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 <[email protected]>
Reported-by: Craig Ringer <[email protected]>
Discussion: https://www.postgresql.org/message-id/flat/56a138c5-de61-f553-7e8f-6789296de785%402ndquadrant.com

diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index 9a6cde09bc31def45e24356e20c1e1a6f7f0af15..14fc04df09cb7369799c68f30a250d82e67fc456 100644 (file)
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -1010,6 +1010,12 @@ SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel)
                           S_IRUSR | S_IWUSR);
    if (fd < 0)
    {
+       /*
+        * If not an ERROR, then release the lock before returning.  In case
+        * of an ERROR, the error recovery path automatically releases the
+        * lock, but no harm in explicitly releasing even in that case.
+        */
+       LWLockRelease(slot->io_in_progress_lock);
        ereport(elevel,
                (errcode_for_file_access(),
                 errmsg("could not create file \"%s\": %m",
@@ -1039,6 +1045,7 @@ SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel)
        int         save_errno = errno;
 
        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;
@@ -1055,6 +1062,7 @@ SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel)
        int         save_errno = errno;
 
        CloseTransientFile(fd);
+       LWLockRelease(slot->io_in_progress_lock);
        errno = save_errno;
        ereport(elevel,
                (errcode_for_file_access(),
@@ -1068,6 +1076,7 @@ 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",