pgstat: Infrastructure for more detailed IO statistics

This commit adds the infrastructure for more detailed IO statistics. The calls
to actually count IOs, a system view to access the new statistics,
documentation and tests will be added in subsequent commits, to make review
easier.

While we already had some IO statistics, e.g. in pg_stat_bgwriter and
pg_stat_database, they did not provide sufficient detail to understand what
the main sources of IO are, or whether configuration changes could avoid
IO. E.g., pg_stat_bgwriter.buffers_backend does contain the number of buffers
written out by a backend, but as that includes extending relations (always
done by backends) and writes triggered by the use of buffer access strategies,
it cannot easily be used to tune background writer or checkpointer. Similarly,
pg_stat_database.blks_read cannot easily be used to tune shared_buffers /
compute a cache hit ratio, as the use of buffer access strategies will often
prevent a large fraction of the read blocks to end up in shared_buffers.

The new IO statistics count IO operations (evict, extend, fsync, read, reuse,
and write), and are aggregated for each combination of backend type (backend,
autovacuum worker, bgwriter, etc), target object of the IO (relations, temp
relations) and context of the IO (normal, vacuum, bulkread, bulkwrite).

What is tracked in this series of patches, is sufficient to perform the
aforementioned analyses. Further details, e.g. tracking the number of buffer
hits, would make that even easier, but was left out for now, to keep the scope
of the already large patchset manageable.

Bumps PGSTAT_FILE_FORMAT_ID.

Author: Melanie Plageman <melanieplageman@gmail.com>
Reviewed-by: Andres Freund <andres@anarazel.de>
Reviewed-by: Justin Pryzby <pryzby@telsasoft.com>
Reviewed-by: Kyotaro Horiguchi <horikyota.ntt@gmail.com>
Discussion: https://postgr.es/m/20200124195226.lth52iydq2n2uilq@alap3.anarazel.de

Author: anarazel

doc/src/sgml/monitoring.sgml

@@ -5444,6 +5444,8 @@ SELECT pid, wait_event_type, wait_event FROM pg_stat_activity WHERE wait_event i
         the <structname>pg_stat_bgwriter</structname>
         view, <literal>archiver</literal> to reset all the counters shown in
         the <structname>pg_stat_archiver</structname> view,
+        <literal>io</literal> to reset all the counters shown in the
+        <structname>pg_stat_io</structname> view,
         <literal>wal</literal> to reset all the counters shown in the
         <structname>pg_stat_wal</structname> view or
         <literal>recovery_prefetch</literal> to reset all the counters shown

src/backend/utils/activity/Makefile

@@ -22,6 +22,7 @@ OBJS = \
 	pgstat_checkpointer.o \
 	pgstat_database.o \
 	pgstat_function.o \
+	pgstat_io.o \
 	pgstat_relation.o \
 	pgstat_replslot.o \
 	pgstat_shmem.o \

src/backend/utils/activity/meson.build

@@ -9,6 +9,7 @@ backend_sources += files(
   'pgstat_checkpointer.c',
   'pgstat_database.c',
   'pgstat_function.c',
+  'pgstat_io.c',
   'pgstat_relation.c',
   'pgstat_replslot.c',
   'pgstat_shmem.c',

src/backend/utils/activity/pgstat.c

@@ -72,6 +72,7 @@
  * - pgstat_checkpointer.c
  * - pgstat_database.c
  * - pgstat_function.c
+ * - pgstat_io.c
  * - pgstat_relation.c
  * - pgstat_replslot.c
  * - pgstat_slru.c
@@ -359,6 +360,15 @@ static const PgStat_KindInfo pgstat_kind_infos[PGSTAT_NUM_KINDS] = {
 		.snapshot_cb = pgstat_checkpointer_snapshot_cb,
 	},
 
+	[PGSTAT_KIND_IO] = {
+		.name = "io",
+
+		.fixed_amount = true,
+
+		.reset_all_cb = pgstat_io_reset_all_cb,
+		.snapshot_cb = pgstat_io_snapshot_cb,
+	},
+
 	[PGSTAT_KIND_SLRU] = {
 		.name = "slru",
 
@@ -582,6 +592,7 @@ pgstat_report_stat(bool force)
 
 	/* Don't expend a clock check if nothing to do */
 	if (dlist_is_empty(&pgStatPending) &&
+		!have_iostats &&
 		!have_slrustats &&
 		!pgstat_have_pending_wal())
 	{
@@ -628,6 +639,9 @@ pgstat_report_stat(bool force)
 	/* flush database / relation / function / ... stats */
 	partial_flush |= pgstat_flush_pending_entries(nowait);
 
+	/* flush IO stats */
+	partial_flush |= pgstat_flush_io(nowait);
+
 	/* flush wal stats */
 	partial_flush |= pgstat_flush_wal(nowait);
 
@@ -1322,6 +1336,12 @@ pgstat_write_statsfile(void)
 	pgstat_build_snapshot_fixed(PGSTAT_KIND_CHECKPOINTER);
 	write_chunk_s(fpout, &pgStatLocal.snapshot.checkpointer);
 
+	/*
+	 * Write IO stats struct
+	 */
+	pgstat_build_snapshot_fixed(PGSTAT_KIND_IO);
+	write_chunk_s(fpout, &pgStatLocal.snapshot.io);
+
 	/*
 	 * Write SLRU stats struct
 	 */
@@ -1496,6 +1516,12 @@ pgstat_read_statsfile(void)
 	if (!read_chunk_s(fpin, &shmem->checkpointer.stats))
 		goto error;
 
+	/*
+	 * Read IO stats struct
+	 */
+	if (!read_chunk_s(fpin, &shmem->io.stats))
+		goto error;
+
 	/*
 	 * Read SLRU stats struct
 	 */

src/backend/utils/activity/pgstat_bgwriter.c

@@ -24,7 +24,7 @@ PgStat_BgWriterStats PendingBgWriterStats = {0};
 
 
 /*
- * Report bgwriter statistics
+ * Report bgwriter and IO statistics
  */
 void
 pgstat_report_bgwriter(void)
@@ -56,6 +56,11 @@ pgstat_report_bgwriter(void)
 	 * Clear out the statistics buffer, so it can be re-used.
 	 */
 	MemSet(&PendingBgWriterStats, 0, sizeof(PendingBgWriterStats));
+
+	/*
+	 * Report IO statistics
+	 */
+	pgstat_flush_io(false);
 }
 
 /*

src/backend/utils/activity/pgstat_checkpointer.c

@@ -24,7 +24,7 @@ PgStat_CheckpointerStats PendingCheckpointerStats = {0};
 
 
 /*
- * Report checkpointer statistics
+ * Report checkpointer and IO statistics
  */
 void
 pgstat_report_checkpointer(void)
@@ -62,6 +62,11 @@ pgstat_report_checkpointer(void)
 	 * Clear out the statistics buffer, so it can be re-used.
 	 */
 	MemSet(&PendingCheckpointerStats, 0, sizeof(PendingCheckpointerStats));
+
+	/*
+	 * Report IO statistics
+	 */
+	pgstat_flush_io(false);
 }
 
 /*