summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorPranith Kumar K <pkarampu@redhat.com>2014-09-17 11:33:23 +0530
committerPranith Kumar Karampuri <pkarampu@redhat.com>2014-09-29 05:46:55 -0700
commit94045e4ae779b1bde54ad1dd0ed87981a6872125 (patch)
treef8edbdc702545cf8afe61c0f190bb4416ba997cd
parent3ba5f1d38d58e72d562f6d19498bed00fb2727bc (diff)
cluster/afr: Launch self-heal only when all the brick status is known
Problem: File goes into split-brain because of wrong erasing of xattrs. RCA: The issue happens because index self-heal is triggered even before all the bricks are up. So what ends up happening while erasing the xattrs is, xattrs are erased only on the sink brick for the brick that it thinks is up leading to split-brain Example: lets say the xattrs before heal started are: brick 2: trusted.afr.vol1-client-2=0x000000020000000000000000 trusted.afr.vol1-client-3=0x000000020000000000000000 brick 3: trusted.afr.vol1-client-2=0x000010040000000000000000 trusted.afr.vol1-client-3=0x000000000000000000000000 if only brick-2 came up at the time of triggering the self-heal only 'trusted.afr.vol1-client-2' is erased leading to the following xattrs: brick 2: trusted.afr.vol1-client-2=0x000000000000000000000000 trusted.afr.vol1-client-3=0x000000020000000000000000 brick 3: trusted.afr.vol1-client-2=0x000010040000000000000000 trusted.afr.vol1-client-3=0x000000000000000000000000 So the file goes into split-brain. Change-Id: I1185713c688e0f41fd32bf2a5953c505d17a3173 BUG: 1142601 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/8755 Reviewed-by: Krutika Dhananjay <kdhananj@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
-rw-r--r--xlators/cluster/afr/src/afr-common.c17
1 files changed, 15 insertions, 2 deletions
diff --git a/xlators/cluster/afr/src/afr-common.c b/xlators/cluster/afr/src/afr-common.c
index 3e745e2491e..42ff70937ac 100644
--- a/xlators/cluster/afr/src/afr-common.c
+++ b/xlators/cluster/afr/src/afr-common.c
@@ -3678,8 +3678,21 @@ afr_notify (xlator_t *this, int32_t event,
if (propagate)
ret = default_notify (this, event, data);
- if (call_psh && priv->shd.iamshd) {
- afr_selfheal_childup (this, up_child);
+ if (!had_heard_from_all && have_heard_from_all && priv->shd.iamshd) {
+ /*
+ * Since self-heal is supposed to be launched only after
+ * the responses from all the bricks are collected,
+ * launch self-heals now on all up subvols.
+ */
+ for (i = 0; i < priv->child_count; i++)
+ if (priv->child_up[i])
+ afr_selfheal_childup (this, i);
+ } else if (have_heard_from_all && call_psh && priv->shd.iamshd) {
+ /*
+ * Already heard from everyone. Just launch heal on now up
+ * subvolume.
+ */
+ afr_selfheal_childup (this, up_child);
}
out:
return ret;