v3-0001-Track-per-relation-cumulative-time-spent-in-vacuu.patch

From 69b2b23face81daa4ef3870988c9a0e51140321b Mon Sep 17 00:00:00 2001
From: EC2 Default User <ec2-user@ip-172-31-76-150.ec2.internal>
Date: Mon, 13 Jan 2025 17:27:40 +0000
Subject: [PATCH v3 1/1] Track per relation cumulative time spent in vacuum or
 analyze

Added cumulative counter fields in pg_stat_all_tables for
(auto)vacuum and (auto)analyze. This will allow a user to
derive the average time spent for these operations with
the help of the exiting (auto)vacuum_count and
(auto)analyze_count fields.
---
 doc/src/sgml/monitoring.sgml                 | 38 ++++++++++++++++++++
 src/backend/access/heap/vacuumlazy.c         | 18 +++++++---
 src/backend/catalog/system_views.sql         |  6 +++-
 src/backend/commands/analyze.c               | 18 ++++++----
 src/backend/utils/activity/pgstat_relation.c | 23 +++++++-----
 src/backend/utils/adt/pgstatfuncs.c          | 28 +++++++++++++++
 src/include/catalog/pg_proc.dat              | 16 +++++++++
 src/include/pgstat.h                         | 10 ++++--
 src/test/regress/expected/rules.out          | 18 ++++++++--
 9 files changed, 149 insertions(+), 26 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index d0d176cc54..909c6eb535 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -4040,6 +4040,44 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        daemon
       </para></entry>
      </row>
+
+     <row>
+      <entry role="catalog_table_entry"><para role="column_definition">
+       <structfield>total_vacuum_time</structfield> <type>bigint</type>
+      </para>
+      <para>
+       Total time this table has spent in manual vacuum, in milliseconds
+      </para></entry>
+     </row>
+
+     <row>
+      <entry role="catalog_table_entry"><para role="column_definition">
+       <structfield>total_autovacuum_time</structfield> <type>bigint</type>
+      </para>
+      <para>
+       Total time this table has spent in vacuum by the autovacuum
+       daemon, in milliseconds
+      </para></entry>
+     </row>
+
+     <row>
+      <entry role="catalog_table_entry"><para role="column_definition">
+       <structfield>total_analyze_time</structfield> <type>bigint</type>
+      </para>
+      <para>
+       Total time this table has spent in manual analyze, in milliseconds
+      </para></entry>
+     </row>
+
+     <row>
+      <entry role="catalog_table_entry"><para role="column_definition">
+       <structfield>total_autoanalyze_time</structfield> <type>bigint</type>
+      </para>
+      <para>
+       Total time this table has spent in analyze by the autovacuum
+       daemon, in milliseconds
+      </para></entry>
+     </row>
     </tbody>
    </tgroup>
   </table>
diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index 09fab08b8e..432359e548 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -319,6 +319,8 @@ heap_vacuum_rel(Relation rel, VacuumParams *params,
 				new_rel_allvisible;
 	PGRUsage	ru0;
 	TimestampTz starttime = 0;
+	TimestampTz endtime = 0;
+	PgStat_Counter elapsedtime = 0;
 	PgStat_Counter startreadtime = 0,
 				startwritetime = 0;
 	WalUsage	startwalusage = pgWalUsage;
@@ -329,10 +331,10 @@ heap_vacuum_rel(Relation rel, VacuumParams *params,
 	verbose = (params->options & VACOPT_VERBOSE) != 0;
 	instrument = (verbose || (AmAutoVacuumWorkerProcess() &&
 							  params->log_min_duration >= 0));
+
 	if (instrument)
 	{
 		pg_rusage_init(&ru0);
-		starttime = GetCurrentTimestamp();
 		if (track_io_timing)
 		{
 			startreadtime = pgStatBlockReadTime;
@@ -340,6 +342,8 @@ heap_vacuum_rel(Relation rel, VacuumParams *params,
 		}
 	}
 
+	starttime = GetCurrentTimestamp();
+
 	pgstat_progress_start_command(PROGRESS_COMMAND_VACUUM,
 								  RelationGetRelid(rel));
 
@@ -591,6 +595,11 @@ heap_vacuum_rel(Relation rel, VacuumParams *params,
 						vacrel->NewRelfrozenXid, vacrel->NewRelminMxid,
 						&frozenxid_updated, &minmulti_updated, false);
 
+	pgstat_progress_end_command();
+
+	endtime = GetCurrentTimestamp();
+	elapsedtime = TimestampDifferenceMilliseconds(starttime, endtime);
+
 	/*
 	 * Report results to the cumulative stats system, too.
 	 *
@@ -605,13 +614,12 @@ heap_vacuum_rel(Relation rel, VacuumParams *params,
 						 rel->rd_rel->relisshared,
 						 Max(vacrel->new_live_tuples, 0),
 						 vacrel->recently_dead_tuples +
-						 vacrel->missed_dead_tuples);
-	pgstat_progress_end_command();
+						 vacrel->missed_dead_tuples,
+						 endtime,
+						 elapsedtime);
 
 	if (instrument)
 	{
-		TimestampTz endtime = GetCurrentTimestamp();
-
 		if (verbose || params->log_min_duration == 0 ||
 			TimestampDifferenceExceeds(starttime, endtime,
 									   params->log_min_duration))
diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql
index 7a595c84db..cf35bff30b 100644
--- a/src/backend/catalog/system_views.sql
+++ b/src/backend/catalog/system_views.sql
@@ -691,7 +691,11 @@ CREATE VIEW pg_stat_all_tables AS
             pg_stat_get_vacuum_count(C.oid) AS vacuum_count,
             pg_stat_get_autovacuum_count(C.oid) AS autovacuum_count,
             pg_stat_get_analyze_count(C.oid) AS analyze_count,
-            pg_stat_get_autoanalyze_count(C.oid) AS autoanalyze_count
+            pg_stat_get_autoanalyze_count(C.oid) AS autoanalyze_count,
+            pg_stat_get_total_vacuum_time(C.oid) AS total_vacuum_time,
+            pg_stat_get_total_autovacuum_time(C.oid) AS total_autovacuum_time,
+            pg_stat_get_total_analyze_time(C.oid) AS total_analyze_time,
+            pg_stat_get_total_autoanalyze_time(C.oid) AS total_autoanalyze_time
     FROM pg_class C LEFT JOIN
          pg_index I ON C.oid = I.indrelid
          LEFT JOIN pg_namespace N ON (N.oid = C.relnamespace)
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 2a7769b1fd..768e1b509e 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -299,6 +299,8 @@ do_analyze_rel(Relation onerel, VacuumParams *params,
 	HeapTuple  *rows;
 	PGRUsage	ru0;
 	TimestampTz starttime = 0;
+	TimestampTz endtime = 0;
+	PgStat_Counter elapsedtime = 0;
 	MemoryContext caller_context;
 	Oid			save_userid;
 	int			save_sec_context;
@@ -344,8 +346,8 @@ do_analyze_rel(Relation onerel, VacuumParams *params,
 	RestrictSearchPath();
 
 	/*
-	 * measure elapsed time if called with verbose or if autovacuum logging
-	 * requires it
+	 * When verbose or autovacuum logging is used, initialize a resource usage
+	 * snapshot and optionally track I/O timing.
 	 */
 	if (instrument)
 	{
@@ -356,9 +358,10 @@ do_analyze_rel(Relation onerel, VacuumParams *params,
 		}
 
 		pg_rusage_init(&ru0);
-		starttime = GetCurrentTimestamp();
 	}
 
+	starttime = GetCurrentTimestamp();
+
 	/*
 	 * Determine which columns to analyze
 	 *
@@ -682,6 +685,9 @@ do_analyze_rel(Relation onerel, VacuumParams *params,
 							in_outer_xact);
 	}
 
+	elapsedtime = TimestampDifferenceMilliseconds(starttime,
+												  GetCurrentTimestamp());
+
 	/*
 	 * Now report ANALYZE to the cumulative stats system.  For regular tables,
 	 * we do it only if not doing inherited stats.  For partitioned tables, we
@@ -693,9 +699,9 @@ do_analyze_rel(Relation onerel, VacuumParams *params,
 	 */
 	if (!inh)
 		pgstat_report_analyze(onerel, totalrows, totaldeadrows,
-							  (va_cols == NIL));
+							  (va_cols == NIL), elapsedtime);
 	else if (onerel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE)
-		pgstat_report_analyze(onerel, 0, 0, (va_cols == NIL));
+		pgstat_report_analyze(onerel, 0, 0, (va_cols == NIL), elapsedtime);
 
 	/*
 	 * If this isn't part of VACUUM ANALYZE, let index AMs do cleanup.
@@ -732,8 +738,6 @@ do_analyze_rel(Relation onerel, VacuumParams *params,
 	/* Log the action if appropriate */
 	if (instrument)
 	{
-		TimestampTz endtime = GetCurrentTimestamp();
-
 		if (verbose || params->log_min_duration == 0 ||
 			TimestampDifferenceExceeds(starttime, endtime,
 									   params->log_min_duration))
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index 09247ba097..6a2033524a 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -208,20 +208,17 @@ pgstat_drop_relation(Relation rel)
  */
 void
 pgstat_report_vacuum(Oid tableoid, bool shared,
-					 PgStat_Counter livetuples, PgStat_Counter deadtuples)
+					 PgStat_Counter livetuples, PgStat_Counter deadtuples,
+					 TimestampTz endtime, PgStat_Counter elapsedtime)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
 	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
-	TimestampTz ts;
 
 	if (!pgstat_track_counts)
 		return;
 
-	/* Store the data in the table's hash table entry. */
-	ts = GetCurrentTimestamp();
-
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
 	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
 											dboid, tableoid, false);
@@ -246,15 +243,20 @@ pgstat_report_vacuum(Oid tableoid, bool shared,
 
 	if (AmAutoVacuumWorkerProcess())
 	{
-		tabentry->last_autovacuum_time = ts;
+		tabentry->last_autovacuum_time = endtime;
 		tabentry->autovacuum_count++;
 	}
 	else
 	{
-		tabentry->last_vacuum_time = ts;
+		tabentry->last_vacuum_time = endtime;
 		tabentry->vacuum_count++;
 	}
 
+	if (AmAutoVacuumWorkerProcess())
+		tabentry->total_autovacuum_time += elapsedtime;
+	else
+		tabentry->total_vacuum_time += elapsedtime;
+
 	pgstat_unlock_entry(entry_ref);
 
 	/*
@@ -276,7 +278,7 @@ pgstat_report_vacuum(Oid tableoid, bool shared,
 void
 pgstat_report_analyze(Relation rel,
 					  PgStat_Counter livetuples, PgStat_Counter deadtuples,
-					  bool resetcounter)
+					  bool resetcounter, PgStat_Counter elapsedtime)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
@@ -347,6 +349,11 @@ pgstat_report_analyze(Relation rel,
 		tabentry->analyze_count++;
 	}
 
+	if (AmAutoVacuumWorkerProcess())
+		tabentry->total_autoanalyze_time += elapsedtime;
+	else
+		tabentry->total_analyze_time += elapsedtime;
+
 	pgstat_unlock_entry(entry_ref);
 
 	/* see pgstat_report_vacuum() */
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 5f8d20a406..e020fc4303 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -106,6 +106,34 @@ PG_STAT_GET_RELENTRY_INT64(tuples_updated)
 /* pg_stat_get_vacuum_count */
 PG_STAT_GET_RELENTRY_INT64(vacuum_count)
 
+#define PG_STAT_GET_RELENTRY_FLOAT8(stat)						\
+Datum															\
+CppConcat(pg_stat_get_,stat)(PG_FUNCTION_ARGS)					\
+{																\
+	Oid			relid = PG_GETARG_OID(0);						\
+	float8		result;											\
+	PgStat_StatTabEntry *tabentry;								\
+																\
+	if ((tabentry = pgstat_fetch_stat_tabentry(relid)) == NULL)	\
+		result = 0;												\
+	else														\
+		result = (float8) (tabentry->stat);						\
+																\
+	PG_RETURN_FLOAT8(result);									\
+}
+
+/* pg_stat_get_total_vacuum_time */
+PG_STAT_GET_RELENTRY_FLOAT8(total_vacuum_time)
+
+/* pg_stat_get_total_autovacuum_time */
+PG_STAT_GET_RELENTRY_FLOAT8(total_autovacuum_time)
+
+/* pg_stat_get_total_analyze_time */
+PG_STAT_GET_RELENTRY_FLOAT8(total_analyze_time)
+
+/* pg_stat_get_total_autoanalyze_time */
+PG_STAT_GET_RELENTRY_FLOAT8(total_autoanalyze_time)
+
 #define PG_STAT_GET_RELENTRY_TIMESTAMPTZ(stat)					\
 Datum															\
 CppConcat(pg_stat_get_,stat)(PG_FUNCTION_ARGS)					\
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index b37e8a6f88..4ca8430b67 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -5540,6 +5540,22 @@
   proname => 'pg_stat_get_autoanalyze_count', provolatile => 's',
   proparallel => 'r', prorettype => 'int8', proargtypes => 'oid',
   prosrc => 'pg_stat_get_autoanalyze_count' },
+{ oid => '8406', descr => 'total vacuum time, in milliseconds',
+  proname => 'pg_stat_get_total_vacuum_time', provolatile => 's',
+  proparallel => 'r', prorettype => 'float8', proargtypes => 'oid',
+  prosrc => 'pg_stat_get_total_vacuum_time' },
+{ oid => '8407', descr => 'total autovacuum time, in milliseconds',
+  proname => 'pg_stat_get_total_autovacuum_time', provolatile => 's',
+  proparallel => 'r', prorettype => 'float8', proargtypes => 'oid',
+  prosrc => 'pg_stat_get_total_autovacuum_time' },
+{ oid => '8408', descr => 'total analyze time, in milliseconds',
+  proname => 'pg_stat_get_total_analyze_time', provolatile => 's',
+  proparallel => 'r', prorettype => 'float8', proargtypes => 'oid',
+  prosrc => 'pg_stat_get_total_analyze_time' },
+{ oid => '8409', descr => 'total autoanalyze time, in milliseconds',
+  proname => 'pg_stat_get_total_autoanalyze_time', provolatile => 's',
+  proparallel => 'r', prorettype => 'float8', proargtypes => 'oid',
+  prosrc => 'pg_stat_get_total_autoanalyze_time' },
 { oid => '1936', descr => 'statistics: currently active backend IDs',
   proname => 'pg_stat_get_backend_idset', prorows => '100', proretset => 't',
   provolatile => 's', proparallel => 'r', prorettype => 'int4',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 6475889c58..5ce2d5d718 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -502,6 +502,11 @@ typedef struct PgStat_StatTabEntry
 	PgStat_Counter analyze_count;
 	TimestampTz last_autoanalyze_time;	/* autovacuum initiated */
 	PgStat_Counter autoanalyze_count;
+
+	PgStat_Counter total_vacuum_time;
+	PgStat_Counter total_autovacuum_time;
+	PgStat_Counter total_analyze_time;
+	PgStat_Counter total_autoanalyze_time;
 } PgStat_StatTabEntry;
 
 typedef struct PgStat_WalStats
@@ -676,10 +681,11 @@ extern void pgstat_assoc_relation(Relation rel);
 extern void pgstat_unlink_relation(Relation rel);
 
 extern void pgstat_report_vacuum(Oid tableoid, bool shared,
-								 PgStat_Counter livetuples, PgStat_Counter deadtuples);
+								 PgStat_Counter livetuples, PgStat_Counter deadtuples,
+								 TimestampTz endtime, PgStat_Counter elapsedtime);
 extern void pgstat_report_analyze(Relation rel,
 								  PgStat_Counter livetuples, PgStat_Counter deadtuples,
-								  bool resetcounter);
+								  bool resetcounter, PgStat_Counter elapsedtime);
 
 /*
  * If stats are enabled, but pending data hasn't been prepared yet, call
diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out
index 3014d047fe..33f631dafa 100644
--- a/src/test/regress/expected/rules.out
+++ b/src/test/regress/expected/rules.out
@@ -1804,7 +1804,11 @@ pg_stat_all_tables| SELECT c.oid AS relid,
     pg_stat_get_vacuum_count(c.oid) AS vacuum_count,
     pg_stat_get_autovacuum_count(c.oid) AS autovacuum_count,
     pg_stat_get_analyze_count(c.oid) AS analyze_count,
-    pg_stat_get_autoanalyze_count(c.oid) AS autoanalyze_count
+    pg_stat_get_autoanalyze_count(c.oid) AS autoanalyze_count,
+    pg_stat_get_total_vacuum_time(c.oid) AS total_vacuum_time,
+    pg_stat_get_total_autovacuum_time(c.oid) AS total_autovacuum_time,
+    pg_stat_get_total_analyze_time(c.oid) AS total_analyze_time,
+    pg_stat_get_total_autoanalyze_time(c.oid) AS total_autoanalyze_time
    FROM ((pg_class c
      LEFT JOIN pg_index i ON ((c.oid = i.indrelid)))
      LEFT JOIN pg_namespace n ON ((n.oid = c.relnamespace)))
@@ -2188,7 +2192,11 @@ pg_stat_sys_tables| SELECT relid,
     vacuum_count,
     autovacuum_count,
     analyze_count,
-    autoanalyze_count
+    autoanalyze_count,
+    total_vacuum_time,
+    total_autovacuum_time,
+    total_analyze_time,
+    total_autoanalyze_time
    FROM pg_stat_all_tables
   WHERE ((schemaname = ANY (ARRAY['pg_catalog'::name, 'information_schema'::name])) OR (schemaname ~ '^pg_toast'::text));
 pg_stat_user_functions| SELECT p.oid AS funcid,
@@ -2236,7 +2244,11 @@ pg_stat_user_tables| SELECT relid,
     vacuum_count,
     autovacuum_count,
     analyze_count,
-    autoanalyze_count
+    autoanalyze_count,
+    total_vacuum_time,
+    total_autovacuum_time,
+    total_analyze_time,
+    total_autoanalyze_time
    FROM pg_stat_all_tables
   WHERE ((schemaname <> ALL (ARRAY['pg_catalog'::name, 'information_schema'::name])) AND (schemaname !~ '^pg_toast'::text));
 pg_stat_wal| SELECT wal_records,
-- 
2.40.1