On Tue, Apr 4, 2023 at 4:27 AM Masahiko Sawada <sawada.m...@gmail.com> wrote:
> The 0001 patch mostly looks good to me except for one
> point:
>
> @@ -391,7 +389,7 @@ heap_vacuum_rel(Relation rel, VacuumParams *params,
>          Assert(params->index_cleanup != VACOPTVALUE_UNSPECIFIED);
>          Assert(params->truncate != VACOPTVALUE_UNSPECIFIED &&
>                     params->truncate != VACOPTVALUE_AUTO);
> -        vacrel->failsafe_active = false;
> +        VacuumFailsafeActive = false;
>          vacrel->consider_bypass_optimization = true;
>          vacrel->do_index_vacuuming = true;
>
> Looking at the 0003 patch, we set VacuumFailsafeActive to false per table:
>
> +                        /*
> +                         * Ensure VacuumFailsafeActive has been reset
> before vacuuming the
> +                         * next relation relation.
> +                         */
> +                        VacuumFailsafeActive = false;
>
> Given that we ensure it's reset before vacuuming the next table, do we
> need to reset it in heap_vacuum_rel?

I've changed the one in heap_vacuum_rel() to an assert.

> (there is a typo; s/relation relation/relation/)

Thanks! fixed.

> > > 0002:
> > >
> > > @@ -2388,6 +2398,7 @@ vac_max_items_to_alloc_size(int max_items)
> > >          return offsetof(VacDeadItems, items) +
> > > sizeof(ItemPointerData) * max_items;
> > >  }
> > >
> > > +
> > >  /*
> > >   *     vac_tid_reaped() -- is a particular tid deletable?
> > >   *
> > >
> > > Unnecessary new line. There are some other unnecessary new lines in this 
> > > patch.
> >
> > Thanks! I think I got them all.
> >
> > > ---
> > > @@ -307,6 +309,8 @@ extern PGDLLIMPORT pg_atomic_uint32 
> > > *VacuumActiveNWorkers;
> > >  extern PGDLLIMPORT int VacuumCostBalanceLocal;
> > >
> > >  extern bool VacuumFailsafeActive;
> > > +extern int     VacuumCostLimit;
> > > +extern double VacuumCostDelay;
> > >
> > > and
> > >
> > > @@ -266,8 +266,6 @@ extern PGDLLIMPORT int 
> > > max_parallel_maintenance_workers;
> > >  extern PGDLLIMPORT int VacuumCostPageHit;
> > >  extern PGDLLIMPORT int VacuumCostPageMiss;
> > >  extern PGDLLIMPORT int VacuumCostPageDirty;
> > > -extern PGDLLIMPORT int VacuumCostLimit;
> > > -extern PGDLLIMPORT double VacuumCostDelay;
> > >
> > > Do we need PGDLLIMPORT too?
> >
> > I was on the fence about this. I annotated the new guc variables
> > vacuum_cost_delay and vacuum_cost_limit with PGDLLIMPORT, but I did not
> > annotate the variables used in vacuum code (VacuumCostLimit/Delay). I
> > think whether or not this is the right choice depends on two things:
> > whether or not my understanding of PGDLLIMPORT is correct and, if it is,
> > whether or not we want extensions to be able to access
> > VacuumCostLimit/Delay or if just access to the guc variables is
> > sufficient/desirable.
>
> I guess it would be better to keep both accessible for backward
> compatibility. Extensions are able to access both GUC values and
> values that are actually used for vacuum delays (as we used to use the
> same variables).

> Here are some review comments for 0002-0004 patches:
>
> 0002:
> -        if (MyWorkerInfo)
> +        if (am_autovacuum_launcher)
> +                return;
> +
> +        if (am_autovacuum_worker)
>          {
> -                VacuumCostDelay = MyWorkerInfo->wi_cost_delay;
>                  VacuumCostLimit = MyWorkerInfo->wi_cost_limit;
> +                VacuumCostDelay = MyWorkerInfo->wi_cost_delay;
> +        }
>
> Isn't it a bit safer to check MyWorkerInfo instead of
> am_autovacuum_worker?

Ah, since we access it. I've made the change.

> Also, I don't think there is any reason why we want to exclude only
> the autovacuum launcher.

My rationale is that the launcher is the only other process type which
might reasonably be executing this code besides autovac workers, client
backends doing VACUUM/ANALYZE, and parallel vacuum workers. Is it
confusing to have the launcher have VacuumCostLimt and VacuumCostDelay
set to the guc values for explicit VACUUM and ANALYZE -- even if the
launcher doesn't use these variables?

I've removed the check, because I do agree with you that it may be
unnecessarily confusing in the code.

> ---
> + * TODO: should VacuumCostLimit and VacuumCostDelay be initialized to valid 
> or
> + * invalid values?
>
> How about using the default value of normal backends, 200 and 0?

I've gone with this suggestion

> 0003:
>
> @@ -83,6 +84,7 @@ int                   vacuum_cost_limit;
>   */
>  int                    VacuumCostLimit = 0;
>  double         VacuumCostDelay = -1;
> +static bool vacuum_can_reload_config = false;
>
> In vacuum.c, we use snake case for GUC parameters and camel case for
> other global variables, so it seems better to rename it
> VacuumCanReloadConfig. Sorry, that's my fault.

I have renamed it.

> 0004:
>
> +                if (tab->at_dobalance)
> +                        pg_atomic_test_set_flag(&MyWorkerInfo->wi_dobalance);
> +                else
>
> The comment of pg_atomic_test_set_flag() says that it returns false if
> the flag has not successfully been set:
>
>  * pg_atomic_test_set_flag - TAS()
>  *
>  * Returns true if the flag has successfully been set, false otherwise.
>  *
>  * Acquire (including read barrier) semantics.
>
> But IIUC we don't need to worry about that as only one process updates
> the flag, right? It might be a good idea to add some comments why we
> don't need to check the return value.

I have added this comment.

> ---
> -                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);
>
> I think it's better to keep this kind of log in some form for
> debugging. For example, we can show these values of autovacuum workers
> in VacuumUpdateCosts().

I added a message to do_autovacuum() after calling VacuumUpdateCosts()
in the loop vacuuming each table. That means it will happen once per
table. It's not ideal that I had to move the call to VacuumUpdateCosts()
behind the shared lock in that loop so that we could access the pid and
such in the logging message after updating the cost and delay, but it is
probably okay. Though noone is going to be changing those at this
point, it still seemed better to access them under the lock.

This does mean we won't log anything when we do change the values of
VacuumCostDelay and VacuumCostLimit while vacuuming a table. Is it worth
adding some code to do that in VacuumUpdateCosts() (only when the value
has changed not on every call to VacuumUpdateCosts())? Or perhaps we
could add it in the config reload branch that is already in
vacuum_delay_point()?


On Tue, Apr 4, 2023 at 9:36 AM Daniel Gustafsson <dan...@yesql.se> wrote:
>

Thanks for the review!

> > On 4 Apr 2023, at 00:35, Melanie Plageman <melanieplage...@gmail.com> wrote:
> >
> > On Mon, Apr 3, 2023 at 3:08 PM Andres Freund <and...@anarazel.de> wrote:
> >> On 2023-04-03 14:43:14 -0400, Tom Lane wrote:
> >>> Melanie Plageman <melanieplage...@gmail.com> writes:
> >>>> v13 attached with requested updates.
> >>>
> >>> I'm afraid I'd not been paying any attention to this discussion,
> >>> but better late than never.  I'm okay with letting autovacuum
> >>> processes reload config files more often than now.  However,
> >>> I object to allowing ProcessConfigFile to be called from within
> >>> commands in a normal user backend.  The existing semantics are
> >>> that user backends respond to SIGHUP only at the start of processing
> >>> a user command, and I'm uncomfortable with suddenly deciding that
> >>> that can work differently if the command happens to be VACUUM.
> >>> It seems unprincipled and perhaps actively unsafe.
> >>
> >> I think it should be ok in commands like VACUUM that already internally 
> >> start
> >> their own transactions, and thus require to be run outside of a transaction
> >> and at the toplevel. I share your concerns about allowing config reload in
> >> arbitrary places. While we might want to go there, it would require a lot 
> >> more
> >> analysis.
>
> Thinking more on this I'm leaning towards going with allowing more frequent
> reloads in autovacuum, and saving the same for VACUUM for more careful study.
> The general case is probably fine but I'm not convinced that there aren't 
> error
> cases which can present unpleasant scenarios.

In attached v15, I've dropped support for VACUUM and non-nested ANALYZE.
It is like a 5 line change and could be added back at any time.

> > As an alternative for your consideration, attached v14 set implements
> > the config file reload for autovacuum only (in 0003) and then enables it
> > for VACUUM and ANALYZE not in a nested transaction command (in 0004).
> >
> > Previously I had the commits in the reverse order for ease of review (to
> > separate changes to worker limit balancing logic from config reload
> > code).
>
> A few comments on top of already submitted reviews, will do another pass over
> this later today.
>
> + * VacuumFailsafeActive is a defined as a global so that we can determine
> + * whether or not to re-enable cost-based vacuum delay when vacuuming a 
> table.
>
> This comment should be expanded to document who we expect to inspect this
> variable in order to decide on cost-based vacuum.
>
> Moving the failsafe switch into a global context means we face the risk of an
> extension changing it independently of the GUCs that control it (or the code
> relying on it) such that these are out of sync.  External code messing up
> internal state is not new and of course outside of our control, but it's worth
> at least considering.  There isn't too much we can do here, but perhaps expand
> this comment to include a "do not change this" note?

I've updated the comment to mention how table AM-agnostic VACUUM code
uses it and to say that table AMs can set it if they want that behavior.

> +extern bool VacuumFailsafeActive;
>
> While I agree with upthread review comments that extensions shoulnd't poke at
> this, not decorating it with PGDLLEXPORT adds little protection and only cause
> inconsistencies in symbol exports across platforms.  We only explicitly hide
> symbols in shared libraries IIRC.

I've updated this.

> +extern int VacuumCostLimit;
> +extern double VacuumCostDelay;
>  ...
> -extern PGDLLIMPORT int VacuumCostLimit;
> -extern PGDLLIMPORT double VacuumCostDelay;
>
> Same with these, I don't think this is according to our default visibility.
> Moreover, I'm not sure it's a good idea to perform this rename.  This will 
> keep
> VacuumCostLimit and VacuumCostDelay exported, but change their meaning.  Any
> external code referring to these thinking they are backing the GUCs will still
> compile, but may be broken in subtle ways.  Is there a reason for not keeping
> the current GUC variables and instead add net new ones?

When VacuumCostLimit was the same variable in the code and for the GUC
vacuum_cost_limit, everytime we reload the config file, VacuumCostLimit
is overwritten. Autovacuum workers have to overwrite this value with the
appropriate one for themselves given the balancing logic and the value
of autovacuum_vacuum_cost_limit. However, the problem is, because you
can specify -1 for autovacuum_vacuum_cost_limit to indicate it should
fall back to vacuum_cost_limit, we have to reference the value of
VacuumCostLimit when calculating the new autovacuum worker's cost limit
after a config reload.

But, you have to be sure you *only* do this after a config reload when
the value of VacuumCostLimit is fresh and unmodified or you risk
dividing the value of VacuumCostLimit over and over. That means it is
unsafe to call functions updating the cost limit more than once.

This orchestration wasn't as difficult when we only reloaded the config
file once every table. We were careful about it and also kept the
original "base" cost limit around from table_recheck_autovac(). However,
once we started reloading the config file more often, this no longer
works.

By separating the variables modified when the gucs are set and the ones
used the code, we can make sure we always have the original value the
guc was set to in vacuum_cost_limit and autovacuum_vacuum_cost_limit,
whenever we need to reference it.

That being said, perhaps we should document what extensions should do?
Do you think they will want to use the variables backing the gucs or to
be able to overwrite the variables being used in the code?

Oh, also I've annotated these with PGDLLIMPORT too.

> + * TODO: should VacuumCostLimit and VacuumCostDelay be initialized to valid 
> or
> + * invalid values?
> + */
> +int                    VacuumCostLimit = 0;
> +double         VacuumCostDelay = -1;
>
> I think the important part is to make sure they are never accessed without
> VacuumUpdateCosts having been called first.  I think that's the case here, but
> it's not entirely clear.  Do you see a codepath where that could happen?  If
> they are initialized to a sentinel value we also need to check for that, so
> initializing to the defaults from the corresponding GUCs seems better.

I don't see a case where autovacuum could access these without calling
VacuumUpdateCosts() first. I think the other callers of
vacuum_delay_point() are the issue (gist/gin/hash/etc).

It might need a bit more thought.

My concern was that these variables correspond to multiple GUCs each
depending on the backend type, and those backends have different
defaults (e.g. autovac workers default cost delay is different than
client backend doing vacuum cost delay).

However, what I have done in this version is initialize them to the
defaults for a client backend executing VACUUM or ANALYZE, since I am
fairly confident that autovacuum will not use them without calling
VacuumUpdateCosts().

>
> +* Update VacuumCostLimit with the correct value for an autovacuum worker, 
> given
>
> Trivial whitespace error in function comment.

Fixed.

> +static double av_relopt_cost_delay = -1;
> +static int av_relopt_cost_limit = 0;
>
> These need a comment IMO, ideally one that explain why they are initialized to
> those values.

I've added a comment.

> +       /* There is at least 1 autovac worker (this worker). */
> +       Assert(nworkers_for_balance > 0);
>
> Is there a scenario where this is expected to fail?  If so I think this should
> be handled and not just an Assert.

No, this isn't expected to happen because an autovacuum worker would
have called autovac_recalculate_workers_for_balance() before calling
VacuumUpdateCosts() (which calls AutoVacuumUpdateLimit()) in
do_autovacuum(). But, if someone were to move around or add a call to
VacuumUpdateCosts() there is a chance it could happen.

- Melanie
From 5b11ac2a9b1ddba24b95c5b2a33d791d99e615ba Mon Sep 17 00:00:00 2001
From: Melanie Plageman <melanieplage...@gmail.com>
Date: Fri, 31 Mar 2023 10:38:39 -0400
Subject: [PATCH v15 1/3] Make vacuum's failsafe_active a global

While vacuuming a table in failsafe mode, VacuumCostActive should not be
re-enabled. This currently isn't a problem because vacuum cost
parameters are only refreshed in between vacuuming tables and failsafe
status is reset for every table. In preparation for allowing vacuum cost
parameters to be updated more frequently, elevate
LVRelState->failsafe_active to a global, VacuumFailsafeActive, which
will be checked when determining whether or not to re-enable vacuum
cost-related delays.

Reviewed-by: Masahiko Sawada <sawada.m...@gmail.com>
Reviewed-by: Daniel Gustafsson <dan...@yesql.se>
Discussion: https://www.postgresql.org/message-id/flat/CAAKRu_ZngzqnEODc7LmS1NH04Kt6Y9huSjz5pp7%2BDXhrjDA0gw%40mail.gmail.com
---
 src/backend/access/heap/vacuumlazy.c | 16 +++++++---------
 src/backend/commands/vacuum.c        | 12 ++++++++++++
 src/include/commands/vacuum.h        |  1 +
 3 files changed, 20 insertions(+), 9 deletions(-)

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index 639179aa46..2ba85bd3d6 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -153,8 +153,6 @@ typedef struct LVRelState
 	bool		aggressive;
 	/* Use visibility map to skip? (disabled by DISABLE_PAGE_SKIPPING) */
 	bool		skipwithvm;
-	/* Wraparound failsafe has been triggered? */
-	bool		failsafe_active;
 	/* Consider index vacuuming bypass optimization? */
 	bool		consider_bypass_optimization;
 
@@ -391,7 +389,7 @@ heap_vacuum_rel(Relation rel, VacuumParams *params,
 	Assert(params->index_cleanup != VACOPTVALUE_UNSPECIFIED);
 	Assert(params->truncate != VACOPTVALUE_UNSPECIFIED &&
 		   params->truncate != VACOPTVALUE_AUTO);
-	vacrel->failsafe_active = false;
+	VacuumFailsafeActive = false;
 	vacrel->consider_bypass_optimization = true;
 	vacrel->do_index_vacuuming = true;
 	vacrel->do_index_cleanup = true;
@@ -709,7 +707,7 @@ heap_vacuum_rel(Relation rel, VacuumParams *params,
 			}
 			else
 			{
-				if (!vacrel->failsafe_active)
+				if (!VacuumFailsafeActive)
 					appendStringInfoString(&buf, _("index scan bypassed: "));
 				else
 					appendStringInfoString(&buf, _("index scan bypassed by failsafe: "));
@@ -2293,7 +2291,7 @@ lazy_vacuum(LVRelState *vacrel)
 		 * vacuuming or heap vacuuming.  This VACUUM operation won't end up
 		 * back here again.
 		 */
-		Assert(vacrel->failsafe_active);
+		Assert(VacuumFailsafeActive);
 	}
 
 	/*
@@ -2374,7 +2372,7 @@ lazy_vacuum_all_indexes(LVRelState *vacrel)
 	 */
 	Assert(vacrel->num_index_scans > 0 ||
 		   vacrel->dead_items->num_items == vacrel->lpdead_items);
-	Assert(allindexes || vacrel->failsafe_active);
+	Assert(allindexes || VacuumFailsafeActive);
 
 	/*
 	 * Increase and report the number of index scans.
@@ -2616,12 +2614,12 @@ static bool
 lazy_check_wraparound_failsafe(LVRelState *vacrel)
 {
 	/* Don't warn more than once per VACUUM */
-	if (vacrel->failsafe_active)
+	if (VacuumFailsafeActive)
 		return true;
 
 	if (unlikely(vacuum_xid_failsafe_check(&vacrel->cutoffs)))
 	{
-		vacrel->failsafe_active = true;
+		VacuumFailsafeActive = true;
 
 		/*
 		 * Abandon use of a buffer access strategy to allow use of all of
@@ -2820,7 +2818,7 @@ should_attempt_truncation(LVRelState *vacrel)
 {
 	BlockNumber possibly_freeable;
 
-	if (!vacrel->do_rel_truncate || vacrel->failsafe_active ||
+	if (!vacrel->do_rel_truncate || VacuumFailsafeActive ||
 		old_snapshot_threshold >= 0)
 		return false;
 
diff --git a/src/backend/commands/vacuum.c b/src/backend/commands/vacuum.c
index da85330ef4..cf3abb072c 100644
--- a/src/backend/commands/vacuum.c
+++ b/src/backend/commands/vacuum.c
@@ -72,6 +72,18 @@ int			vacuum_multixact_freeze_table_age;
 int			vacuum_failsafe_age;
 int			vacuum_multixact_failsafe_age;
 
+/*
+ * VacuumFailsafeActive is a defined as a global so that we can determine
+ * whether or not to re-enable cost-based vacuum delay when vacuuming a table.
+ * If failsafe mode has been engaged, we will not re-enable cost-based delay
+ * for the table until after vacuuming has completed, regardless of other
+ * settings. Only VACUUM code should inspect this variable and only table
+ * access methods should set it. In Table AM-agnostic VACUUM code, this
+ * variable controls whether or not to allow cost-based delays. Table AMs are
+ * free to use it if they desire this behavior.
+ */
+bool		VacuumFailsafeActive = false;
+
 /*
  * Variables for cost-based parallel vacuum.  See comments atop
  * compute_parallel_delay to understand how it works.
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index bdfd96cfec..7219c6ba9c 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -306,6 +306,7 @@ extern PGDLLIMPORT pg_atomic_uint32 *VacuumSharedCostBalance;
 extern PGDLLIMPORT pg_atomic_uint32 *VacuumActiveNWorkers;
 extern PGDLLIMPORT int VacuumCostBalanceLocal;
 
+extern PGDLLIMPORT bool VacuumFailsafeActive;
 
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
-- 
2.37.2

From 010136b5ad848590e6dfc139b45a0008e1d2afb8 Mon Sep 17 00:00:00 2001
From: Melanie Plageman <melanieplage...@gmail.com>
Date: Sat, 25 Mar 2023 14:14:55 -0400
Subject: [PATCH v15 3/3] Autovacuum refreshes cost-based delay params more
 often

Allow autovacuum to reload the config file more often so that cost-based
delay parameters can take effect while VACUUMing a relation. Previously
autovacuum workers only reloaded the config file once per relation
vacuumed, so config changes could not take effect until beginning to
vacuum the next table.

Now, check if a reload is pending roughly once per block, when checking
if we need to delay.

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.m...@gmail.com>
Reviewed-by: Kyotaro Horiguchi <horikyota....@gmail.com>
Reviewed-by: Daniel Gustafsson <dan...@yesql.se>
Discussion: https://www.postgresql.org/message-id/flat/CAAKRu_ZngzqnEODc7LmS1NH04Kt6Y9huSjz5pp7%2BDXhrjDA0gw%40mail.gmail.com
---
 src/backend/access/heap/vacuumlazy.c  |   2 +-
 src/backend/commands/vacuum.c         |  44 ++++-
 src/backend/commands/vacuumparallel.c |   1 -
 src/backend/postmaster/autovacuum.c   | 266 +++++++++++++++-----------
 src/include/commands/vacuum.h         |   1 +
 5 files changed, 196 insertions(+), 118 deletions(-)

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index 2ba85bd3d6..0a9ebd22bd 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -389,7 +389,7 @@ heap_vacuum_rel(Relation rel, VacuumParams *params,
 	Assert(params->index_cleanup != VACOPTVALUE_UNSPECIFIED);
 	Assert(params->truncate != VACOPTVALUE_UNSPECIFIED &&
 		   params->truncate != VACOPTVALUE_AUTO);
-	VacuumFailsafeActive = false;
+	Assert(!VacuumFailsafeActive);
 	vacrel->consider_bypass_optimization = true;
 	vacrel->do_index_vacuuming = true;
 	vacrel->do_index_cleanup = true;
diff --git a/src/backend/commands/vacuum.c b/src/backend/commands/vacuum.c
index b1fc7a0efc..9964c9ea4d 100644
--- a/src/backend/commands/vacuum.c
+++ b/src/backend/commands/vacuum.c
@@ -48,6 +48,7 @@
 #include "pgstat.h"
 #include "postmaster/autovacuum.h"
 #include "postmaster/bgworker_internals.h"
+#include "postmaster/interrupt.h"
 #include "storage/bufmgr.h"
 #include "storage/lmgr.h"
 #include "storage/pmsignal.h"
@@ -512,9 +513,9 @@ vacuum(List *relations, VacuumParams *params,
 	{
 		ListCell   *cur;
 
-		VacuumUpdateCosts();
 		in_vacuum = true;
-		VacuumCostActive = (VacuumCostDelay > 0);
+		VacuumFailsafeActive = false;
+		VacuumUpdateCosts();
 		VacuumCostBalance = 0;
 		VacuumPageHit = 0;
 		VacuumPageMiss = 0;
@@ -568,12 +569,20 @@ vacuum(List *relations, VacuumParams *params,
 					CommandCounterIncrement();
 				}
 			}
+
+			/*
+			 * Ensure VacuumFailsafeActive has been reset before vacuuming the
+			 * next relation.
+			 */
+			VacuumFailsafeActive = false;
 		}
 	}
 	PG_FINALLY();
 	{
 		in_vacuum = false;
 		VacuumCostActive = false;
+		VacuumFailsafeActive = false;
+		VacuumCostBalance = 0;
 	}
 	PG_END_TRY();
 
@@ -2240,7 +2249,27 @@ vacuum_delay_point(void)
 	/* Always check for interrupts */
 	CHECK_FOR_INTERRUPTS();
 
-	if (!VacuumCostActive || InterruptPending)
+	if (InterruptPending ||
+		(!VacuumCostActive && !ConfigReloadPending))
+		return;
+
+	/*
+	 * Reload the configuration file if requested. This allows changes to
+	 * autovacuum_vacuum_cost_limit and autovacuum_vacuum_cost_delay to take
+	 * effect while a table is being vacuumed or analyzed.
+	 */
+	if (ConfigReloadPending && IsAutoVacuumWorkerProcess())
+	{
+		ConfigReloadPending = false;
+		ProcessConfigFile(PGC_SIGHUP);
+		VacuumUpdateCosts();
+	}
+
+	/*
+	 * If we disabled cost-based delays after reloading the config file,
+	 * return.
+	 */
+	if (!VacuumCostActive)
 		return;
 
 	/*
@@ -2273,7 +2302,14 @@ 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/commands/vacuumparallel.c b/src/backend/commands/vacuumparallel.c
index 0b59c922e4..e200d5caf8 100644
--- a/src/backend/commands/vacuumparallel.c
+++ b/src/backend/commands/vacuumparallel.c
@@ -995,7 +995,6 @@ parallel_vacuum_main(dsm_segment *seg, shm_toc *toc)
 												 false);
 
 	/* Set cost-based vacuum delay */
-	VacuumCostActive = (VacuumCostDelay > 0);
 	VacuumUpdateCosts();
 	VacuumCostBalance = 0;
 	VacuumPageHit = 0;
diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index ce7e009576..0c1e4652fb 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -139,6 +139,17 @@ int			Log_autovacuum_min_duration = 600000;
 static bool am_autovacuum_launcher = false;
 static bool am_autovacuum_worker = false;
 
+/*
+ * Variables to save the cost-related table options for the current relation
+ * being vacuumed by this autovacuum worker. Using these, we can ensure we
+ * don't overwrite the values of VacuumCostDelay and VacuumCostLimit after
+ * reloading the configuration file. They are initialized to "invalid" values
+ * to indicate no table options were specified and will be set in
+ * do_autovacuum() after checking the table options in table_recheck_autovac().
+ */
+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 +200,8 @@ 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 +220,7 @@ 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 +234,8 @@ 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 +281,8 @@ 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 +296,7 @@ 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 +330,7 @@ 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 +681,7 @@ 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 +831,8 @@ 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 +1766,7 @@ 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 */
@@ -1784,97 +1792,119 @@ VacuumUpdateCosts(void)
 {
 	if (MyWorkerInfo)
 	{
-		VacuumCostDelay = MyWorkerInfo->wi_cost_delay;
-		VacuumCostLimit = MyWorkerInfo->wi_cost_limit;
+		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;
+	}
+
+	/*
+	 * If configuration changes are allowed to impact VacuumCostActive, make
+	 * sure it is updated.
+	 */
+	if (VacuumFailsafeActive)
+	{
+		Assert(!VacuumCostActive);
+		return;
+	}
+
+	if (VacuumCostDelay > 0)
+		VacuumCostActive = true;
+	else
+	{
+		VacuumCostActive = false;
+		VacuumCostBalance = 0;
 	}
 }
 
 /*
- * autovac_balance_cost
- *		Recalculate the cost limit setting for each active worker.
- *
- * Caller must hold the AutovacuumLock in exclusive mode.
+ * 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.
  */
-static void
-autovac_balance_cost(void)
+void
+AutoVacuumUpdateLimit(void)
 {
+	if (!MyWorkerInfo)
+		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;
 
-		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;
+		Assert(VacuumCostLimit > 0);
+
+		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);
 }
 
 /*
@@ -2422,22 +2452,39 @@ do_autovacuum(void)
 			continue;
 		}
 
-		/* Must hold AutovacuumLock while mucking with cost balance info */
-		LWLockAcquire(AutovacuumLock, LW_EXCLUSIVE);
+		/*
+		 * 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;
 
-		/* 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;
+		/*
+		 * We only expect this worker to ever set the flag, so don't bother
+		 * checking the return value. We shouldn't have to retry.
+		 */
+		if (tab->at_dobalance)
+			pg_atomic_test_set_flag(&MyWorkerInfo->wi_dobalance);
+		else
+			pg_atomic_clear_flag(&MyWorkerInfo->wi_dobalance);
 
-		/* do a balance */
-		autovac_balance_cost();
+		LWLockAcquire(AutovacuumLock, LW_SHARED);
 
-		/* set the active cost parameters from the result of that */
+		autovac_recalculate_workers_for_balance();
+
+		/*
+		 * 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 */
+		elog(DEBUG2, "VacuumUpdateCosts(pid=%d db=%u, rel=%u, dobalance=%s cost_limit=%d, cost_delay=%g)",
+			 MyWorkerInfo->wi_proc->pid, MyWorkerInfo->wi_dboid, MyWorkerInfo->wi_tableoid,
+			 pg_atomic_unlocked_test_flag(&MyWorkerInfo->wi_dobalance) ? "no" : "yes",
+			 VacuumCostLimit, VacuumCostDelay);
+
 		LWLockRelease(AutovacuumLock);
 
 		/* clean up memory before each iteration */
@@ -2523,10 +2570,10 @@ 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;
@@ -2563,6 +2610,7 @@ deleted:
 		{
 			ConfigReloadPending = false;
 			ProcessConfigFile(PGC_SIGHUP);
+			VacuumUpdateCosts();
 		}
 
 		LWLockAcquire(AutovacuumLock, LW_EXCLUSIVE);
@@ -2798,8 +2846,6 @@ 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;
 
 		/*
@@ -2809,20 +2855,6 @@ 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
@@ -2878,8 +2910,10 @@ 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;
@@ -3371,10 +3405,18 @@ 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 17cf58255f..ef938fb692 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

From 00ddceeb3e565bc88f9691da29e01903aa69cf22 Mon Sep 17 00:00:00 2001
From: Melanie Plageman <melanieplage...@gmail.com>
Date: Mon, 3 Apr 2023 11:22:18 -0400
Subject: [PATCH v15 2/3] Separate vacuum cost variables from gucs

Vacuum code run both by autovacuum workers and a backend doing
VACUUM/ANALYZE previously used VacuumCostLimit and VacuumCostDelay which
were the global variables for the gucs vacuum_cost_limit and
vacuum_cost_delay. Autovacuum workers needed to override these variables
with their own values, derived from autovacuum_vacuum_cost_limit and
autovacuum_vacuum_cost_delay and worker cost limit balancing logic. This
led to confusing code which, in some cases, both derived and set a new
value of VacuumCostLimit from VacuumCostLimit.

In preparation for refreshing these guc values more often, separate
these variables from the gucs themselves and add a function to update
the global variables using the gucs and existing logic.

Per suggestion by Kyotaro Horiguchi

Reviewed-by: Masahiko Sawada <sawada.m...@gmail.com>
Discussion: https://www.postgresql.org/message-id/flat/CAAKRu_ZngzqnEODc7LmS1NH04Kt6Y9huSjz5pp7%2BDXhrjDA0gw%40mail.gmail.com
---
 src/backend/commands/vacuum.c         | 15 +++++++++--
 src/backend/commands/vacuumparallel.c |  1 +
 src/backend/postmaster/autovacuum.c   | 38 +++++++++++----------------
 src/backend/utils/init/globals.c      |  2 --
 src/backend/utils/misc/guc_tables.c   |  4 +--
 src/include/commands/vacuum.h         |  7 +++++
 src/include/miscadmin.h               |  2 --
 src/include/postmaster/autovacuum.h   |  3 ---
 8 files changed, 39 insertions(+), 33 deletions(-)

diff --git a/src/backend/commands/vacuum.c b/src/backend/commands/vacuum.c
index cf3abb072c..b1fc7a0efc 100644
--- a/src/backend/commands/vacuum.c
+++ b/src/backend/commands/vacuum.c
@@ -71,6 +71,17 @@ int			vacuum_multixact_freeze_min_age;
 int			vacuum_multixact_freeze_table_age;
 int			vacuum_failsafe_age;
 int			vacuum_multixact_failsafe_age;
+double		vacuum_cost_delay;
+int			vacuum_cost_limit;
+
+/*
+ * Variables for cost-based vacuum delay. The defaults differ between
+ * autovacuum and vacuum. These should be overridden with the appropriate GUC
+ * value in vacuum code. These are initialized here to the defaults for client
+ * backends executing VACUUM or ANALYZE.
+ */
+int			VacuumCostLimit = 200;
+double		VacuumCostDelay = 0;
 
 /*
  * VacuumFailsafeActive is a defined as a global so that we can determine
@@ -501,6 +512,7 @@ vacuum(List *relations, VacuumParams *params,
 	{
 		ListCell   *cur;
 
+		VacuumUpdateCosts();
 		in_vacuum = true;
 		VacuumCostActive = (VacuumCostDelay > 0);
 		VacuumCostBalance = 0;
@@ -2261,8 +2273,7 @@ vacuum_delay_point(void)
 
 		VacuumCostBalance = 0;
 
-		/* update balance values for workers */
-		AutoVacuumUpdateDelay();
+		VacuumUpdateCosts();
 
 		/* Might have gotten an interrupt while sleeping */
 		CHECK_FOR_INTERRUPTS();
diff --git a/src/backend/commands/vacuumparallel.c b/src/backend/commands/vacuumparallel.c
index 563117a8f6..0b59c922e4 100644
--- a/src/backend/commands/vacuumparallel.c
+++ b/src/backend/commands/vacuumparallel.c
@@ -996,6 +996,7 @@ parallel_vacuum_main(dsm_segment *seg, shm_toc *toc)
 
 	/* Set cost-based vacuum delay */
 	VacuumCostActive = (VacuumCostDelay > 0);
+	VacuumUpdateCosts();
 	VacuumCostBalance = 0;
 	VacuumPageHit = 0;
 	VacuumPageMiss = 0;
diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index 585d28148c..ce7e009576 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -1774,17 +1774,25 @@ FreeWorkerInfo(int code, Datum arg)
 }
 
 /*
- * Update the cost-based delay parameters, so that multiple workers consume
- * each a fraction of the total available I/O.
+ * Update vacuum cost-based delay-related parameters for autovacuum workers and
+ * backends executing VACUUM or ANALYZE using the value of relevant gucs and
+ * global state. This must be called during setup for vacuum and after every
+ * config reload to ensure up-to-date values.
  */
 void
-AutoVacuumUpdateDelay(void)
+VacuumUpdateCosts(void)
 {
 	if (MyWorkerInfo)
 	{
 		VacuumCostDelay = MyWorkerInfo->wi_cost_delay;
 		VacuumCostLimit = MyWorkerInfo->wi_cost_limit;
 	}
+	else
+	{
+		/* Must be explicit VACUUM or ANALYZE */
+		VacuumCostLimit = vacuum_cost_limit;
+		VacuumCostDelay = vacuum_cost_delay;
+	}
 }
 
 /*
@@ -1805,9 +1813,9 @@ autovac_balance_cost(void)
 	 * zero is not a valid value.
 	 */
 	int			vac_cost_limit = (autovacuum_vac_cost_limit > 0 ?
-								  autovacuum_vac_cost_limit : VacuumCostLimit);
+								  autovacuum_vac_cost_limit : vacuum_cost_limit);
 	double		vac_cost_delay = (autovacuum_vac_cost_delay >= 0 ?
-								  autovacuum_vac_cost_delay : VacuumCostDelay);
+								  autovacuum_vac_cost_delay : vacuum_cost_delay);
 	double		cost_total;
 	double		cost_avail;
 	dlist_iter	iter;
@@ -2312,8 +2320,6 @@ do_autovacuum(void)
 		autovac_table *tab;
 		bool		isshared;
 		bool		skipit;
-		double		stdVacuumCostDelay;
-		int			stdVacuumCostLimit;
 		dlist_iter	iter;
 
 		CHECK_FOR_INTERRUPTS();
@@ -2416,14 +2422,6 @@ do_autovacuum(void)
 			continue;
 		}
 
-		/*
-		 * Remember the prevailing values of the vacuum cost GUCs.  We have to
-		 * restore these at the bottom of the loop, else we'll compute wrong
-		 * values in the next iteration of autovac_balance_cost().
-		 */
-		stdVacuumCostDelay = VacuumCostDelay;
-		stdVacuumCostLimit = VacuumCostLimit;
-
 		/* Must hold AutovacuumLock while mucking with cost balance info */
 		LWLockAcquire(AutovacuumLock, LW_EXCLUSIVE);
 
@@ -2437,7 +2435,7 @@ do_autovacuum(void)
 		autovac_balance_cost();
 
 		/* set the active cost parameters from the result of that */
-		AutoVacuumUpdateDelay();
+		VacuumUpdateCosts();
 
 		/* done */
 		LWLockRelease(AutovacuumLock);
@@ -2534,10 +2532,6 @@ deleted:
 		MyWorkerInfo->wi_tableoid = InvalidOid;
 		MyWorkerInfo->wi_sharedrel = false;
 		LWLockRelease(AutovacuumScheduleLock);
-
-		/* restore vacuum cost GUCs for the next iteration */
-		VacuumCostDelay = stdVacuumCostDelay;
-		VacuumCostLimit = stdVacuumCostLimit;
 	}
 
 	/*
@@ -2820,14 +2814,14 @@ table_recheck_autovac(Oid relid, HTAB *table_toast_map,
 			? avopts->vacuum_cost_delay
 			: (autovacuum_vac_cost_delay >= 0)
 			? autovacuum_vac_cost_delay
-			: VacuumCostDelay;
+			: 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
-			: VacuumCostLimit;
+			: vacuum_cost_limit;
 
 		/* -1 in autovac setting means use log_autovacuum_min_duration */
 		log_min_duration = (avopts && avopts->log_min_duration >= 0)
diff --git a/src/backend/utils/init/globals.c b/src/backend/utils/init/globals.c
index 1b1d814254..8e5b065e8f 100644
--- a/src/backend/utils/init/globals.c
+++ b/src/backend/utils/init/globals.c
@@ -142,8 +142,6 @@ int			MaxBackends = 0;
 int			VacuumCostPageHit = 1;	/* GUC parameters for vacuum */
 int			VacuumCostPageMiss = 2;
 int			VacuumCostPageDirty = 20;
-int			VacuumCostLimit = 200;
-double		VacuumCostDelay = 0;
 
 int64		VacuumPageHit = 0;
 int64		VacuumPageMiss = 0;
diff --git a/src/backend/utils/misc/guc_tables.c b/src/backend/utils/misc/guc_tables.c
index 8062589efd..77db1a146c 100644
--- a/src/backend/utils/misc/guc_tables.c
+++ b/src/backend/utils/misc/guc_tables.c
@@ -2409,7 +2409,7 @@ struct config_int ConfigureNamesInt[] =
 			gettext_noop("Vacuum cost amount available before napping."),
 			NULL
 		},
-		&VacuumCostLimit,
+		&vacuum_cost_limit,
 		200, 1, 10000,
 		NULL, NULL, NULL
 	},
@@ -3701,7 +3701,7 @@ struct config_real ConfigureNamesReal[] =
 			NULL,
 			GUC_UNIT_MS
 		},
-		&VacuumCostDelay,
+		&vacuum_cost_delay,
 		0, 0, 100,
 		NULL, NULL, NULL
 	},
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index 7219c6ba9c..17cf58255f 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -300,6 +300,8 @@ extern PGDLLIMPORT int vacuum_multixact_freeze_min_age;
 extern PGDLLIMPORT int vacuum_multixact_freeze_table_age;
 extern PGDLLIMPORT int vacuum_failsafe_age;
 extern PGDLLIMPORT int vacuum_multixact_failsafe_age;
+extern PGDLLIMPORT double vacuum_cost_delay;
+extern PGDLLIMPORT int vacuum_cost_limit;
 
 /* Variables for cost-based parallel vacuum */
 extern PGDLLIMPORT pg_atomic_uint32 *VacuumSharedCostBalance;
@@ -307,6 +309,8 @@ extern PGDLLIMPORT pg_atomic_uint32 *VacuumActiveNWorkers;
 extern PGDLLIMPORT int VacuumCostBalanceLocal;
 
 extern PGDLLIMPORT bool VacuumFailsafeActive;
+extern PGDLLIMPORT int	VacuumCostLimit;
+extern PGDLLIMPORT double VacuumCostDelay;
 
 /* in commands/vacuum.c */
 extern void ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel);
@@ -346,6 +350,9 @@ extern IndexBulkDeleteResult *vac_cleanup_one_index(IndexVacuumInfo *ivinfo,
 													IndexBulkDeleteResult *istat);
 extern Size vac_max_items_to_alloc_size(int max_items);
 
+/* In postmaster/autovacuum.c */
+extern void VacuumUpdateCosts(void);
+
 /* in commands/vacuumparallel.c */
 extern ParallelVacuumState *parallel_vacuum_init(Relation rel, Relation *indrels,
 												 int nindexes, int nrequested_workers,
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 06a86f9ac1..66db1b2c69 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -266,8 +266,6 @@ extern PGDLLIMPORT int max_parallel_maintenance_workers;
 extern PGDLLIMPORT int VacuumCostPageHit;
 extern PGDLLIMPORT int VacuumCostPageMiss;
 extern PGDLLIMPORT int VacuumCostPageDirty;
-extern PGDLLIMPORT int VacuumCostLimit;
-extern PGDLLIMPORT double VacuumCostDelay;
 
 extern PGDLLIMPORT int64 VacuumPageHit;
 extern PGDLLIMPORT int64 VacuumPageMiss;
diff --git a/src/include/postmaster/autovacuum.h b/src/include/postmaster/autovacuum.h
index c140371b51..65afd1ea1e 100644
--- a/src/include/postmaster/autovacuum.h
+++ b/src/include/postmaster/autovacuum.h
@@ -63,9 +63,6 @@ extern int	StartAutoVacWorker(void);
 /* called from postmaster when a worker could not be forked */
 extern void AutoVacWorkerFailed(void);
 
-/* autovacuum cost-delay balancer */
-extern void AutoVacuumUpdateDelay(void);
-
 #ifdef EXEC_BACKEND
 extern void AutoVacLauncherMain(int argc, char *argv[]) pg_attribute_noreturn();
 extern void AutoVacWorkerMain(int argc, char *argv[]) pg_attribute_noreturn();
-- 
2.37.2

Reply via email to