From 6e2ce37341e5d600d8fd5648b39eec0dbdbe45ad Mon Sep 17 00:00:00 2001 From: Kotresh HR Date: Mon, 13 Nov 2017 05:27:50 -0500 Subject: geo-rep: Fix data sync issue during hardlink, rename Problem: The data is not getting synced if master witnessed IO as below. 1. echo "test_data" > f1 2. ln f1 f2 3. mv f2 f3 4. unlink f1 On master, 'f3' exists with data "test_data" but on slave, only f3 exists with zero byte file without backend gfid link. Cause: On master, since 'f2' no longer exists, the hardlink is skipped during processing. Later, on trying to sync rename, since source ('f2') doesn't exist, dst ('f3') is created with same gfid. But in this use case, it succeeds but backend gfid would not have linked as 'f1' exists with the same gfid. So, rsync would fail with ENOENT as backend gfid is not linked with 'f3' and 'f1' is unlinked. Fix: On processing rename, if src doesn't exist on slave, don't blindly create dst with same gfid. The gfid needs to be checked, if it exists, hardlink needs to be created instead of mknod. Thanks Aravinda for helping in RCA :) Change-Id: I5af4f99798ed1bcb297598a4bc796b701d1e0130 Signed-off-by: Kotresh HR BUG: 1512483 Reporter: dimitri.ars@gmail.com --- geo-replication/syncdaemon/resource.py | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'geo-replication') diff --git a/geo-replication/syncdaemon/resource.py b/geo-replication/syncdaemon/resource.py index a9810ae325b..c617c7b312e 100644 --- a/geo-replication/syncdaemon/resource.py +++ b/geo-replication/syncdaemon/resource.py @@ -688,8 +688,17 @@ class Server(object): elif not matching_disk_gfid(gfid, en): collect_failure(e, EEXIST, True) else: - (pg, bname) = entry2pb(en) - blob = entry_pack_reg_stat(gfid, bname, e['stat']) + slink = os.path.join(pfx, gfid) + st = lstat(slink) + # don't create multiple entries with same gfid + if isinstance(st, int): + (pg, bname) = entry2pb(en) + blob = entry_pack_reg_stat(gfid, bname, + e['stat']) + else: + cmd_ret = errno_wrap(os.link, [slink, en], + [ENOENT, EEXIST], [ESTALE]) + collect_failure(e, cmd_ret) else: st1 = lstat(en) if isinstance(st1, int): -- cgit