SET_CURRENT(io_time);
-			INSTR_TIME_SUBTRACT(io_time, io_start);
-			pgstat_count_buffer_read_time(INSTR_TIME_GET_MICROSEC(io_time));
-			INSTR_TIME_ADD(pgBufferUsage.blk_read_time, io_time);
-		}
-
-		pgstat_count_io_op(io_object, io_context, IOOP_READ);
+		pgstat_count_io_op_time(io_object, io_context,
+								IOOP_READ, io_start, 1);
 
 		/* check for garbage data */
 		if (!PageIsVerifiedExtended((Page) bufBlock, blockNum,
@@ -1837,6 +1826,7 @@ ExtendBufferedRelShared(ExtendBufferedWhat eb,
 {
 	BlockNumber first_block;
 	IOContext	io_context = IOContextForStrategy(strategy);
+	instr_time	io_start;
 
 	LimitAdditionalPins(&extend_by);
 
@@ -2044,6 +2034,8 @@ ExtendBufferedRelShared(ExtendBufferedWhat eb,
 		}
 	}
 
+	io_start = pgstat_prepare_io_time();
+
 	/*
 	 * Note: if smgzerorextend fails, we will end up with buffers that are
 	 * allocated but not marked BM_VALID.  The next relation extension will
@@ -2066,6 +2058,9 @@ ExtendBufferedRelShared(ExtendBufferedWhat eb,
 	if (!(flags & EB_SKIP_EXTENSION_LOCK))
 		UnlockRelationForExtension(eb.rel, ExclusiveLock);
 
+	pgstat_count_io_op_time(IOOBJECT_RELATION, io_context, IOOP_EXTEND,
+							io_start, extend_by);
+
 	/* Set BM_VALID, terminate IO, and wake up any waiters */
 	for (int i = 0; i < extend_by; i++)
 	{
@@ -2089,8 +2084,6 @@ ExtendBufferedRelShared(ExtendBufferedWhat eb,
 	}
 
 	pgBufferUsage.shared_blks_written += extend_by;
-	pgstat_count_io_op_n(IOOBJECT_RELATION, io_context, IOOP_EXTEND,
-						 extend_by);
 
 	*extended_by = extend_by;
 
@@ -3344,8 +3337,7 @@ FlushBuffer(BufferDesc *buf, SMgrRelation reln, IOObject io_object,
 {
 	XLogRecPtr	recptr;
 	ErrorContextCallback errcallback;
-	instr_time	io_start,
-				io_time;
+	instr_time	io_start;
 	Block		bufBlock;
 	char	   *bufToWrite;
 	uint32		buf_state;
@@ -3420,10 +3412,7 @@ FlushBuffer(BufferDesc *buf, SMgrRelation reln, IOObject io_object,
 	 */
 	bufToWrite = PageSetChecksumCopy((Page) bufBlock, buf->tag.blockNum);
 
-	if (track_io_timing)
-		INSTR_TIME_SET_CURRENT(io_start);
-	else
-		INSTR_TIME_SET_ZERO(io_start);
+	io_start = pgstat_prepare_io_time();
 
 	/*
 	 * bufToWrite is either the shared buffer or a copy, as appropriate.
@@ -3452,15 +3441,8 @@ FlushBuffer(BufferDesc *buf, SMgrRelation reln, IOObject io_object,
 	 * When a strategy is not in use, the write can only be a "regular" write
 	 * of a dirty shared buffer (IOCONTEXT_NORMAL IOOP_WRITE).
 	 */
-	pgstat_count_io_op(IOOBJECT_RELATION, io_context, IOOP_WRITE);
-
-	if (track_io_timing)
-	{
-		INSTR_TIME_SET_CURRENT(io_time);
-		INSTR_TIME_SUBTRACT(io_time, io_start);
-		pgstat_count_buffer_write_time(INSTR_TIME_GET_MICROSEC(io_time));
-		INSTR_TIME_ADD(pgBufferUsage.blk_write_time, io_time);
-	}
+	pgstat_count_io_op_time(IOOBJECT_RELATION, io_context,
+							IOOP_WRITE, io_start, 1);
 
 	pgBufferUsage.shared_blks_written++;
 
@@ -4062,14 +4044,13 @@ FlushRelationBuffers(Relation rel)
 {
 	int			i;
 	BufferDesc *bufHdr;
-	instr_time	io_start,
-				io_time;
 
 	if (RelationUsesLocalBuffers(rel))
 	{
 		for (i = 0; i < NLocBuffer; i++)
 		{
 			uint32		buf_state;
+			instr_time	io_start;
 
 			bufHdr = GetLocalBufferDescriptor(i);
 			if (BufTagMatchesRelFileLocator(&bufHdr->tag, &rel->rd_locator) &&
@@ -4089,30 +4070,21 @@ FlushRelationBuffers(Relation rel)
 
 				PageSetChecksumInplace(localpage, bufHdr->tag.blockNum);
 
-				if (track_io_timing)
-					INSTR_TIME_SET_CURRENT(io_start);
-				else
-					INSTR_TIME_SET_ZERO(io_start);
+				io_start = pgstat_prepare_io_time();
 
 				smgrwrite(RelationGetSmgr(rel),
 						  BufTagGetForkNum(&bufHdr->tag),
 						  bufHdr->tag.blockNum,
 						  localpage,
 						  false);
 
+				pgstat_count_io_op_time(IOOBJECT_TEMP_RELATION,
+										IOCONTEXT_NORMAL, IOOP_WRITE,
+										io_start, 1);
+
 				buf_state &= ~(BM_DIRTY | BM_JUST_DIRTIED);
 				pg_atomic_unlocked_write_u32(&bufHdr->state, buf_state);
 
-				pgstat_count_io_op(IOOBJECT_TEMP_RELATION, IOCONTEXT_NORMAL, IOOP_WRITE);
-
-				if (track_io_timing)
-				{
-					INSTR_TIME_SET_CURRENT(io_time);
-					INSTR_TIME_SUBTRACT(io_time, io_start);
-					pgstat_count_buffer_write_time(INSTR_TIME_GET_MICROSEC(io_time));
-					INSTR_TIME_ADD(pgBufferUsage.blk_write_time, io_time);
-				}
-
 				pgBufferUsage.local_blks_written++;
 
 				/* Pop the error context stack */

src/backend/storage/buffer/localbuf.c

@@ -176,8 +176,6 @@ GetLocalVictimBuffer(void)
 	int			trycounter;
 	uint32		buf_state;
 	BufferDesc *bufHdr;
-	instr_time	io_start,
-				io_time;
 
 	ResourceOwnerEnlargeBuffers(CurrentResourceOwner);
 
@@ -233,6 +231,7 @@ GetLocalVictimBuffer(void)
 	 */
 	if (buf_state & BM_DIRTY)
 	{
+		instr_time	io_start;
 		SMgrRelation oreln;
 		Page		localpage = (char *) LocalBufHdrGetBlock(bufHdr);
 
@@ -241,10 +240,7 @@ GetLocalVictimBuffer(void)
 
 		PageSetChecksumInplace(localpage, bufHdr->tag.blockNum);
 
-		if (track_io_timing)
-			INSTR_TIME_SET_CURRENT(io_start);
-		else
-			INSTR_TIME_SET_ZERO(io_start);
+		io_start = pgstat_prepare_io_time();
 
 		/* And write... */
 		smgrwrite(oreln,
@@ -253,21 +249,14 @@ GetLocalVictimBuffer(void)
 				  localpage,
 				  false);
 
+		/* Temporary table I/O does not use Buffer Access Strategies */
+		pgstat_count_io_op_time(IOOBJECT_TEMP_RELATION, IOCONTEXT_NORMAL,
+								IOOP_WRITE, io_start, 1);
+
 		/* Mark not-dirty now in case we error out below */
 		buf_state &= ~BM_DIRTY;
 		pg_atomic_unlocked_write_u32(&bufHdr->state, buf_state);
 
-		/* Temporary table I/O does not use Buffer Access Strategies */
-		pgstat_count_io_op(IOOBJECT_TEMP_RELATION, IOCONTEXT_NORMAL, IOOP_WRITE);
-
-		if (track_io_timing)
-		{
-			INSTR_TIME_SET_CURRENT(io_time);
-			INSTR_TIME_SUBTRACT(io_time, io_start);
-			pgstat_count_buffer_write_time(INSTR_TIME_GET_MICROSEC(io_time));
-			INSTR_TIME_ADD(pgBufferUsage.blk_write_time, io_time);
-		}
-
 		pgBufferUsage.local_blks_written++;
 	}
 
@@ -325,6 +314,7 @@ ExtendBufferedRelLocal(ExtendBufferedWhat eb,
 					   uint32 *extended_by)
 {
 	BlockNumber first_block;
+	instr_time	io_start;
 
 	/* Initialize local buffers if first request in this session */
 	if (LocalBufHash == NULL)
@@ -415,9 +405,14 @@ ExtendBufferedRelLocal(ExtendBufferedWhat eb,
 		}
 	}
 
+	io_start = pgstat_prepare_io_time();
+
 	/* actually extend relation */
 	smgrzeroextend(eb.smgr, fork, first_block, extend_by, false);
 
+	pgstat_count_io_op_time(IOOBJECT_TEMP_RELATION, IOCONTEXT_NORMAL, IOOP_EXTEND,
+							io_start, extend_by);
+
 	for (int i = 0; i < extend_by; i++)
 	{
 		Buffer		buf = buffers[i];
@@ -434,8 +429,6 @@ ExtendBufferedRelLocal(ExtendBufferedWhat eb,
 	*extended_by = extend_by;
 
 	pgBufferUsage.temp_blks_written += extend_by;
-	pgstat_count_io_op_n(IOOBJECT_TEMP_RELATION, IOCONTEXT_NORMAL, IOOP_EXTEND,
-						 extend_by);
 
 	return first_block;
 }