0001-Drop-slot-s-LWLock-before-returning-from-SaveSlotToP.patch

From b33a856c68e1c48c8663a760f79b2b3d3bf0088c Mon Sep 17 00:00:00 2001
From: Peter Eisentraut <peter@eisentraut.org>
Date: Wed, 18 Mar 2020 16:24:59 +0100
Subject: [PATCH] Drop slot's LWLock before returning from SaveSlotToPath()

When SaveSlotToPath() is called with elevel=LOG, the early exits didn't
release the slot's io_in_progress_lock.

This could result in a walsender being stuck on the lock forever.  A
possible way to get into this situation is if the offending code paths
are triggered in a low disk space situation.

Author: Pavan Deolasee <pavan.deolasee@2ndquadrant.com>
Reported-by: Craig Ringer <craig@2ndquadrant.com>
---
 src/backend/replication/slot.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index 1cec53d748..1bff2d6185 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -1256,6 +1256,13 @@ SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel)
 	fd = OpenTransientFile(tmppath, O_CREAT | O_EXCL | O_WRONLY | PG_BINARY);
 	if (fd < 0)
 	{
+		/*
+		 * If not an ERROR, then release the lock before returning the control
+		 * back to the caller. In case of an ERROR, the error recovery path
+		 * should automatically release the lock, but no harm in explicitly
+		 * releaseing even in that case.
+		 */
+		LWLockRelease(&slot->io_in_progress_lock);
 		ereport(elevel,
 				(errcode_for_file_access(),
 				 errmsg("could not create file \"%s\": %m",
@@ -1287,6 +1294,7 @@ SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel)
 
 		pgstat_report_wait_end();
 		CloseTransientFile(fd);
+		LWLockRelease(&slot->io_in_progress_lock);
 
 		/* if write didn't set errno, assume problem is no disk space */
 		errno = save_errno ? save_errno : ENOSPC;
@@ -1306,6 +1314,7 @@ SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel)
 
 		pgstat_report_wait_end();
 		CloseTransientFile(fd);
+		LWLockRelease(&slot->io_in_progress_lock);
 		errno = save_errno;
 		ereport(elevel,
 				(errcode_for_file_access(),
@@ -1317,6 +1326,7 @@ SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel)
 
 	if (CloseTransientFile(fd) != 0)
 	{
+		LWLockRelease(&slot->io_in_progress_lock);
 		ereport(elevel,
 				(errcode_for_file_access(),
 				 errmsg("could not close file \"%s\": %m",
@@ -1327,6 +1337,7 @@ SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel)
 	/* rename to permanent file, fsync file and directory */
 	if (rename(tmppath, path) != 0)
 	{
+		LWLockRelease(&slot->io_in_progress_lock);
 		ereport(elevel,
 				(errcode_for_file_access(),
 				 errmsg("could not rename file \"%s\" to \"%s\": %m",
-- 
2.25.0