v6-0002-Trigger-more-frequent-autovacuums-with-relallfroz.patch

From 6048afbedf1590c3669c9f952fa70b244839c987 Mon Sep 17 00:00:00 2001
From: Melanie Plageman <melanieplageman@gmail.com>
Date: Thu, 16 Jan 2025 16:31:55 -0500
Subject: [PATCH v6 2/2] Trigger more frequent autovacuums with relallfrozen

Calculate the insert threshold for triggering an autovacuum of a
relation based on the number of unfrozen pages. By only considering the
"active" (unfrozen) portion of the table when calculating how many
tuples to add to the insert threshold, we can trigger more frequent
vacuums of insert-heavy tables and increase the chances of vacuuming
those pages when they still reside in shared buffers.

Reviewed-by: Greg Sabino Mullane
---
 doc/src/sgml/config.sgml                      | 16 +++++-----
 src/backend/postmaster/autovacuum.c           | 32 +++++++++++++++++--
 src/backend/utils/misc/postgresql.conf.sample |  4 +--
 3 files changed, 39 insertions(+), 13 deletions(-)

diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index 38244409e3c..8cef54bf183 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -8652,14 +8652,14 @@ 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 active (unfrozen) table size to add to
+        <varname>autovacuum_vacuum_insert_threshold</varname>
+        when deciding whether to trigger a <command>VACUUM</command>.
+        The default is 0.2 (20% of active 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.
         </para>
        </listitem>
       </varlistentry>
diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index 09ec9bb6990..250de2bb8ae 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -2932,7 +2932,6 @@ 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,
@@ -3046,7 +3045,12 @@ 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;
+		int32		relallvisible = classForm->relallvisible;
+
 		vactuples = tabentry->dead_tuples;
 		instuples = tabentry->ins_since_vacuum;
 		anltuples = tabentry->mod_since_analyze;
@@ -3055,11 +3059,33 @@ relation_needs_vacanalyze(Oid relid,
 		if (reltuples < 0)
 			reltuples = 0;
 
+		/*
+		 * If the table has been vacuumed and we have reliable data for
+		 * relallfrozen and relallvisible, 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 relallfrozen is -1, that means relallvisible was updated
+		 * manually and we can't rely on relallfrozen.
+		 */
+		if (relpages > 0 && reltuples > 0 && relallfrozen > -1)
+		{
+			if (relallvisible > relpages)
+				relallvisible = relpages;
+
+			if (relallfrozen > relallvisible)
+				relallfrozen = relallvisible;
+
+			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;
 
 		/*
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index c40b7a3121e..543e365adb6 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -667,8 +667,8 @@ 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 inserts over active
+						# 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
-- 
2.34.1