Add pg_stat_io view, providing more detailed IO statistics

Builds on 28e626bde00 and f30d62c2fc6. See the former for motivation.

Rows of the view show IO operations for a particular backend type, IO target
object, IO context combination (e.g. a client backend's operations on
permanent relations in shared buffers) and each column in the view is the
total number of IO Operations done (e.g. writes). So a cell in the view would
be, for example, the number of blocks of relation data written from shared
buffers by client backends since the last stats reset.

In anticipation of tracking WAL IO and non-block-oriented IO (such as
temporary file IO), the "op_bytes" column specifies the unit of the "reads",
"writes", and "extends" columns for a given row.

Rows for combinations of IO operation, backend type, target object and context
that never occur, are ommitted entirely. For example, checkpointer will never
operate on temporary relations.

Similarly, if an IO operation never occurs for such a combination, the IO
operation's cell will be null, to distinguish from 0 observed IO
operations. For example, bgwriter should not perform reads.

Note that some of the cells in the view are redundant with fields in
pg_stat_bgwriter (e.g. buffers_backend). For now, these have been kept for
backwards compatibility.

Bumps catversion.

Author: Melanie Plageman <melanieplageman@gmail.com>
Author: Samay Sharma <smilingsamay@gmail.com>
Reviewed-by: Maciek Sakrejda <m.sakrejda@gmail.com>
Reviewed-by: Lukas Fittl <lukas@fittl.com>
Reviewed-by: Andres Freund <andres@anarazel.de>
Reviewed-by: Justin Pryzby <pryzby@telsasoft.com>
Discussion: https://postgr.es/m/20200124195226.lth52iydq2n2uilq@alap3.anarazel.de

6 files changed, 179 insertions, 1 deletions

diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql
index 8608e3fa5b1..34ca0e739f5 100644
--- a/src/backend/catalog/system_views.sql
+++ b/src/backend/catalog/system_views.sql
@@ -1117,6 +1117,21 @@ CREATE VIEW pg_stat_bgwriter AS
         pg_stat_get_buf_alloc() AS buffers_alloc,
         pg_stat_get_bgwriter_stat_reset_time() AS stats_reset;
 
+CREATE VIEW pg_stat_io AS
+SELECT
+       b.backend_type,
+       b.io_object,
+       b.io_context,
+       b.reads,
+       b.writes,
+       b.extends,
+       b.op_bytes,
+       b.evictions,
+       b.reuses,
+       b.fsyncs,
+       b.stats_reset
+FROM pg_stat_get_io() b;
+
 CREATE VIEW pg_stat_wal AS
     SELECT
         w.wal_records,
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 924698e6ae4..9d707c35216 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1246,6 +1246,147 @@ pg_stat_get_buf_alloc(PG_FUNCTION_ARGS)
 }
 
 /*
+* When adding a new column to the pg_stat_io view, add a new enum value
+* here above IO_NUM_COLUMNS.
+*/
+typedef enum io_stat_col
+{
+	IO_COL_BACKEND_TYPE,
+	IO_COL_IO_OBJECT,
+	IO_COL_IO_CONTEXT,
+	IO_COL_READS,
+	IO_COL_WRITES,
+	IO_COL_EXTENDS,
+	IO_COL_CONVERSION,
+	IO_COL_EVICTIONS,
+	IO_COL_REUSES,
+	IO_COL_FSYNCS,
+	IO_COL_RESET_TIME,
+	IO_NUM_COLUMNS,
+} io_stat_col;
+
+/*
+ * When adding a new IOOp, add a new io_stat_col and add a case to this
+ * function returning the corresponding io_stat_col.
+ */
+static io_stat_col
+pgstat_get_io_op_index(IOOp io_op)
+{
+	switch (io_op)
+	{
+		case IOOP_EVICT:
+			return IO_COL_EVICTIONS;
+		case IOOP_READ:
+			return IO_COL_READS;
+		case IOOP_REUSE:
+			return IO_COL_REUSES;
+		case IOOP_WRITE:
+			return IO_COL_WRITES;
+		case IOOP_EXTEND:
+			return IO_COL_EXTENDS;
+		case IOOP_FSYNC:
+			return IO_COL_FSYNCS;
+	}
+
+	elog(ERROR, "unrecognized IOOp value: %d", io_op);
+	pg_unreachable();
+}
+
+Datum
+pg_stat_get_io(PG_FUNCTION_ARGS)
+{
+	ReturnSetInfo *rsinfo;
+	PgStat_IO  *backends_io_stats;
+	Datum		reset_time;
+
+	InitMaterializedSRF(fcinfo, 0);
+	rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
+
+	backends_io_stats = pgstat_fetch_stat_io();
+
+	reset_time = TimestampTzGetDatum(backends_io_stats->stat_reset_timestamp);
+
+	for (BackendType bktype = B_INVALID; bktype < BACKEND_NUM_TYPES; bktype++)
+	{
+		Datum		bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype));
+		PgStat_BktypeIO *bktype_stats = &backends_io_stats->stats[bktype];
+
+		/*
+		 * In Assert builds, we can afford an extra loop through all of the
+		 * counters checking that only expected stats are non-zero, since it
+		 * keeps the non-Assert code cleaner.
+		 */
+		Assert(pgstat_bktype_io_stats_valid(bktype_stats, bktype));
+
+		/*
+		 * For those BackendTypes without IO Operation stats, skip
+		 * representing them in the view altogether.
+		 */
+		if (!pgstat_tracks_io_bktype(bktype))
+			continue;
+
+		for (IOObject io_obj = IOOBJECT_FIRST;
+			 io_obj < IOOBJECT_NUM_TYPES; io_obj++)
+		{
+			const char *obj_name = pgstat_get_io_object_name(io_obj);
+
+			for (IOContext io_context = IOCONTEXT_FIRST;
+				 io_context < IOCONTEXT_NUM_TYPES; io_context++)
+			{
+				const char *context_name = pgstat_get_io_context_name(io_context);
+
+				Datum		values[IO_NUM_COLUMNS] = {0};
+				bool		nulls[IO_NUM_COLUMNS] = {0};
+
+				/*
+				 * Some combinations of BackendType, IOObject, and IOContext
+				 * are not valid for any type of IOOp. In such cases, omit the
+				 * entire row from the view.
+				 */
+				if (!pgstat_tracks_io_object(bktype, io_obj, io_context))
+					continue;
+
+				values[IO_COL_BACKEND_TYPE] = bktype_desc;
+				values[IO_COL_IO_CONTEXT] = CStringGetTextDatum(context_name);
+				values[IO_COL_IO_OBJECT] = CStringGetTextDatum(obj_name);
+				values[IO_COL_RESET_TIME] = TimestampTzGetDatum(reset_time);
+
+				/*
+				 * Hard-code this to the value of BLCKSZ for now. Future
+				 * values could include XLOG_BLCKSZ, once WAL IO is tracked,
+				 * and constant multipliers, once non-block-oriented IO (e.g.
+				 * temporary file IO) is tracked.
+				 */
+				values[IO_COL_CONVERSION] = Int64GetDatum(BLCKSZ);
+
+				for (IOOp io_op = IOOP_FIRST; io_op < IOOP_NUM_TYPES; io_op++)
+				{
+					int			col_idx = pgstat_get_io_op_index(io_op);
+
+					/*
+					 * Some combinations of BackendType and IOOp, of IOContext
+					 * and IOOp, and of IOObject and IOOp are not tracked. Set
+					 * these cells in the view NULL.
+					 */
+					nulls[col_idx] = !pgstat_tracks_io_op(bktype, io_obj, io_context, io_op);
+
+					if (nulls[col_idx])
+						continue;
+
+					values[col_idx] =
+						Int64GetDatum(bktype_stats->data[io_obj][io_context][io_op]);
+				}
+
+				tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc,
+									 values, nulls);
+			}
+		}
+	}
+
+	return (Datum) 0;
+}
+
+/*
  * Returns statistics of WAL activity
  */
 Datum
diff --git a/src/include/catalog/catversion.h b/src/include/catalog/catversion.h
index c1ce0b76e14..9c298cb1253 100644
--- a/src/include/catalog/catversion.h
+++ b/src/include/catalog/catversion.h
@@ -57,6 +57,6 @@
  */
 
 /*							yyyymmddN */
-#define CATALOG_VERSION_NO	202301301
+#define CATALOG_VERSION_NO	202302111
 
 #endif
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index c0f2a8a77c8..66b73c3900d 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -5717,6 +5717,15 @@
   proname => 'pg_stat_get_buf_alloc', provolatile => 's', proparallel => 'r',
   prorettype => 'int8', proargtypes => '', prosrc => 'pg_stat_get_buf_alloc' },
 
+{ oid => '8459', descr => 'statistics: per backend type IO statistics',
+  proname => 'pg_stat_get_io', provolatile => 'v',
+  prorows => '30', proretset => 't',
+  proparallel => 'r', prorettype => 'record', proargtypes => '',
+  proallargtypes => '{text,text,text,int8,int8,int8,int8,int8,int8,int8,timestamptz}',
+  proargmodes => '{o,o,o,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_type,io_object,io_context,reads,writes,extends,op_bytes,evictions,reuses,fsyncs,stats_reset}',
+  prosrc => 'pg_stat_get_io' },
+
 { oid => '1136', descr => 'statistics: information about WAL activity',
   proname => 'pg_stat_get_wal', proisstrict => 'f', provolatile => 's',
   proparallel => 'r', prorettype => 'record', proargtypes => '',
diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out
index e7a2f5856aa..174b725fff1 100644
--- a/src/test/regress/expected/rules.out
+++ b/src/test/regress/expected/rules.out
@@ -1876,6 +1876,18 @@ pg_stat_gssapi| SELECT pid,
     gss_enc AS encrypted
    FROM pg_stat_get_activity(NULL::integer) s(datid, pid, usesysid, application_name, state, query, wait_event_type, wait_event, xact_start, query_start, backend_start, state_change, client_addr, client_hostname, client_port, backend_xid, backend_xmin, backend_type, ssl, sslversion, sslcipher, sslbits, ssl_client_dn, ssl_client_serial, ssl_issuer_dn, gss_auth, gss_princ, gss_enc, leader_pid, query_id)
   WHERE (client_port IS NOT NULL);
+pg_stat_io| SELECT backend_type,
+    io_object,
+    io_context,
+    reads,
+    writes,
+    extends,
+    op_bytes,
+    evictions,
+    reuses,
+    fsyncs,
+    stats_reset
+   FROM pg_stat_get_io() b(backend_type, io_object, io_context, reads, writes, extends, op_bytes, evictions, reuses, fsyncs, stats_reset);
 pg_stat_progress_analyze| SELECT s.pid,
     s.datid,
     d.datname,
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 36d1dc01177..45fc5759ced 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -3378,6 +3378,7 @@ intset_internal_node
 intset_leaf_node
 intset_node
 intvKEY
+io_stat_col
 itemIdCompact
 itemIdCompactData
 iterator