[CF 5732] v2 - Introduce some randomness to autovacuum

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

https://commitfest.postgresql.org/patch/5732

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/CAEG8a3Jw77SV7XWkYTN50jgYQ6CxcTCch=1a8a5ZmbLdD2yR8w@mail.gmail.com
Author(s): Zhao Junwang

Author: Commitfest Bot

src/backend/postmaster/autovacuum.c

@@ -79,6 +79,7 @@
 #include "catalog/pg_namespace.h"
 #include "commands/dbcommands.h"
 #include "commands/vacuum.h"
+#include "common/pg_prng.h"
 #include "common/int.h"
 #include "lib/ilist.h"
 #include "libpq/pqsignal.h"
@@ -132,9 +133,16 @@ int			autovacuum_multixact_freeze_max_age;
 
 double		autovacuum_vac_cost_delay;
 int			autovacuum_vac_cost_limit;
+int			autovacuum_vac_strategy;
 
 int			Log_autovacuum_min_duration = 600000;
 
+const struct config_enum_entry autovacuum_vac_strategy_options[] = {
+	{"sequential", AUTOVACUUM_VAC_STRATEGY_SEQUENTIAL, false},
+	{"random", AUTOVACUUM_VAC_STRATEGY_RANDOM, false},
+	{NULL, 0, false}
+};
+
 /* the minimum allowed time between two awakenings of the launcher */
 #define MIN_AUTOVAC_SLEEPTIME 100.0 /* milliseconds */
 #define MAX_AUTOVAC_SLEEPTIME 300	/* seconds */
@@ -2267,6 +2275,30 @@ do_autovacuum(void)
 										  "Autovacuum Portal",
 										  ALLOCSET_DEFAULT_SIZES);
 
+	/*
+	 * Randomly rotate the list of tables to vacuum.  This is to avoid always
+	 * vacuuming the same table first, which could lead to spinning on the
+	 * same table or vacuuming starvation.
+	 */
+	if (list_length(table_oids) > 1 && autovacuum_vac_strategy == AUTOVACUUM_VAC_STRATEGY_RANDOM)
+	{
+
+		int			rand = 0;
+		static pg_prng_state prng_state;
+		List	   *tmp_oids = NIL;
+
+		pg_prng_seed(&prng_state, (uint64) (getpid() ^ time(NULL)));
+		rand = (int) pg_prng_uint64_range(&prng_state, 0,
+										  list_length(table_oids) - 1);
+		if (rand != 0)
+		{
+			tmp_oids = list_copy_tail(table_oids, rand);
+			table_oids = list_copy_head(table_oids,
+										list_length(table_oids) - rand);
+			table_oids = list_concat(table_oids, tmp_oids);
+		}
+	}
+
 	/*
 	 * Perform operations on collected tables.
 	 */
@@ -3061,6 +3093,22 @@ relation_needs_vacanalyze(Oid relid,
 		float4		reltuples = classForm->reltuples;
 		int32		relpages = classForm->relpages;
 		int32		relallfrozen = classForm->relallfrozen;
+		float4		last_remove_tuples_percent = tabentry->last_autovacuum_removed_tuples_percent;
+		TimestampTz last_autovacuum_time = tabentry->last_autovacuum_time;
+
+		/*
+		 * If the last autovacuum removed tuples is less than 10% of the
+		 * current dead tuples, then skip vacuuming this table for some time.
+		 */
+		if (!TimestampDifferenceExceedsSeconds(last_autovacuum_time,
+											   GetCurrentTimestamp(),
+											   autovacuum_naptime) &&
+			last_remove_tuples_percent < 10.0)
+		{
+			*doanalyze = false;
+			*dovacuum = false;
+			return;
+		}
 
 		vactuples = tabentry->dead_tuples;
 		instuples = tabentry->ins_since_vacuum;
@@ -3282,6 +3330,7 @@ AutoVacuumRequestWork(AutoVacuumWorkItemType type, Oid relationId,
 		workitem->avw_used = true;
 		workitem->avw_active = false;
 		workitem->avw_type = type;
+
 		workitem->avw_database = MyDatabaseId;
 		workitem->avw_relation = relationId;
 		workitem->avw_blockNumber = blkno;

src/backend/utils/activity/pgstat_relation.c

@@ -217,6 +217,7 @@ pgstat_report_vacuum(Oid tableoid, bool shared,
 	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	PgStat_Counter old_dead_tuples;
 
 	if (!pgstat_track_counts)
 		return;
@@ -232,6 +233,7 @@ pgstat_report_vacuum(Oid tableoid, bool shared,
 	shtabentry = (PgStatShared_Relation *) entry_ref->shared_stats;
 	tabentry = &shtabentry->stats;
 
+	old_dead_tuples = tabentry->dead_tuples;
 	tabentry->live_tuples = livetuples;
 	tabentry->dead_tuples = deadtuples;
 
@@ -250,6 +252,11 @@ pgstat_report_vacuum(Oid tableoid, bool shared,
 	if (AmAutoVacuumWorkerProcess())
 	{
 		tabentry->last_autovacuum_time = ts;
+		if (old_dead_tuples > deadtuples)
+			tabentry->last_autovacuum_removed_tuples_percent =
+				100 * (old_dead_tuples - deadtuples) / old_dead_tuples;
+		else
+			tabentry->last_autovacuum_removed_tuples_percent = 0;
 		tabentry->autovacuum_count++;
 		tabentry->total_autovacuum_time += elapsedtime;
 	}

src/backend/utils/misc/guc_tables.c

@@ -5418,6 +5418,16 @@ struct config_enum ConfigureNamesEnum[] =
 		NULL, assign_io_method, NULL
 	},
 
+	{
+		{"autovacuum_vacuum_strategy", PGC_SIGHUP, VACUUM_AUTOVACUUM,
+			gettext_noop("Vacuum strategy for autovacuum."),
+			NULL
+		},
+		&autovacuum_vac_strategy,
+		AUTOVACUUM_VAC_STRATEGY_SEQUENTIAL, autovacuum_vac_strategy_options,
+		NULL, NULL, NULL
+	},
+
 	/* End-of-list marker */
 	{
 		{NULL, 0, 0, NULL, NULL}, NULL, 0, NULL, NULL, NULL, NULL

src/backend/utils/misc/postgresql.conf.sample

@@ -713,6 +713,7 @@ autovacuum_worker_slots = 16	# autovacuum worker slots to allocate
 #autovacuum_vacuum_cost_limit = -1	# default vacuum cost limit for
 					# autovacuum, -1 means use
 					# vacuum_cost_limit
+#autovacuum_vacuum_strategy = sequential
 
 # - Cost-Based Vacuum Delay -
 

src/include/pgstat.h

@@ -443,6 +443,7 @@ typedef struct PgStat_StatTabEntry
 	TimestampTz last_vacuum_time;	/* user initiated vacuum */
 	PgStat_Counter vacuum_count;
 	TimestampTz last_autovacuum_time;	/* autovacuum initiated */
+	PgStat_Counter last_autovacuum_removed_tuples_percent;
 	PgStat_Counter autovacuum_count;
 	TimestampTz last_analyze_time;	/* user initiated */
 	PgStat_Counter analyze_count;

src/include/postmaster/autovacuum.h

@@ -25,6 +25,12 @@ typedef enum
 	AVW_BRINSummarizeRange,
 } AutoVacuumWorkItemType;
 
+/* Autovacuum vacuum strategies */
+enum AutovacuumVacStrategy
+{
+	AUTOVACUUM_VAC_STRATEGY_SEQUENTIAL = 0,
+	AUTOVACUUM_VAC_STRATEGY_RANDOM,
+};
 
 /* GUC variables */
 extern PGDLLIMPORT bool autovacuum_start_daemon;
@@ -43,6 +49,7 @@ extern PGDLLIMPORT int autovacuum_freeze_max_age;
 extern PGDLLIMPORT int autovacuum_multixact_freeze_max_age;
 extern PGDLLIMPORT double autovacuum_vac_cost_delay;
 extern PGDLLIMPORT int autovacuum_vac_cost_limit;
+extern PGDLLIMPORT int autovacuum_vac_strategy;
 
 /* autovacuum launcher PID, only valid when worker is shutting down */
 extern PGDLLIMPORT int AutovacuumLauncherPid;

src/include/utils/guc.h

@@ -322,6 +322,7 @@ extern PGDLLIMPORT const struct config_enum_entry io_method_options[];
 extern PGDLLIMPORT const struct config_enum_entry recovery_target_action_options[];
 extern PGDLLIMPORT const struct config_enum_entry wal_level_options[];
 extern PGDLLIMPORT const struct config_enum_entry wal_sync_method_options[];
+extern PGDLLIMPORT const struct config_enum_entry autovacuum_vac_strategy_options[];
 
 /*
  * Functions exported by guc.c