From e6b00d5df4954a00bd47cfc64ba02b2c1888937b Mon Sep 17 00:00:00 2001
From: Nathan Bossart <bossartn@amazon.com>
Date: Sun, 5 Dec 2021 22:02:40 -0800
Subject: [PATCH v8 5/6] 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           | 8 ++++++--
 src/backend/postmaster/custodian.c          | 2 ++
 src/backend/replication/logical/snapbuild.c | 9 ++++-----
 src/include/postmaster/custodian.h          | 1 +
 src/include/replication/snapbuild.h         | 2 +-
 5 files changed, 14 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 9cedd6876f..72645f1fe6 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -76,12 +76,12 @@
 #include "port/atomics.h"
 #include "port/pg_iovec.h"
 #include "postmaster/bgwriter.h"
+#include "postmaster/custodian.h"
 #include "postmaster/startup.h"
 #include "postmaster/walwriter.h"
 #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"
@@ -6846,10 +6846,14 @@ CheckPointGuts(XLogRecPtr checkPointRedo, int flags)
 {
 	CheckPointRelationMap();
 	CheckPointReplicationSlots();
-	CheckPointSnapBuild();
 	CheckPointLogicalRewriteHeap();
 	CheckPointReplicationOrigin();
 
+	/* tasks offloaded to custodian */
+	RequestCustodian(CUSTODIAN_REMOVE_SERIALIZED_SNAPSHOTS,
+					 !IsUnderPostmaster,
+					 (Datum) 0);
+
 	/* Write out all dirty data in SLRUs and the main buffer pool */
 	TRACE_POSTGRESQL_BUFFER_CHECKPOINT_START(flags);
 	CheckpointStats.ckpt_write_t = GetCurrentTimestamp();
diff --git a/src/backend/postmaster/custodian.c b/src/backend/postmaster/custodian.c
index fe1f48844e..855a756ca0 100644
--- a/src/backend/postmaster/custodian.c
+++ b/src/backend/postmaster/custodian.c
@@ -25,6 +25,7 @@
 #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"
@@ -71,6 +72,7 @@ struct cust_task_funcs_entry
  */
 static const struct cust_task_funcs_entry cust_task_functions[] = {
 	{CUSTODIAN_REMOVE_TEMP_FILES, RemovePgTempFiles, NULL},
+	{CUSTODIAN_REMOVE_SERIALIZED_SNAPSHOTS, RemoveOldSerializedSnapshots, NULL},
 	{INVALID_CUSTODIAN_TASK, NULL, NULL}	/* must be last */
 };
 
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 1ff2c12240..abafdb52b2 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -2014,14 +2014,13 @@ SnapBuildRestoreContents(int fd, char *dest, Size size, const char *path)
 
 /*
  * 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;
diff --git a/src/include/postmaster/custodian.h b/src/include/postmaster/custodian.h
index 80890ceadd..37334941cc 100644
--- a/src/include/postmaster/custodian.h
+++ b/src/include/postmaster/custodian.h
@@ -19,6 +19,7 @@
 typedef enum CustodianTask
 {
 	CUSTODIAN_REMOVE_TEMP_FILES,
+	CUSTODIAN_REMOVE_SERIALIZED_SNAPSHOTS,
 
 	NUM_CUSTODIAN_TASKS,			/* new tasks go above */
 	INVALID_CUSTODIAN_TASK
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index e6adea24f2..e1de013ece 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