Introduce autovacuum_vacuum_max_threshold.

One way autovacuum chooses tables to vacuum is by comparing the
number of updated or deleted tuples with a value calculated using
autovacuum_vacuum_threshold and autovacuum_vacuum_scale_factor.
The threshold specifies the base value for comparison, and the
scale factor specifies the fraction of the table size to add to it.
This strategy ensures that smaller tables are vacuumed after fewer
updates/deletes than larger tables, which is reasonable in many
cases but can result in infrequent vacuums on very large tables.
This is undesirable for a couple of reasons, such as very large
tables incurring a huge amount of bloat between vacuums.

This new parameter provides a way to set a limit on the value
calculated with autovacuum_vacuum_threshold and
autovacuum_vacuum_scale_factor so that very large tables are
vacuumed more frequently.  By default, it is set to 100,000,000
tuples, but it can be disabled by setting it to -1.  It can also be
adjusted for individual tables by changing storage parameters.

Author: Nathan Bossart <nathandbossart@gmail.com>
Co-authored-by: Frédéric Yhuel <frederic.yhuel@dalibo.com>
Reviewed-by: Melanie Plageman <melanieplageman@gmail.com>
Reviewed-by: Robert Haas <robertmhaas@gmail.com>
Reviewed-by: Laurenz Albe <laurenz.albe@cybertec.at>
Reviewed-by: Michael Banck <mbanck@gmx.net>
Reviewed-by: Joe Conway <mail@joeconway.com>
Reviewed-by: Sami Imseih <samimseih@gmail.com>
Reviewed-by: David Rowley <dgrowleyml@gmail.com>
Reviewed-by: wenhui qiu <qiuwenhuifx@gmail.com>
Reviewed-by: Vinícius Abrahão <vinnix.bsd@gmail.com>
Reviewed-by: Robert Treat <rob@xzilla.net>
Reviewed-by: Alena Rybakina <a.rybakina@postgrespro.ru>
Discussion: https://postgr.es/m/956435f8-3b2f-47a6-8756-8c54ded61802%40dalibo.com

Author: nathan-bossart

doc/src/sgml/config.sgml

@@ -8685,6 +8685,30 @@ COPY postgres_log FROM '/full/path/to/logfile.csv' WITH csv;
        </listitem>
       </varlistentry>
 
+      <varlistentry id="guc-autovacuum-vacuum-max-threshold" xreflabel="autovacuum_vacuum_max_threshold">
+       <term><varname>autovacuum_vacuum_max_threshold</varname> (<type>integer</type>)
+       <indexterm>
+        <primary><varname>autovacuum_vacuum_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 limit 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-freeze-max-age" xreflabel="autovacuum_freeze_max_age">
        <term><varname>autovacuum_freeze_max_age</varname> (<type>integer</type>)
        <indexterm>

doc/src/sgml/maintenance.sgml

@@ -895,9 +895,11 @@ HINT:  Execute a database-wide VACUUM in that database.
     <command>VACUUM</command> exceeds the <quote>vacuum threshold</quote>, the
     table is vacuumed.  The vacuum threshold is defined as:
 <programlisting>
-vacuum threshold = vacuum base threshold + vacuum scale factor * number of tuples
+vacuum threshold = Minimum(vacuum max threshold, vacuum base threshold + vacuum scale factor * number of tuples)
 </programlisting>
-    where the vacuum base threshold is
+    where the vacuum max threshold is
+    <xref linkend="guc-autovacuum-vacuum-max-threshold"/>,
+    the vacuum base threshold is
     <xref linkend="guc-autovacuum-vacuum-threshold"/>,
     the vacuum scale factor is
     <xref linkend="guc-autovacuum-vacuum-scale-factor"/>,

doc/src/sgml/ref/create_table.sgml

@@ -1712,6 +1712,21 @@ WITH ( MODULUS <replaceable class="parameter">numeric_literal</replaceable>, REM
     </listitem>
    </varlistentry>
 
+   <varlistentry id="reloption-autovacuum-vacuum-max-threshold" xreflabel="autovacuum_vacuum_max_threshold">
+    <term><literal>autovacuum_vacuum_max_threshold</literal>, <literal>toast.autovacuum_vacuum_max_threshold</literal> (<type>integer</type>)
+    <indexterm>
+     <primary><varname>autovacuum_vacuum_max_threshold</varname></primary>
+     <secondary>storage parameter</secondary>
+    </indexterm>
+    </term>
+   <listitem>
+    <para>
+     Per-table value for <xref linkend="guc-autovacuum-vacuum-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>

src/backend/access/common/reloptions.c

@@ -231,6 +231,15 @@ static relopt_int intRelOpts[] =
 		},
 		-1, 0, INT_MAX
 	},
+	{
+		{
+			"autovacuum_vacuum_max_threshold",
+			"Maximum number of tuple updates or deletes prior to vacuum",
+			RELOPT_KIND_HEAP | RELOPT_KIND_TOAST,
+			ShareUpdateExclusiveLock
+		},
+		-2, -1, 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_vacuum_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,

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_vac_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_thresh;
  *
  * 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 +2978,11 @@ relation_needs_vacanalyze(Oid relid,
 		? relopts->vacuum_threshold
 		: autovacuum_vac_thresh;
 
+	/* -1 is used to disable max threshold */
+	vac_max_thresh = (relopts && relopts->vacuum_max_threshold >= -1)
+		? relopts->vacuum_max_threshold
+		: autovacuum_vac_max_thresh;
+
 	vac_ins_scale_factor = (relopts && relopts->vacuum_ins_scale_factor >= 0)
 		? relopts->vacuum_ins_scale_factor
 		: autovacuum_vac_ins_scale;
@@ -3047,6 +3056,9 @@ 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;
 

src/backend/utils/misc/guc_tables.c

@@ -3426,6 +3426,15 @@ struct config_int ConfigureNamesInt[] =
 		50, 0, INT_MAX,
 		NULL, NULL, NULL
 	},
+	{
+		{"autovacuum_vacuum_max_threshold", PGC_SIGHUP, VACUUM_AUTOVACUUM,
+			gettext_noop("Maximum number of tuple updates or deletes prior to vacuum."),
+			NULL
+		},
+		&autovacuum_vac_max_thresh,
+		100000000, -1, INT_MAX,
+		NULL, NULL, NULL
+	},
 	{
 		{"autovacuum_vacuum_insert_threshold", PGC_SIGHUP, VACUUM_AUTOVACUUM,
 			gettext_noop("Minimum number of tuple inserts prior to vacuum, or -1 to disable insert vacuums."),

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

@@ -670,6 +670,9 @@ autovacuum_worker_slots = 16	# autovacuum worker slots to allocate
 #autovacuum_vacuum_insert_scale_factor = 0.2	# fraction of inserts over table
 						# size before insert vacuum
 #autovacuum_analyze_scale_factor = 0.1	# fraction of table size before analyze
+#autovacuum_vacuum_max_threshold = 100000000    # max number of row updates
+						# before vacuum; -1 disables max
+						# threshold
 #autovacuum_freeze_max_age = 200000000	# maximum XID age before forced vacuum
 					# (change requires restart)
 #autovacuum_multixact_freeze_max_age = 400000000	# maximum multixact age

src/bin/psql/tab-complete.in.c

@@ -1368,6 +1368,7 @@ static const char *const table_storage_parameters[] = {
 	"autovacuum_vacuum_cost_limit",
 	"autovacuum_vacuum_insert_scale_factor",
 	"autovacuum_vacuum_insert_threshold",
+	"autovacuum_vacuum_max_threshold",
 	"autovacuum_vacuum_scale_factor",
 	"autovacuum_vacuum_threshold",
 	"fillfactor",
@@ -1384,6 +1385,7 @@ static const char *const table_storage_parameters[] = {
 	"toast.autovacuum_vacuum_cost_limit",
 	"toast.autovacuum_vacuum_insert_scale_factor",
 	"toast.autovacuum_vacuum_insert_threshold",
+	"toast.autovacuum_vacuum_max_threshold",
 	"toast.autovacuum_vacuum_scale_factor",
 	"toast.autovacuum_vacuum_threshold",
 	"toast.log_autovacuum_min_duration",

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_vac_max_thresh;
 extern PGDLLIMPORT double autovacuum_vac_scale;
 extern PGDLLIMPORT int autovacuum_vac_ins_thresh;
 extern PGDLLIMPORT double autovacuum_vac_ins_scale;

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;