Date: Tue, 7 Jan 2025 16:57:41 -0600
From: Nathan Bossart <nathandbossart@gmail.com>
To: wenhui qiu <qiuwenhuifx@gmail.com>
Cc: =?iso-8859-1?Q?Fr=E9d=E9ric?= Yhuel <frederic.yhuel@dalibo.com>,
	Robert Haas <robertmhaas@gmail.com>,
	"Imseih (AWS), Sami" <simseih@amazon.com>,
	David Rowley <dgrowleyml@gmail.com>,
	Joe Conway <mail@joeconway.com>, Michael Banck <mbanck@gmx.net>,
	Laurenz Albe <laurenz.albe@cybertec.at>,
	Melanie Plageman <melanieplageman@gmail.com>,
	PostgreSQL Hackers <pgsql-hackers@lists.postgresql.org>
Subject: Re: New GUC autovacuum_max_threshold ?
Message-ID: <Z32xZZwOi5pXZjYU@nathan>
References: <ZnD509Q1jROYKhz_@nathan>
 <97f04e09-a08a-417c-b65d-5d5cbdd0b845@dalibo.com>
 <ZrPprRLBzi1YUBLn@nathan>
 <6a2ac9b7-6535-4bb1-8274-0647f7c31c82@dalibo.com>
 <CAGjGUALGtQ8MoshY6tEUPiAOjWNefBzq61gZ_5Dx-Uai1cC39Q@mail.gmail.com>
 <Zy5N-M2jPIYzPdku@nathan>
 <CAGjGUALGwH9LJUxe+ZbjnW_Cg4B4qyFrXFv+oWYCYnLcwggBJQ@mail.gmail.com>
 <Zy-G7u43r1siVkQ6@nathan>
 <2ca7f9c7-5da9-46cb-9072-39b71bfab948@dalibo.com>
 <CAGjGUAKSvvQA583hk-62HyBRhPvowNbhv5+QiRt+znWMA+5OLg@mail.gmail.com>
MIME-Version: 1.0
Content-Type: multipart/mixed; boundary="se9LvmAYPj/v8/s/"
Content-Disposition: inline
In-Reply-To: <CAGjGUAKSvvQA583hk-62HyBRhPvowNbhv5+QiRt+znWMA+5OLg@mail.gmail.com>
Archived-At: <https://www.postgresql.org/message-id/Z32xZZwOi5pXZjYU%40nathan>
Precedence: bulk


--se9LvmAYPj/v8/s/
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline

Here is a rebased patch for cfbot.  AFAICT we are still pretty far from
consensus on which approach to take, unfortunately.

-- 
nathan

--se9LvmAYPj/v8/s/
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0001-autovacuum_max_threshold.patch"

From df17b1f8b18300bc8426c06ab4e4d2d1c9169d85 Mon Sep 17 00:00:00 2001
From: Nathan Bossart <nathan@postgresql.org>
Date: Wed, 7 Aug 2024 16:22:37 -0500
Subject: [PATCH v3 1/1] autovacuum_max_threshold

---
 doc/src/sgml/config.sgml                      | 24 +++++++++++++++++++
 doc/src/sgml/ref/create_table.sgml            | 15 ++++++++++++
 src/backend/access/common/reloptions.c        | 11 +++++++++
 src/backend/postmaster/autovacuum.c           | 11 +++++++++
 src/backend/utils/misc/guc_tables.c           |  9 +++++++
 src/backend/utils/misc/postgresql.conf.sample |  2 ++
 src/bin/psql/tab-complete.in.c                |  2 ++
 src/include/postmaster/autovacuum.h           |  1 +
 src/include/utils/rel.h                       |  1 +
 9 files changed, 76 insertions(+)

diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index 8683f0bdf53..3c03bdd5790 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -8712,6 +8712,30 @@ COPY postgres_log FROM '/full/path/to/logfile.csv' WITH csv;
       </listitem>
      </varlistentry>
 
+     <varlistentry id="guc-autovacuum-max-threshold" xreflabel="autovacuum_max_threshold">
+      <term><varname>autovacuum_max_threshold</varname> (<type>integer</type>)
+      <indexterm>
+       <primary><varname>autovacuum_max_threshold</varname></primary>
+       <secondary>configuration parameter</secondary>
+      </indexterm>
+      </term>
+      <listitem>
+       <para>
+        Specifies the maximum number of updated or deleted tuples needed to
+        trigger a <command>VACUUM</command> in any one table, i.e., a cap on
+        the value calculated with
+        <varname>autovacuum_vacuum_threshold</varname> and
+        <varname>autovacuum_vacuum_scale_factor</varname>.  The default is
+        100,000,000 tuples.  If -1 is specified, autovacuum will not enforce a
+        maximum number of updated or deleted tuples that will trigger a
+        <command>VACUUM</command> operation.  This parameter can only be set in
+        the <filename>postgresql.conf</filename> file or on the server command
+        line; but the setting can be overridden for individual tables by
+        changing storage parameters.
+       </para>
+      </listitem>
+     </varlistentry>
+
      <varlistentry id="guc-autovacuum-vacuum-insert-threshold" xreflabel="autovacuum_vacuum_insert_threshold">
       <term><varname>autovacuum_vacuum_insert_threshold</varname> (<type>integer</type>)
       <indexterm>
diff --git a/doc/src/sgml/ref/create_table.sgml b/doc/src/sgml/ref/create_table.sgml
index 70fa929caa4..77cee4a2888 100644
--- a/doc/src/sgml/ref/create_table.sgml
+++ b/doc/src/sgml/ref/create_table.sgml
@@ -1682,6 +1682,21 @@ WITH ( MODULUS <replaceable class="parameter">numeric_literal</replaceable>, REM
     </listitem>
    </varlistentry>
 
+   <varlistentry id="reloption-autovacuum-max-threshold" xreflabel="autovacuum_max_threshold">
+    <term><literal>autovacuum_max_threshold</literal>, <literal>toast.autovacuum_max_threshold</literal> (<type>integer</type>)
+    <indexterm>
+     <primary><varname>autovacuum_max_threshold</varname></primary>
+     <secondary>storage parameter</secondary>
+    </indexterm>
+    </term>
+   <listitem>
+    <para>
+     Per-table value for <xref linkend="guc-autovacuum-max-threshold"/>
+     parameter.
+    </para>
+   </listitem>
+  </varlistentry>
+
    <varlistentry id="reloption-autovacuum-vacuum-scale-factor" xreflabel="autovacuum_vacuum_scale_factor">
     <term><literal>autovacuum_vacuum_scale_factor</literal>, <literal>toast.autovacuum_vacuum_scale_factor</literal> (<type>floating point</type>)
     <indexterm>
diff --git a/src/backend/access/common/reloptions.c b/src/backend/access/common/reloptions.c
index e587abd9990..c28c7517aeb 100644
--- a/src/backend/access/common/reloptions.c
+++ b/src/backend/access/common/reloptions.c
@@ -231,6 +231,15 @@ static relopt_int intRelOpts[] =
 		},
 		-1, 0, INT_MAX
 	},
+	{
+		{
+			"autovacuum_max_threshold",
+			"Maximum number of tuple updates or deletes prior to vacuum",
+			RELOPT_KIND_HEAP | RELOPT_KIND_TOAST,
+			ShareUpdateExclusiveLock
+		},
+		-1, 0, INT_MAX
+	},
 	{
 		{
 			"autovacuum_vacuum_insert_threshold",
@@ -1843,6 +1852,8 @@ default_reloptions(Datum reloptions, bool validate, relopt_kind kind)
 		offsetof(StdRdOptions, autovacuum) + offsetof(AutoVacOpts, enabled)},
 		{"autovacuum_vacuum_threshold", RELOPT_TYPE_INT,
 		offsetof(StdRdOptions, autovacuum) + offsetof(AutoVacOpts, vacuum_threshold)},
+		{"autovacuum_max_threshold", RELOPT_TYPE_INT,
+		offsetof(StdRdOptions, autovacuum) + offsetof(AutoVacOpts, vacuum_max_threshold)},
 		{"autovacuum_vacuum_insert_threshold", RELOPT_TYPE_INT,
 		offsetof(StdRdOptions, autovacuum) + offsetof(AutoVacOpts, vacuum_ins_threshold)},
 		{"autovacuum_analyze_threshold", RELOPT_TYPE_INT,
diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index 0ab921a169b..680b3dcae48 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -120,6 +120,7 @@ int			autovacuum_max_workers;
 int			autovacuum_work_mem = -1;
 int			autovacuum_naptime;
 int			autovacuum_vac_thresh;
+int			autovacuum_max_thresh;
 double		autovacuum_vac_scale;
 int			autovacuum_vac_ins_thresh;
 double		autovacuum_vac_ins_scale;
@@ -2895,6 +2896,8 @@ recheck_relation_needs_vacanalyze(Oid relid,
  * threshold.  This threshold is calculated as
  *
  * threshold = vac_base_thresh + vac_scale_factor * reltuples
+ * if (threshold > vac_max_thresh)
+ *     threshold = vac_max_thres;
  *
  * For analyze, the analysis done is that the number of tuples inserted,
  * deleted and updated since the last analyze exceeds a threshold calculated
@@ -2933,6 +2936,7 @@ relation_needs_vacanalyze(Oid relid,
 
 	/* constants from reloptions or GUC variables */
 	int			vac_base_thresh,
+				vac_max_thresh,
 				vac_ins_base_thresh,
 				anl_base_thresh;
 	float4		vac_scale_factor,
@@ -2974,6 +2978,10 @@ relation_needs_vacanalyze(Oid relid,
 		? relopts->vacuum_threshold
 		: autovacuum_vac_thresh;
 
+	vac_max_thresh = (relopts && relopts->vacuum_max_threshold >= 0)
+		? relopts->vacuum_max_threshold
+		: autovacuum_max_thresh;
+
 	vac_ins_scale_factor = (relopts && relopts->vacuum_ins_scale_factor >= 0)
 		? relopts->vacuum_ins_scale_factor
 		: autovacuum_vac_ins_scale;
@@ -3047,6 +3055,9 @@ relation_needs_vacanalyze(Oid relid,
 			reltuples = 0;
 
 		vacthresh = (float4) vac_base_thresh + vac_scale_factor * reltuples;
+		if (vac_max_thresh >= 0 && vacthresh > (float4) vac_max_thresh)
+			vacthresh = (float4) vac_max_thresh;
+
 		vacinsthresh = (float4) vac_ins_base_thresh + vac_ins_scale_factor * reltuples;
 		anlthresh = (float4) anl_base_thresh + anl_scale_factor * reltuples;
 
diff --git a/src/backend/utils/misc/guc_tables.c b/src/backend/utils/misc/guc_tables.c
index c9d8cd796a8..2a18ba80c87 100644
--- a/src/backend/utils/misc/guc_tables.c
+++ b/src/backend/utils/misc/guc_tables.c
@@ -3425,6 +3425,15 @@ struct config_int ConfigureNamesInt[] =
 		50, 0, INT_MAX,
 		NULL, NULL, NULL
 	},
+	{
+		{"autovacuum_max_threshold", PGC_SIGHUP, AUTOVACUUM,
+			gettext_noop("Maximum number of tuple updates or deletes prior to vacuum."),
+			NULL
+		},
+		&autovacuum_max_thresh,
+		100000000, -1, INT_MAX,
+		NULL, NULL, NULL
+	},
 	{
 		{"autovacuum_vacuum_insert_threshold", PGC_SIGHUP, AUTOVACUUM,
 			gettext_noop("Minimum number of tuple inserts prior to vacuum, or -1 to disable insert vacuums."),
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index b2bc43383db..d0e1c9b53c0 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -667,6 +667,8 @@ autovacuum_worker_slots = 16	# autovacuum worker slots to allocate
 #autovacuum_naptime = 1min		# time between autovacuum runs
 #autovacuum_vacuum_threshold = 50	# min number of row updates before
 					# vacuum
+#autovacuum_max_threshold = 100000000	# max number of row updates before
+					# vacuum
 #autovacuum_vacuum_insert_threshold = 1000	# min number of row inserts
 						# before vacuum; -1 disables insert
 						# vacuums
diff --git a/src/bin/psql/tab-complete.in.c b/src/bin/psql/tab-complete.in.c
index 81cbf10aa28..6ede5090cc0 100644
--- a/src/bin/psql/tab-complete.in.c
+++ b/src/bin/psql/tab-complete.in.c
@@ -1361,6 +1361,7 @@ static const char *const table_storage_parameters[] = {
 	"autovacuum_freeze_max_age",
 	"autovacuum_freeze_min_age",
 	"autovacuum_freeze_table_age",
+	"autovacuum_max_threshold",
 	"autovacuum_multixact_freeze_max_age",
 	"autovacuum_multixact_freeze_min_age",
 	"autovacuum_multixact_freeze_table_age",
@@ -1377,6 +1378,7 @@ static const char *const table_storage_parameters[] = {
 	"toast.autovacuum_freeze_max_age",
 	"toast.autovacuum_freeze_min_age",
 	"toast.autovacuum_freeze_table_age",
+	"toast.autovacuum_max_threshold",
 	"toast.autovacuum_multixact_freeze_max_age",
 	"toast.autovacuum_multixact_freeze_min_age",
 	"toast.autovacuum_multixact_freeze_table_age",
diff --git a/src/include/postmaster/autovacuum.h b/src/include/postmaster/autovacuum.h
index 54e01c81d68..b5c7b9b8abb 100644
--- a/src/include/postmaster/autovacuum.h
+++ b/src/include/postmaster/autovacuum.h
@@ -33,6 +33,7 @@ extern PGDLLIMPORT int autovacuum_max_workers;
 extern PGDLLIMPORT int autovacuum_work_mem;
 extern PGDLLIMPORT int autovacuum_naptime;
 extern PGDLLIMPORT int autovacuum_vac_thresh;
+extern PGDLLIMPORT int autovacuum_max_thresh;
 extern PGDLLIMPORT double autovacuum_vac_scale;
 extern PGDLLIMPORT int autovacuum_vac_ins_thresh;
 extern PGDLLIMPORT double autovacuum_vac_ins_scale;
diff --git a/src/include/utils/rel.h b/src/include/utils/rel.h
index 33d1e4a4e2e..48b95f211f3 100644
--- a/src/include/utils/rel.h
+++ b/src/include/utils/rel.h
@@ -309,6 +309,7 @@ typedef struct AutoVacOpts
 {
 	bool		enabled;
 	int			vacuum_threshold;
+	int			vacuum_max_threshold;
 	int			vacuum_ins_threshold;
 	int			analyze_threshold;
 	int			vacuum_cost_limit;
-- 
2.39.5 (Apple Git-154)


--se9LvmAYPj/v8/s/--