From bad41764a443605bef9bb3d1c3614e1b3770005d Mon Sep 17 00:00:00 2001 From: Michael Paquier Date: Thu, 29 Nov 2018 09:12:40 +0900 Subject: [PATCH] Fix handling of synchronous replication for stopping WAL senders This fixes an oversight from c6c3334 which forgot that if a subset of WAL senders are stopping and in a sync state, other WAL senders could still be waiting for a WAL position to be synced while committing a transaction. However the subset of stopping senders would not release waiters, potentially breaking synchronous replication guarantees. This commit makes sure that even WAL senders stopping are able to release waiters and are tracked properly. On 9.4, this can also trigger an assertion failure when setting for example max_wal_senders to 1 where a WAL sender is not able to find itself as in synchronous state when the instance stops. Reported-by: Paul Guo Author: Paul Guo, Michael Paquier Discussion: https://postgr.es/m/CAEET0ZEv8VFqT3C-cQm6byOB4r4VYWcef1J21dOX-gcVhCSpmA@mail.gmail.com Backpatch-through: 9.4 --- src/backend/replication/syncrep.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/src/backend/replication/syncrep.c b/src/backend/replication/syncrep.c index 75d2681719..61256db467 100644 --- a/src/backend/replication/syncrep.c +++ b/src/backend/replication/syncrep.c @@ -423,10 +423,12 @@ SyncRepReleaseWaiters(void) * If this WALSender is serving a standby that is not on the list of * potential sync standbys then we have nothing to do. If we are still * starting up, still running base backup or the current flush position is - * still invalid, then leave quickly also. + * still invalid, then leave quickly also. Streaming or stopping WAL + * senders are allowed to release waiters. */ if (MyWalSnd->sync_standby_priority == 0 || - MyWalSnd->state < WALSNDSTATE_STREAMING || + (MyWalSnd->state != WALSNDSTATE_STREAMING && + MyWalSnd->state != WALSNDSTATE_STOPPING) || XLogRecPtrIsInvalid(MyWalSnd->flush)) { announce_next_takeover = true; @@ -728,8 +730,9 @@ SyncRepGetSyncStandbysQuorum(bool *am_sync) if (pid == 0) continue; - /* Must be streaming */ - if (state != WALSNDSTATE_STREAMING) + /* Must be streaming or stopping */ + if (state != WALSNDSTATE_STREAMING && + state != WALSNDSTATE_STOPPING) continue; /* Must be synchronous */ @@ -807,8 +810,9 @@ SyncRepGetSyncStandbysPriority(bool *am_sync) if (pid == 0) continue; - /* Must be streaming */ - if (state != WALSNDSTATE_STREAMING) + /* Must be streaming or stopping */ + if (state != WALSNDSTATE_STREAMING && + state != WALSNDSTATE_STOPPING) continue; /* Must be synchronous */