From 9c2013d53cc5c857ef8aca3df044613e66215aee Mon Sep 17 00:00:00 2001
From: Nathan Bossart <bossartn@amazon.com>
Date: Sun, 5 Dec 2021 22:02:40 -0800
Subject: [PATCH v5 5/8] Move removal of old serialized snapshots to custodian.

This was only done during checkpoints because it was a convenient
place to put it.  However, if there are many snapshots to remove,
it can significantly extend checkpoint time.  To avoid this, move
this work to the newly-introduced custodian process.
---
 src/backend/access/transam/xlog.c           |  2 --
 src/backend/postmaster/custodian.c          | 11 +++++++++++
 src/backend/replication/logical/snapbuild.c | 13 +++++++------
 src/include/replication/snapbuild.h         |  2 +-
 4 files changed, 19 insertions(+), 9 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index ce78ac413e..c4a80ea82a 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -79,7 +79,6 @@
 #include "replication/logical.h"
 #include "replication/origin.h"
 #include "replication/slot.h"
-#include "replication/snapbuild.h"
 #include "replication/walreceiver.h"
 #include "replication/walsender.h"
 #include "storage/bufmgr.h"
@@ -6807,7 +6806,6 @@ CheckPointGuts(XLogRecPtr checkPointRedo, int flags)
 {
 	CheckPointRelationMap();
 	CheckPointReplicationSlots();
-	CheckPointSnapBuild();
 	CheckPointLogicalRewriteHeap();
 	CheckPointReplicationOrigin();
 
diff --git a/src/backend/postmaster/custodian.c b/src/backend/postmaster/custodian.c
index 5bad0af474..8591c5db9b 100644
--- a/src/backend/postmaster/custodian.c
+++ b/src/backend/postmaster/custodian.c
@@ -40,6 +40,7 @@
 #include "pgstat.h"
 #include "postmaster/custodian.h"
 #include "postmaster/interrupt.h"
+#include "replication/snapbuild.h"
 #include "storage/bufmgr.h"
 #include "storage/condition_variable.h"
 #include "storage/fd.h"
@@ -208,6 +209,16 @@ CustodianMain(void)
 		 */
 		RemovePgTempFiles(false, false);
 
+		/*
+		 * Remove serialized snapshots that are no longer required by any
+		 * logical replication slot.
+		 *
+		 * It is not important for these to be removed in single-user mode, so
+		 * we don't need any extra handling outside of the custodian process for
+		 * this.
+		 */
+		RemoveOldSerializedSnapshots();
+
 		/* Calculate how long to sleep */
 		end_time = (pg_time_t) time(NULL);
 		elapsed_secs = end_time - start_time;
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 83fca8a77d..466a6478f3 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include "access/xact.h"
 #include "miscadmin.h"
 #include "pgstat.h"
+#include "postmaster/interrupt.h"
 #include "replication/logical.h"
 #include "replication/reorderbuffer.h"
 #include "replication/snapbuild.h"
@@ -1912,14 +1913,13 @@ snapshot_not_interesting:
 
 /*
  * Remove all serialized snapshots that are not required anymore because no
- * slot can need them. This doesn't actually have to run during a checkpoint,
- * but it's a convenient point to schedule this.
+ * slot can need them.
  *
- * NB: We run this during checkpoints even if logical decoding is disabled so
- * we cleanup old slots at some point after it got disabled.
+ * NB: We run this even if logical decoding is disabled so we cleanup old slots
+ * at some point after it got disabled.
  */
 void
-CheckPointSnapBuild(void)
+RemoveOldSerializedSnapshots(void)
 {
 	XLogRecPtr	cutoff;
 	XLogRecPtr	redo;
@@ -1942,7 +1942,8 @@ CheckPointSnapBuild(void)
 		cutoff = redo;
 
 	snap_dir = AllocateDir("pg_logical/snapshots");
-	while ((snap_de = ReadDir(snap_dir, "pg_logical/snapshots")) != NULL)
+	while (!ShutdownRequestPending &&
+		   (snap_de = ReadDir(snap_dir, "pg_logical/snapshots")) != NULL)
 	{
 		uint32		hi;
 		uint32		lo;
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index d179251aad..55a2beb434 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -57,7 +57,7 @@ struct ReorderBuffer;
 struct xl_heap_new_cid;
 struct xl_running_xacts;
 
-extern void CheckPointSnapBuild(void);
+extern void RemoveOldSerializedSnapshots(void);
 
 extern SnapBuild *AllocateSnapshotBuilder(struct ReorderBuffer *cache,
 										  TransactionId xmin_horizon, XLogRecPtr start_lsn,
-- 
2.25.1