[CF 6639] v14 - Track skipped vacuum and analyze in pg_stat_all_tables

This branch was automatically generated by a robot using patches from an
email thread registered at:

https://commitfest.postgresql.org/patch/6639

The branch will be overwritten each time a new patch version is posted to
the thread, and also periodically to check for bitrot caused by changes
on the master branch.

Patch(es): https://www.postgresql.org/message-id/20260728232710.a00f54d1136b788437b2eb7e@sraoss.co.jp
Author(s): Yugo Nagata

Author: Commitfest Bot

doc/src/sgml/monitoring.sgml

@@ -4683,6 +4683,16 @@ description | Waiting for a newly initialized WAL file to reach durable storage
       </para></entry>
      </row>
 
+     <row>
+      <entry role="catalog_table_entry"><para role="column_definition">
+       <structfield>last_lock_skipped_vacuum</structfield> <type>timestamp with time zone</type>
+      </para>
+      <para>
+       Last time a manual vacuum on this table was attempted but skipped due to
+       lock unavailability (not counting <command>VACUUM FULL</command>)
+      </para></entry>
+     </row>
+
      <row>
       <entry role="catalog_table_entry"><para role="column_definition">
        <structfield>last_autovacuum</structfield> <type>timestamp with time zone</type>
@@ -4693,6 +4703,16 @@ description | Waiting for a newly initialized WAL file to reach durable storage
       </para></entry>
      </row>
 
+     <row>
+      <entry role="catalog_table_entry"><para role="column_definition">
+       <structfield>last_lock_skipped_autovacuum</structfield> <type>timestamp with time zone</type>
+      </para>
+      <para>
+       Last time a vacuum on this table by the autovacuum daemon was attempted
+       but skipped due to lock unavailability
+      </para></entry>
+     </row>
+
      <row>
       <entry role="catalog_table_entry"><para role="column_definition">
        <structfield>last_analyze</structfield> <type>timestamp with time zone</type>
@@ -4702,6 +4722,16 @@ description | Waiting for a newly initialized WAL file to reach durable storage
       </para></entry>
      </row>
 
+     <row>
+      <entry role="catalog_table_entry"><para role="column_definition">
+       <structfield>last_lock_skipped_analyze</structfield> <type>timestamp with time zone</type>
+      </para>
+      <para>
+       Last time a manual analyze on this table was attempted but skipped due to
+       lock unavailability
+      </para></entry>
+     </row>
+
      <row>
       <entry role="catalog_table_entry"><para role="column_definition">
        <structfield>last_autoanalyze</structfield> <type>timestamp with time zone</type>
@@ -4712,6 +4742,16 @@ description | Waiting for a newly initialized WAL file to reach durable storage
       </para></entry>
      </row>
 
+     <row>
+      <entry role="catalog_table_entry"><para role="column_definition">
+       <structfield>last_lock_skipped_autoanalyze</structfield> <type>timestamp with time zone</type>
+      </para>
+      <para>
+       Last time at which an analyze on this table by the autovacuum was
+       attempted but skipped due to lock unavailability
+      </para></entry>
+     </row>
+
      <row>
       <entry role="catalog_table_entry"><para role="column_definition">
        <structfield>vacuum_count</structfield> <type>bigint</type>
@@ -4722,6 +4762,16 @@ description | Waiting for a newly initialized WAL file to reach durable storage
       </para></entry>
      </row>
 
+     <row>
+      <entry role="catalog_table_entry"><para role="column_definition">
+       <structfield>lock_skipped_vacuum_count</structfield> <type>bigint</type>
+      </para>
+      <para>
+       Number of times manual vacuums on this table have been attempted but skipped
+       due to lock unavailability (not counting <command>VACUUM FULL</command>)
+      </para></entry>
+     </row>
+
      <row>
       <entry role="catalog_table_entry"><para role="column_definition">
        <structfield>autovacuum_count</structfield> <type>bigint</type>
@@ -4732,6 +4782,16 @@ description | Waiting for a newly initialized WAL file to reach durable storage
       </para></entry>
      </row>
 
+     <row>
+      <entry role="catalog_table_entry"><para role="column_definition">
+       <structfield>lock_skipped_autovacuum_count</structfield> <type>bigint</type>
+      </para>
+      <para>
+       Number of times vacuums on this table by the autovacuum daemon have been
+       attempted but skipped due to lock unavailability
+      </para></entry>
+     </row>
+
      <row>
       <entry role="catalog_table_entry"><para role="column_definition">
        <structfield>analyze_count</structfield> <type>bigint</type>
@@ -4741,6 +4801,16 @@ description | Waiting for a newly initialized WAL file to reach durable storage
       </para></entry>
      </row>
 
+     <row>
+      <entry role="catalog_table_entry"><para role="column_definition">
+       <structfield>lock_skipped_analyze_count</structfield> <type>bigint</type>
+      </para>
+      <para>
+       Number of times manual analyzes on this table have been attempted but
+       skipped due to lock unavailability
+      </para></entry>
+     </row>
+
      <row>
       <entry role="catalog_table_entry"><para role="column_definition">
        <structfield>autoanalyze_count</structfield> <type>bigint</type>
@@ -4751,6 +4821,16 @@ description | Waiting for a newly initialized WAL file to reach durable storage
       </para></entry>
      </row>
 
+     <row>
+      <entry role="catalog_table_entry"><para role="column_definition">
+       <structfield>lock_skipped_autoanalyze_count</structfield> <type>bigint</type>
+      </para>
+      <para>
+       Number of times analyzes on this table by the autovacuum daemon have
+       been attempted but skipped due to lock unavailability
+      </para></entry>
+     </row>
+
      <row>
       <entry role="catalog_table_entry"><para role="column_definition">
        <structfield>total_vacuum_time</structfield> <type>double precision</type>
@@ -4806,6 +4886,14 @@ description | Waiting for a newly initialized WAL file to reach durable storage
    </tgroup>
   </table>
 
+  <note>
+   <para>
+    When a manual vacuum or analyze on a parent table in an inheritance or
+    partitioning hierarchy is skipped, the statistics are recorded only for
+    the parent table, not for its children.
+   </para>
+  </note>
+
  </sect2>
 
  <sect2 id="monitoring-pg-stat-autovacuum-scores-view">

src/backend/catalog/system_views.sql

@@ -736,13 +736,21 @@ CREATE VIEW pg_stat_all_tables AS
             pg_stat_get_mod_since_analyze(C.oid) AS n_mod_since_analyze,
             pg_stat_get_ins_since_vacuum(C.oid) AS n_ins_since_vacuum,
             pg_stat_get_last_vacuum_time(C.oid) as last_vacuum,
+            pg_stat_get_last_lock_skipped_vacuum_time(C.oid) as last_lock_skipped_vacuum,
             pg_stat_get_last_autovacuum_time(C.oid) as last_autovacuum,
+            pg_stat_get_last_lock_skipped_autovacuum_time(C.oid) as last_lock_skipped_autovacuum,
             pg_stat_get_last_analyze_time(C.oid) as last_analyze,
+            pg_stat_get_last_lock_skipped_analyze_time(C.oid) as last_lock_skipped_analyze,
             pg_stat_get_last_autoanalyze_time(C.oid) as last_autoanalyze,
+            pg_stat_get_last_lock_skipped_autoanalyze_time(C.oid) as last_lock_skipped_autoanalyze,
             pg_stat_get_vacuum_count(C.oid) AS vacuum_count,
+            pg_stat_get_lock_skipped_vacuum_count(C.oid) AS lock_skipped_vacuum_count,
             pg_stat_get_autovacuum_count(C.oid) AS autovacuum_count,
+            pg_stat_get_lock_skipped_autovacuum_count(C.oid) AS lock_skipped_autovacuum_count,
             pg_stat_get_analyze_count(C.oid) AS analyze_count,
+            pg_stat_get_lock_skipped_analyze_count(C.oid) AS lock_skipped_analyze_count,
             pg_stat_get_autoanalyze_count(C.oid) AS autoanalyze_count,
+            pg_stat_get_lock_skipped_autoanalyze_count(C.oid) AS lock_skipped_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,

src/backend/commands/vacuum.c

@@ -813,8 +813,26 @@ vacuum_open_relation(Oid relid, RangeVar *relation, uint32 options,
 		rel = try_relation_open(relid, NoLock);
 	else
 	{
+		int			flags = 0;
+
 		rel = NULL;
 		rel_lock = false;
+
+		if ((options & VACOPT_VACUUM) != 0 && (options & VACOPT_FULL) == 0)
+		{
+			if (AmAutoVacuumWorkerProcess())
+				flags |= PGSTAT_REPORT_LOCK_SKIPPED_AUTOVACUUM;
+			else
+				flags |= PGSTAT_REPORT_LOCK_SKIPPED_VACUUM;
+		}
+		if ((options & VACOPT_ANALYZE) != 0)
+		{
+			if (AmAutoVacuumWorkerProcess())
+				flags |= PGSTAT_REPORT_LOCK_SKIPPED_AUTOANALYZE;
+			else
+				flags |= PGSTAT_REPORT_LOCK_SKIPPED_ANALYZE;
+		}
+		pgstat_report_skipped_vacuum_analyze(relid, flags);
 	}
 
 	/* if relation is opened, leave */
@@ -950,6 +968,8 @@ expand_vacuum_rel(VacuumRelation *vrel, MemoryContext vac_context,
 		 */
 		if (!OidIsValid(relid))
 		{
+			int			flags = 0;
+
 			if (options & VACOPT_VACUUM)
 				ereport(WARNING,
 						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
@@ -960,6 +980,24 @@ expand_vacuum_rel(VacuumRelation *vrel, MemoryContext vac_context,
 						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
 						 errmsg("skipping analyze of \"%s\" --- lock not available",
 								vrel->relation->relname)));
+
+			/*
+			 * Get relid for statistics reporting.
+			 *
+			 * Since we failed to acquire the lock, use NoLock here.  Although
+			 * a concurrent DDL may have dropped or renamed the relation,
+			 * RangeVarGetRelid() with NoLock does not check for invalidation
+			 * messages.
+			 */
+			relid = RangeVarGetRelid(vrel->relation, NoLock, true);
+
+			if ((options & VACOPT_VACUUM) != 0 && (options & VACOPT_FULL) == 0)
+				flags |= PGSTAT_REPORT_LOCK_SKIPPED_VACUUM;
+			if ((options & VACOPT_ANALYZE) != 0)
+				flags |= PGSTAT_REPORT_LOCK_SKIPPED_ANALYZE;
+
+			pgstat_report_skipped_vacuum_analyze(relid, flags);
+
 			return vacrels;
 		}
 

src/backend/utils/activity/pgstat_relation.c

@@ -17,12 +17,16 @@
 
 #include "postgres.h"
 
+#include "access/htup_details.h"
 #include "access/twophase_rmgr.h"
 #include "access/xact.h"
 #include "catalog/catalog.h"
+#include "utils/injection_point.h"
+#include "utils/inval.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
 #include "utils/rel.h"
+#include "utils/syscache.h"
 #include "utils/timestamp.h"
 
 
@@ -420,6 +424,89 @@ pgstat_report_analyze(Relation rel,
 	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
 }
 
+/*
+ * Report that the table was skipped during vacuum or/and analyze.
+ */
+void
+pgstat_report_skipped_vacuum_analyze(Oid relid, int flags)
+{
+	PgStat_EntryRef *entry_ref;
+	PgStatShared_Relation *shtabentry;
+	PgStat_StatTabEntry *tabentry;
+	TimestampTz ts;
+	HeapTuple	classTup;
+	bool		isshared;
+
+	if (!pgstat_track_counts || !flags)
+		return;
+
+	classTup = SearchSysCache1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(classTup))
+		return;					/* somebody deleted the rel, forget it */
+	isshared = ((Form_pg_class) GETSTRUCT(classTup))->relisshared;
+	ReleaseSysCache(classTup);
+	INJECTION_POINT("skipped-vacuum-analyze-before-entry-lock", NULL);
+
+	/* Store the data in the table's hash table entry. */
+	ts = GetCurrentTimestamp();
+
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
+											isshared ? InvalidOid : MyDatabaseId,
+											relid, false);
+
+	/*
+	 * Re-check whether the relation still exists.  Unlike the normal stats
+	 * reporting path, we don't hold a relation lock here (the whole point of
+	 * SKIP_LOCKED is that we failed to acquire one).  Without a lock, a
+	 * concurrent DROP TABLE could commit between our earlier syscache lookup
+	 * and the stats entry creation above, leaving an orphaned stats entry.
+	 *
+	 * Accept cache invalidation messages first, so that a DROP that committed
+	 * after our earlier check is visible to the syscache lookup below.
+	 */
+	AcceptInvalidationMessages();
+	classTup = SearchSysCache1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(classTup))
+	{
+		pgstat_unlock_entry(entry_ref);
+		pgstat_drop_entry(PGSTAT_KIND_RELATION,
+						  isshared ? InvalidOid : MyDatabaseId, relid, true);
+		return;
+	}
+	ReleaseSysCache(classTup);
+
+	shtabentry = (PgStatShared_Relation *) entry_ref->shared_stats;
+	tabentry = &shtabentry->stats;
+
+	if (flags & PGSTAT_REPORT_LOCK_SKIPPED_VACUUM)
+	{
+		tabentry->last_lock_skipped_vacuum_time = ts;
+		tabentry->lock_skipped_vacuum_count++;
+	}
+	else if (flags & PGSTAT_REPORT_LOCK_SKIPPED_AUTOVACUUM)
+	{
+		tabentry->last_lock_skipped_autovacuum_time = ts;
+		tabentry->lock_skipped_autovacuum_count++;
+	}
+
+	if (flags & PGSTAT_REPORT_LOCK_SKIPPED_ANALYZE)
+	{
+		tabentry->last_lock_skipped_analyze_time = ts;
+		tabentry->lock_skipped_analyze_count++;
+	}
+	else if (flags & PGSTAT_REPORT_LOCK_SKIPPED_AUTOANALYZE)
+	{
+		tabentry->last_lock_skipped_autoanalyze_time = ts;
+		tabentry->lock_skipped_autoanalyze_count++;
+	}
+
+	pgstat_unlock_entry(entry_ref);
+
+	/* see pgstat_report_vacuum() */
+	pgstat_flush_io(false);
+	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+}
+
 /*
  * count a tuple insertion of n tuples
  */

src/backend/utils/adt/pgstatfuncs.c

@@ -84,6 +84,18 @@ PG_STAT_GET_RELENTRY_INT64(mod_since_analyze)
 /* pg_stat_get_numscans */
 PG_STAT_GET_RELENTRY_INT64(numscans)
 
+/* pg_stat_get_lock_skipped_analyze_count */
+PG_STAT_GET_RELENTRY_INT64(lock_skipped_analyze_count)
+
+/* pg_stat_get_lock_skipped_autoanalyze_count */
+PG_STAT_GET_RELENTRY_INT64(lock_skipped_autoanalyze_count)
+
+/* pg_stat_get_lock_skipped_autovacuum_count */
+PG_STAT_GET_RELENTRY_INT64(lock_skipped_autovacuum_count)
+
+/* pg_stat_get_lock_skipped_vacuum_count */
+PG_STAT_GET_RELENTRY_INT64(lock_skipped_vacuum_count)
+
 /* pg_stat_get_tuples_deleted */
 PG_STAT_GET_RELENTRY_INT64(tuples_deleted)
 
@@ -204,6 +216,18 @@ PG_STAT_GET_RELENTRY_TIMESTAMPTZ(last_vacuum_time)
 /* pg_stat_get_lastscan */
 PG_STAT_GET_RELENTRY_TIMESTAMPTZ(lastscan)
 
+/* pg_stat_get_last_lock_skipped_analyze_time */
+PG_STAT_GET_RELENTRY_TIMESTAMPTZ(last_lock_skipped_analyze_time)
+
+/* pg_stat_get_last_lock_skipped_autoanalyze_time */
+PG_STAT_GET_RELENTRY_TIMESTAMPTZ(last_lock_skipped_autoanalyze_time)
+
+/* pg_stat_get_last_lock_skipped_autovacuum_time */
+PG_STAT_GET_RELENTRY_TIMESTAMPTZ(last_lock_skipped_autovacuum_time)
+
+/* pg_stat_get_last_lock_skipped_vacuum_time */
+PG_STAT_GET_RELENTRY_TIMESTAMPTZ(last_lock_skipped_vacuum_time)
+
 /* pg_stat_get_stat_reset_time */
 PG_STAT_GET_RELENTRY_TIMESTAMPTZ(stat_reset_time)