diff options
| author | Ravishankar N <ravishankar@redhat.com> | 2018-01-28 13:50:47 +0530 |
|---|---|---|
| committer | jiffin tony Thottan <jthottan@redhat.com> | 2018-07-04 04:03:45 +0000 |
| commit | b715dfb39460d053db726c4150c5f209a1503bff (patch) | |
| tree | 159389165a2bead8e7fb242556fffb77620fabcb /xlators/cluster/afr/src/afr-self-heal-data.c | |
| parent | b11866a596bcd16a9fc37317929471e9a4b1d299 (diff) | |
afr: don't treat all cases all bricks being blamed as split-brain
Problem:
We currently don't have a roll-back/undoing of post-ops if quorum is not
met. Though the FOP is still unwound with failure, the xattrs remain on
the disk. Due to these partial post-ops and partial heals (healing only when
2 bricks are up), we can end up in split-brain purely from the afr
xattrs point of view i.e each brick is blamed by atleast one of the
others. These scenarios are hit when there is frequent
connect/disconnect of the client/shd to the bricks while I/O or heal
are in progress.
Fix:
Instead of undoing the post-op, pick a source based on the xattr values.
If 2 bricks blame one, the blamed one must be treated as sink.
If there is no majority, all are sources. Once we pick a source,
self-heal will then do the heal instead of erroring out due to
split-brain.
Change-Id: I3d0224b883eb0945785ade0e9697a1c828aec0ae
BUG: 1597123
Signed-off-by: Ravishankar N <ravishankar@redhat.com>
(cherry picked from commit 0e6e8216823c2d9dafb81aae0f6ee3497c23d140)
Diffstat (limited to 'xlators/cluster/afr/src/afr-self-heal-data.c')
| -rw-r--r-- | xlators/cluster/afr/src/afr-self-heal-data.c | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/xlators/cluster/afr/src/afr-self-heal-data.c b/xlators/cluster/afr/src/afr-self-heal-data.c index 8cf43f2807b..bcd0deccbd4 100644 --- a/xlators/cluster/afr/src/afr-self-heal-data.c +++ b/xlators/cluster/afr/src/afr-self-heal-data.c @@ -684,7 +684,7 @@ __afr_selfheal_data (call_frame_t *frame, xlator_t *this, fd_t *fd, ret = afr_selfheal_inodelk (frame, this, fd->inode, this->name, 0, 0, data_lock); { - if (ret < AFR_SH_MIN_PARTICIPANTS) { + if (ret < priv->child_count) { gf_msg_debug (this->name, 0, "%s: Skipping " "self-heal as only %d number " "of subvolumes " @@ -749,7 +749,7 @@ restore_time: if (!is_arbiter_the_only_sink) { ret = afr_selfheal_inodelk (frame, this, fd->inode, this->name, 0, 0, data_lock); - if (ret < AFR_SH_MIN_PARTICIPANTS) { + if (ret < priv->child_count) { ret = -ENOTCONN; did_sh = _gf_false; goto skip_undo_pending; @@ -878,7 +878,7 @@ afr_selfheal_data (call_frame_t *frame, xlator_t *this, inode_t *inode) priv->sh_domain, 0, 0, locked_on); { - if (ret < AFR_SH_MIN_PARTICIPANTS) { + if (ret < priv->child_count) { gf_msg_debug (this->name, 0, "%s: Skipping " "self-heal as only %d number of " "subvolumes could be locked", |