From b25bf64f3a3520a96ad557daa4903c0ceba96d72 Mon Sep 17 00:00:00 2001 From: Kotresh HR Date: Tue, 4 Jul 2017 08:46:06 -0400 Subject: geo-rep: Fix entry failure because parent dir doesn't exist In a distributed volume on master, it can so happen that the RMDIR followed by MKDIR is recorded in changelog on a particular subvolume with same gfid and pargfid/bname but not on all subvolumes as below. E 61c67a2e-07f2-45a9-95cf-d8f16a5e9c36 RMDIR \ 9cc51be8-91c3-4ef4-8ae3-17596fcfed40%2Ffedora2 E 61c67a2e-07f2-45a9-95cf-d8f16a5e9c36 MKDIR 16877 0 0 \ 9cc51be8-91c3-4ef4-8ae3-17596fcfed40%2Ffedora2 While processing this changelog, geo-rep thinks RMDIR is successful and does recursive rmdir on slave. But in the master the directory still exists. This could lead to data discrepancy between master and slave. Cause: RMDIR-MKDIR pair gets recorded so in changelog when the directory removal is successful on cached subvolume and failed in one of hashed subvol for some reason (may be down). In this case, the directory is re-created on cached subvol which gets recorded as MKDIR again in changelog. Solution: So while processing RMDIR geo-replication should stat on master with gfid and should not delete it if it's present. Change-Id: If5da1d6462eb4d9ebe2e88b3a70cc454411a133e BUG: 1467718 Signed-off-by: Kotresh HR Reviewed-on: https://review.gluster.org/17695 Smoke: Gluster Build System CentOS-regression: Gluster Build System Reviewed-by: Aravinda VK --- geo-replication/syncdaemon/master.py | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'geo-replication') diff --git a/geo-replication/syncdaemon/master.py b/geo-replication/syncdaemon/master.py index 17ec550aafa..9bd6721eab5 100644 --- a/geo-replication/syncdaemon/master.py +++ b/geo-replication/syncdaemon/master.py @@ -870,6 +870,11 @@ class GMasterChangelogMixin(GMasterCommon): # file got unlinked, May be historical Changelog datas.remove(pt) + if ty in ['RMDIR'] and not isinstance(st, int): + logging.info(lf('Ignoring rmdir. Directory present in ' + 'master', gfid=gfid, pgfid_bname=en)) + continue + if not boolify(gconf.ignore_deletes): if not ignore_entry_ops: entries.append(edct(ty, gfid=gfid, entry=en)) -- cgit