Drop slot's LWLock before returning from SaveSlotToPath()
authorPeter Eisentraut <peter@eisentraut.org>
Thu, 26 Mar 2020 10:51:39 +0000 (11:51 +0100)
committerPeter Eisentraut <peter@eisentraut.org>
Thu, 26 Mar 2020 12:29:20 +0000 (13:29 +0100)
commit49bf81536e242f079bfbce6e8f95f53f18207dd5
tree04134155d85d1ee8f85faa22ad23d09292a38c5f
parent958aa438aaa473d580f60154786ffd716a28faf2
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>
Discussion: https://www.postgresql.org/message-id/flat/56a138c5-de61-f553-7e8f-6789296de785%402ndquadrant.com
src/backend/replication/slot.c