[CF 5320] v12 - Trigger more frequent autovacuums for insert-heavy tables

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

https://commitfest.postgresql.org/patch/5320

The branch will be overwritten each time a new patch version is posted to
the thread, and also periodically to check for bitrot caused by changes
on the master branch.

Patch(es): https://www.postgresql.org/message-id/CAAKRu_ZeL689jPWgKGvLHB-vum81P_T=_eyR4sGozygChARaSA@mail.gmail.com
Author(s): Melanie Plageman

Author: Commitfest Bot

doc/src/sgml/catalogs.sgml

@@ -2072,9 +2072,10 @@ SCRAM-SHA-256$<replaceable>&lt;iteration count&gt;</replaceable>:<replaceable>&l
       </para>
       <para>
        Number of pages that are marked all-frozen in the table's visibility
-       map.  This is only an estimate and can be used along with
-       <structfield>relallvisible</structfield> for scheduling vacuums and
-       tuning <link linkend="runtime-config-vacuum-freezing">vacuum's freezing
+       map.  This is only an estimate used for triggering autovacuums. It can
+       also be used along with <structfield>relallvisible</structfield> for
+       scheduling vacuums and tuning <link
+       linkend="runtime-config-vacuum-freezing">vacuum's freezing
        behavior</link>.
 
        It is updated by

doc/src/sgml/config.sgml

@@ -8773,14 +8773,13 @@ COPY postgres_log FROM '/full/path/to/logfile.csv' WITH csv;
        </term>
        <listitem>
         <para>
-         Specifies a fraction of the table size to add to
-         <varname>autovacuum_vacuum_insert_threshold</varname>
-         when deciding whether to trigger a <command>VACUUM</command>.
-         The default is <literal>0.2</literal> (20% of table size).
-         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 table storage parameters.
+         Specifies a fraction of the unfrozen pages in the table to add to
+         <varname>autovacuum_vacuum_insert_threshold</varname> when deciding
+         whether to trigger a <command>VACUUM</command>. The default is
+         <literal>0.2</literal> (20% of unfrozen pages in table). 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 table storage parameters.
         </para>
        </listitem>
       </varlistentry>

src/backend/postmaster/autovacuum.c

@@ -2938,7 +2938,6 @@ relation_needs_vacanalyze(Oid relid,
 {
 	bool		force_vacuum;
 	bool		av_enabled;
-	float4		reltuples;		/* pg_class.reltuples */
 
 	/* constants from reloptions or GUC variables */
 	int			vac_base_thresh,
@@ -3052,7 +3051,11 @@ relation_needs_vacanalyze(Oid relid,
 	 */
 	if (PointerIsValid(tabentry) && AutoVacuumingActive())
 	{
-		reltuples = classForm->reltuples;
+		float4		pcnt_unfrozen = 1;
+		float4		reltuples = classForm->reltuples;
+		int32		relpages = classForm->relpages;
+		int32		relallfrozen = classForm->relallfrozen;
+
 		vactuples = tabentry->dead_tuples;
 		instuples = tabentry->ins_since_vacuum;
 		anltuples = tabentry->mod_since_analyze;
@@ -3061,11 +3064,29 @@ relation_needs_vacanalyze(Oid relid,
 		if (reltuples < 0)
 			reltuples = 0;
 
+		/*
+		 * If we have data for relallfrozen, calculate the unfrozen percentage
+		 * of the table to modify insert scale factor. This helps us decide
+		 * whether or not to vacuum an insert-heavy table based on the number
+		 * of inserts to the "active" part of the table.
+		 */
+		if (relpages > 0 && relallfrozen > 0)
+		{
+			/*
+			 * It could be the stats were updated manually and relallfrozen >
+			 * relpages. Clamp relallfrozen to relpages to avoid nonsensical
+			 * calculations.
+			 */
+			relallfrozen = Min(relallfrozen, relpages);
+			pcnt_unfrozen = 1 - ((float4) relallfrozen / relpages);
+		}
+
 		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;
+		vacinsthresh = (float4) vac_ins_base_thresh +
+			vac_ins_scale_factor * reltuples * pcnt_unfrozen;
 		anlthresh = (float4) anl_base_thresh + anl_scale_factor * reltuples;
 
 		/*

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

@@ -675,8 +675,8 @@ autovacuum_worker_slots = 16	# autovacuum worker slots to allocate
 #autovacuum_analyze_threshold = 50	# min number of row updates before
 					# analyze
 #autovacuum_vacuum_scale_factor = 0.2	# fraction of table size before vacuum
-#autovacuum_vacuum_insert_scale_factor = 0.2	# fraction of inserts over table
-						# size before insert vacuum
+#autovacuum_vacuum_insert_scale_factor = 0.2	# fraction of unfrozen pages
+            # inserted to 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