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 
Reported-by: Craig Ringer 
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 0392f37e198370b0b7bb732f96d990d09ccbe52c..6499162f3772b2a842302d64128e2afc9fc6103c 100644 (file)
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -1257,6 +1257,12 @@ 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.  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",
@@ -1288,6 +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;
@@ -1307,6 +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(),
@@ -1321,6 +1329,7 @@ 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",