From e757a4ae08269bdd8fdcf77b6eeff4a292d1a8ec Mon Sep 17 00:00:00 2001
From: Melanie Plageman <melanieplageman@gmail.com>
Date: Sat, 25 Mar 2023 14:14:55 -0400
Subject: [PATCH v13 4/4] Autovacuum refreshes cost-based delay params more
 often

The previous commit allowed VACUUM to reload the config file more often
so that cost-based delay parameters could take effect while VACUUMing a
relation. Autovacuum, however did not benefit from this change.

In order for autovacuum workers to safely update their own cost delay
and cost limit parameters without impacting performance, we had to
rethink when and how these values were accessed.

Previously, an autovacuum worker's wi_cost_limit was set only at the
beginning of vacuuming a table, after reloading the config file.
Therefore, at the time that autovac_balance_cost() is called, workers
vacuuming tables with no table options could still have different values
for their wi_cost_limit_base and wi_cost_delay.

Now that the cost parameters can be updated while vacuuming a table,
workers will (within some margin of error) have no reason to have
different values for cost limit and cost delay (in the absence of table
options). This removes the rationale for keeping cost limit and cost
delay in shared memory. Balancing the cost limit requires only the
number of active autovacuum workers vacuuming a table with no cost-based
table options.

Reviewed-by: Masahiko Sawada <sawada.mshk@gmail.com>
Reviewed-by: Kyotaro Horiguchi <horikyota.ntt@gmail.com>
Reviewed-by: Daniel Gustafsson <daniel@yesql.se>
Discussion: https://www.postgresql.org/message-id/flat/CAAKRu_ZngzqnEODc7LmS1NH04Kt6Y9huSjz5pp7%2BDXhrjDA0gw%40mail.gmail.com
---
 src/backend/commands/vacuum.c       |  17 +-
 src/backend/postmaster/autovacuum.c | 235 ++++++++++++++--------------
 src/include/commands/vacuum.h       |   1 +
 3 files changed, 134 insertions(+), 119 deletions(-)

diff --git a/src/backend/commands/vacuum.c b/src/backend/commands/vacuum.c
index 888eb022cc..3e34324645 100644
--- a/src/backend/commands/vacuum.c
+++ b/src/backend/commands/vacuum.c
@@ -2257,10 +2257,10 @@ vacuum_delay_point(void)
 
 	/*
 	 * Reload the configuration file if requested. This allows changes to
-	 * vacuum_cost_limit and vacuum_cost_delay to take effect while a table is
-	 * being vacuumed or analyzed. Analyze should not reload configuration
-	 * file if it is in an outer transaction, as we currently only allow
-	 * configuration reload when in top-level statements.
+	 * [autovacuum_]vacuum_cost_limit and [autovacuum_]vacuum_cost_delay to
+	 * take effect while a table is being vacuumed or analyzed. Analyze should
+	 * not reload configuration file if it is in an outer transaction, as we
+	 * currently only allow configuration reload when in top-level statements.
 	 */
 	if (ConfigReloadPending && vacuum_can_reload_config)
 	{
@@ -2306,7 +2306,14 @@ vacuum_delay_point(void)
 
 		VacuumCostBalance = 0;
 
-		VacuumUpdateCosts();
+		/*
+		 * Balance and update limit values for autovacuum workers. We must
+		 * always do this in case the autovacuum launcher or another
+		 * autovacuum worker has recalculated the number of workers across
+		 * which we must balance the limit. This is done by the launcher when
+		 * launching a new worker and by workers before vacuuming each table.
+		 */
+		AutoVacuumUpdateLimit();
 
 		/* Might have gotten an interrupt while sleeping */
 		CHECK_FOR_INTERRUPTS();
diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index 7a9738202f..8cb9bee4eb 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -139,6 +139,9 @@ int			Log_autovacuum_min_duration = 600000;
 static bool am_autovacuum_launcher = false;
 static bool am_autovacuum_worker = false;
 
+static double av_relopt_cost_delay = -1;
+static int	av_relopt_cost_limit = 0;
+
 /* Flags set by signal handlers */
 static volatile sig_atomic_t got_SIGUSR2 = false;
 
@@ -189,8 +192,8 @@ typedef struct autovac_table
 {
 	Oid			at_relid;
 	VacuumParams at_params;
-	double		at_vacuum_cost_delay;
-	int			at_vacuum_cost_limit;
+	double		at_relopt_vac_cost_delay;
+	int			at_relopt_vac_cost_limit;
 	bool		at_dobalance;
 	bool		at_sharedrel;
 	char	   *at_relname;
@@ -209,7 +212,7 @@ typedef struct autovac_table
  * wi_sharedrel flag indicating whether table is marked relisshared
  * wi_proc		pointer to PGPROC of the running worker, NULL if not started
  * wi_launchtime Time at which this worker was launched
- * wi_cost_*	Vacuum cost-based delay parameters current in this worker
+ * wi_dobalance Whether this worker should be included in balance calculations
  *
  * All fields are protected by AutovacuumLock, except for wi_tableoid and
  * wi_sharedrel which are protected by AutovacuumScheduleLock (note these
@@ -223,11 +226,8 @@ typedef struct WorkerInfoData
 	Oid			wi_tableoid;
 	PGPROC	   *wi_proc;
 	TimestampTz wi_launchtime;
-	bool		wi_dobalance;
+	pg_atomic_flag wi_dobalance;
 	bool		wi_sharedrel;
-	double		wi_cost_delay;
-	int			wi_cost_limit;
-	int			wi_cost_limit_base;
 } WorkerInfoData;
 
 typedef struct WorkerInfoData *WorkerInfo;
@@ -273,6 +273,8 @@ typedef struct AutoVacuumWorkItem
  * av_startingWorker pointer to WorkerInfo currently being started (cleared by
  *					the worker itself as soon as it's up and running)
  * av_workItems		work item array
+ * av_nworkersForBalance the number of autovacuum workers to use when
+ * 					calculating the per worker cost limit
  *
  * This struct is protected by AutovacuumLock, except for av_signal and parts
  * of the worker list (see above).
@@ -286,6 +288,7 @@ typedef struct
 	dlist_head	av_runningWorkers;
 	WorkerInfo	av_startingWorker;
 	AutoVacuumWorkItem av_workItems[NUM_WORKITEMS];
+	pg_atomic_uint32 av_nworkersForBalance;
 } AutoVacuumShmemStruct;
 
 static AutoVacuumShmemStruct *AutoVacuumShmem;
@@ -319,7 +322,7 @@ static void launch_worker(TimestampTz now);
 static List *get_database_list(void);
 static void rebuild_database_list(Oid newdb);
 static int	db_comparator(const void *a, const void *b);
-static void autovac_balance_cost(void);
+static void autovac_recalculate_workers_for_balance(void);
 
 static void do_autovacuum(void);
 static void FreeWorkerInfo(int code, Datum arg);
@@ -670,7 +673,7 @@ AutoVacLauncherMain(int argc, char *argv[])
 			{
 				LWLockAcquire(AutovacuumLock, LW_EXCLUSIVE);
 				AutoVacuumShmem->av_signal[AutoVacRebalance] = false;
-				autovac_balance_cost();
+				autovac_recalculate_workers_for_balance();
 				LWLockRelease(AutovacuumLock);
 			}
 
@@ -820,8 +823,8 @@ HandleAutoVacLauncherInterrupts(void)
 			AutoVacLauncherShutdown();
 
 		/* rebalance in case the default cost parameters changed */
-		LWLockAcquire(AutovacuumLock, LW_EXCLUSIVE);
-		autovac_balance_cost();
+		LWLockAcquire(AutovacuumLock, LW_SHARED);
+		autovac_recalculate_workers_for_balance();
 		LWLockRelease(AutovacuumLock);
 
 		/* rebuild the list in case the naptime changed */
@@ -1755,10 +1758,7 @@ FreeWorkerInfo(int code, Datum arg)
 		MyWorkerInfo->wi_sharedrel = false;
 		MyWorkerInfo->wi_proc = NULL;
 		MyWorkerInfo->wi_launchtime = 0;
-		MyWorkerInfo->wi_dobalance = false;
-		MyWorkerInfo->wi_cost_delay = 0;
-		MyWorkerInfo->wi_cost_limit = 0;
-		MyWorkerInfo->wi_cost_limit_base = 0;
+		pg_atomic_clear_flag(&MyWorkerInfo->wi_dobalance);
 		dlist_push_head(&AutoVacuumShmem->av_freeWorkers,
 						&MyWorkerInfo->wi_links);
 		/* not mine anymore */
@@ -1787,14 +1787,21 @@ VacuumUpdateCosts(void)
 
 	if (am_autovacuum_worker)
 	{
-		VacuumCostLimit = MyWorkerInfo->wi_cost_limit;
-		VacuumCostDelay = MyWorkerInfo->wi_cost_delay;
+		if (av_relopt_cost_delay >= 0)
+			VacuumCostDelay = av_relopt_cost_delay;
+		else if (autovacuum_vac_cost_delay >= 0)
+			VacuumCostDelay = autovacuum_vac_cost_delay;
+		else
+			/* fall back to vacuum_cost_delay */
+			VacuumCostDelay = vacuum_cost_delay;
+
+		AutoVacuumUpdateLimit();
 	}
 	else
 	{
 		/* Must be explicit VACUUM or ANALYZE */
-		VacuumCostLimit = vacuum_cost_limit;
 		VacuumCostDelay = vacuum_cost_delay;
+		VacuumCostLimit = vacuum_cost_limit;
 	}
 
 	/*
@@ -1817,85 +1824,82 @@ VacuumUpdateCosts(void)
 }
 
 /*
- * autovac_balance_cost
- *		Recalculate the cost limit setting for each active worker.
- *
- * Caller must hold the AutovacuumLock in exclusive mode.
- */
-static void
-autovac_balance_cost(void)
+* Update VacuumCostLimit with the correct value for an autovacuum worker, given
+* the value of other relevant cost limit parameters and the number of workers
+* across which the limit must be balanced. Autovacuum workers must call this
+* regularly in case av_nworkers_for_balance has been updated by another worker
+* or by the autovacuum launcher. They must also call it after a config reload.
+*/
+void
+AutoVacuumUpdateLimit(void)
 {
+	if (!am_autovacuum_worker)
+		return;
+
 	/*
-	 * The idea here is that we ration out I/O equally.  The amount of I/O
-	 * that a worker can consume is determined by cost_limit/cost_delay, so we
-	 * try to equalize those ratios rather than the raw limit settings.
-	 *
 	 * note: in cost_limit, zero also means use value from elsewhere, because
 	 * zero is not a valid value.
 	 */
-	int			vac_cost_limit = (autovacuum_vac_cost_limit > 0 ?
-								  autovacuum_vac_cost_limit : vacuum_cost_limit);
-	double		vac_cost_delay = (autovacuum_vac_cost_delay >= 0 ?
-								  autovacuum_vac_cost_delay : vacuum_cost_delay);
-	double		cost_total;
-	double		cost_avail;
-	dlist_iter	iter;
-
-	/* not set? nothing to do */
-	if (vac_cost_limit <= 0 || vac_cost_delay <= 0)
-		return;
 
-	/* calculate the total base cost limit of participating active workers */
-	cost_total = 0.0;
-	dlist_foreach(iter, &AutoVacuumShmem->av_runningWorkers)
+	if (av_relopt_cost_limit > 0)
+		VacuumCostLimit = av_relopt_cost_limit;
+	else
 	{
-		WorkerInfo	worker = dlist_container(WorkerInfoData, wi_links, iter.cur);
+		int			nworkers_for_balance;
+
+		if (autovacuum_vac_cost_limit > 0)
+			VacuumCostLimit = autovacuum_vac_cost_limit;
+		else
+			VacuumCostLimit = vacuum_cost_limit;
+
+		/* Only balance limit if no table options specified */
+		if (pg_atomic_unlocked_test_flag(&MyWorkerInfo->wi_dobalance))
+			return;
+
+		Assert(VacuumCostLimit > 0);
 
-		if (worker->wi_proc != NULL &&
-			worker->wi_dobalance &&
-			worker->wi_cost_limit_base > 0 && worker->wi_cost_delay > 0)
-			cost_total +=
-				(double) worker->wi_cost_limit_base / worker->wi_cost_delay;
+		nworkers_for_balance = pg_atomic_read_u32(
+								&AutoVacuumShmem->av_nworkersForBalance);
+
+		/* There is at least 1 autovac worker (this worker). */
+		Assert(nworkers_for_balance > 0);
+
+		VacuumCostLimit = Max(VacuumCostLimit / nworkers_for_balance, 1);
 	}
+}
 
-	/* there are no cost limits -- nothing to do */
-	if (cost_total <= 0)
-		return;
+/*
+ * autovac_recalculate_workers_for_balance
+ *		Recalculate the number of workers to consider, given table options and
+ *		the current number of active workers.
+ *
+ * Caller must hold the AutovacuumLock in at least shared mode to access
+ * worker->wi_proc.
+ */
+static void
+autovac_recalculate_workers_for_balance(void)
+{
+	dlist_iter	iter;
+	int			orig_nworkers_for_balance;
+	int			nworkers_for_balance = 0;
+
+	orig_nworkers_for_balance =
+		pg_atomic_read_u32(&AutoVacuumShmem->av_nworkersForBalance);
 
-	/*
-	 * Adjust cost limit of each active worker to balance the total of cost
-	 * limit to autovacuum_vacuum_cost_limit.
-	 */
-	cost_avail = (double) vac_cost_limit / vac_cost_delay;
 	dlist_foreach(iter, &AutoVacuumShmem->av_runningWorkers)
 	{
 		WorkerInfo	worker = dlist_container(WorkerInfoData, wi_links, iter.cur);
 
-		if (worker->wi_proc != NULL &&
-			worker->wi_dobalance &&
-			worker->wi_cost_limit_base > 0 && worker->wi_cost_delay > 0)
-		{
-			int			limit = (int)
-			(cost_avail * worker->wi_cost_limit_base / cost_total);
-
-			/*
-			 * We put a lower bound of 1 on the cost_limit, to avoid division-
-			 * by-zero in the vacuum code.  Also, in case of roundoff trouble
-			 * in these calculations, let's be sure we don't ever set
-			 * cost_limit to more than the base value.
-			 */
-			worker->wi_cost_limit = Max(Min(limit,
-											worker->wi_cost_limit_base),
-										1);
-		}
+		if (worker->wi_proc == NULL ||
+			pg_atomic_unlocked_test_flag(&worker->wi_dobalance))
+			continue;
 
-		if (worker->wi_proc != NULL)
-			elog(DEBUG2, "autovac_balance_cost(pid=%d db=%u, rel=%u, dobalance=%s cost_limit=%d, cost_limit_base=%d, cost_delay=%g)",
-				 worker->wi_proc->pid, worker->wi_dboid, worker->wi_tableoid,
-				 worker->wi_dobalance ? "yes" : "no",
-				 worker->wi_cost_limit, worker->wi_cost_limit_base,
-				 worker->wi_cost_delay);
+		nworkers_for_balance++;
 	}
+
+	if (nworkers_for_balance != orig_nworkers_for_balance)
+		pg_atomic_write_u32(&AutoVacuumShmem->av_nworkersForBalance,
+							nworkers_for_balance);
 }
 
 /*
@@ -2443,23 +2447,31 @@ do_autovacuum(void)
 			continue;
 		}
 
-		/* Must hold AutovacuumLock while mucking with cost balance info */
-		LWLockAcquire(AutovacuumLock, LW_EXCLUSIVE);
 
-		/* advertise my cost delay parameters for the balancing algorithm */
-		MyWorkerInfo->wi_dobalance = tab->at_dobalance;
-		MyWorkerInfo->wi_cost_delay = tab->at_vacuum_cost_delay;
-		MyWorkerInfo->wi_cost_limit = tab->at_vacuum_cost_limit;
-		MyWorkerInfo->wi_cost_limit_base = tab->at_vacuum_cost_limit;
+		/*
+		 * Save the cost-related table options in global variables for
+		 * reference when updating VacuumCostLimit and VacuumCostDelay during
+		 * vacuuming this table.
+		 */
+		av_relopt_cost_limit = tab->at_relopt_vac_cost_limit;
+		av_relopt_cost_delay = tab->at_relopt_vac_cost_delay;
 
-		/* do a balance */
-		autovac_balance_cost();
+		if (tab->at_dobalance)
+			pg_atomic_test_set_flag(&MyWorkerInfo->wi_dobalance);
+		else
+			pg_atomic_clear_flag(&MyWorkerInfo->wi_dobalance);
 
-		/* set the active cost parameters from the result of that */
+		LWLockAcquire(AutovacuumLock, LW_SHARED);
+		autovac_recalculate_workers_for_balance();
+		LWLockRelease(AutovacuumLock);
+
+		/*
+		 * We wait until this point to update cost delay and cost limit
+		 * values, even though we reloaded the configuration file above, so
+		 * that we can take into account the cost-related table options.
+		 */
 		VacuumUpdateCosts();
 
-		/* done */
-		LWLockRelease(AutovacuumLock);
 
 		/* clean up memory before each iteration */
 		MemoryContextResetAndDeleteChildren(PortalContext);
@@ -2544,10 +2556,10 @@ deleted:
 
 		/*
 		 * Remove my info from shared memory.  We could, but intentionally
-		 * don't, clear wi_cost_limit and friends --- this is on the
-		 * assumption that we probably have more to do with similar cost
-		 * settings, so we don't want to give up our share of I/O for a very
-		 * short interval and thereby thrash the global balance.
+		 * don't, unset wi_dobalance on the assumption that we are more likely
+		 * than not to vacuum a table with no table options next, so we don't
+		 * want to give up our share of I/O for a very short interval and
+		 * thereby thrash the global balance.
 		 */
 		LWLockAcquire(AutovacuumScheduleLock, LW_EXCLUSIVE);
 		MyWorkerInfo->wi_tableoid = InvalidOid;
@@ -2584,6 +2596,7 @@ deleted:
 		{
 			ConfigReloadPending = false;
 			ProcessConfigFile(PGC_SIGHUP);
+			VacuumUpdateCosts();
 		}
 
 		LWLockAcquire(AutovacuumLock, LW_EXCLUSIVE);
@@ -2819,8 +2832,6 @@ table_recheck_autovac(Oid relid, HTAB *table_toast_map,
 		int			freeze_table_age;
 		int			multixact_freeze_min_age;
 		int			multixact_freeze_table_age;
-		int			vac_cost_limit;
-		double		vac_cost_delay;
 		int			log_min_duration;
 
 		/*
@@ -2830,20 +2841,6 @@ table_recheck_autovac(Oid relid, HTAB *table_toast_map,
 		 * defaults, autovacuum's own first and plain vacuum second.
 		 */
 
-		/* -1 in autovac setting means use plain vacuum_cost_delay */
-		vac_cost_delay = (avopts && avopts->vacuum_cost_delay >= 0)
-			? avopts->vacuum_cost_delay
-			: (autovacuum_vac_cost_delay >= 0)
-			? autovacuum_vac_cost_delay
-			: vacuum_cost_delay;
-
-		/* 0 or -1 in autovac setting means use plain vacuum_cost_limit */
-		vac_cost_limit = (avopts && avopts->vacuum_cost_limit > 0)
-			? avopts->vacuum_cost_limit
-			: (autovacuum_vac_cost_limit > 0)
-			? autovacuum_vac_cost_limit
-			: vacuum_cost_limit;
-
 		/* -1 in autovac setting means use log_autovacuum_min_duration */
 		log_min_duration = (avopts && avopts->log_min_duration >= 0)
 			? avopts->log_min_duration
@@ -2899,8 +2896,10 @@ table_recheck_autovac(Oid relid, HTAB *table_toast_map,
 		tab->at_params.multixact_freeze_table_age = multixact_freeze_table_age;
 		tab->at_params.is_wraparound = wraparound;
 		tab->at_params.log_min_duration = log_min_duration;
-		tab->at_vacuum_cost_limit = vac_cost_limit;
-		tab->at_vacuum_cost_delay = vac_cost_delay;
+		tab->at_relopt_vac_cost_limit = avopts ?
+			avopts->vacuum_cost_limit : 0;
+		tab->at_relopt_vac_cost_delay = avopts ?
+			avopts->vacuum_cost_delay : -1;
 		tab->at_relname = NULL;
 		tab->at_nspname = NULL;
 		tab->at_datname = NULL;
@@ -3392,10 +3391,18 @@ AutoVacuumShmemInit(void)
 		worker = (WorkerInfo) ((char *) AutoVacuumShmem +
 							   MAXALIGN(sizeof(AutoVacuumShmemStruct)));
 
+
 		/* initialize the WorkerInfo free list */
 		for (i = 0; i < autovacuum_max_workers; i++)
+		{
 			dlist_push_head(&AutoVacuumShmem->av_freeWorkers,
 							&worker[i].wi_links);
+
+			pg_atomic_init_flag(&worker[i].wi_dobalance);
+		}
+
+		pg_atomic_init_u32(&AutoVacuumShmem->av_nworkersForBalance, 0);
+
 	}
 	else
 		Assert(found);
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index a62dd2e781..6b286037ca 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -351,6 +351,7 @@ extern IndexBulkDeleteResult *vac_cleanup_one_index(IndexVacuumInfo *ivinfo,
 extern Size vac_max_items_to_alloc_size(int max_items);
 
 /* In postmaster/autovacuum.c */
+extern void AutoVacuumUpdateLimit(void);
 extern void VacuumUpdateCosts(void);
 
 /* in commands/vacuumparallel.c */
-- 
2.37.2

