From e88962f8c49ea1d65fa26703e5c11be3f21af2ba Mon Sep 17 00:00:00 2001 From: Pranith Kumar K Date: Mon, 21 Mar 2016 23:26:43 +0530 Subject: cluster/afr: Fix witness counting code in src/sink detection Problem: In afr-v1 pre-op, xattrop increments self xattr first then it increments the value on rest. In post-op, xattr value is decreased first on rest and at last it gets decremented on self. So for a possible operation to be witnessed i.e. a fop is seen by the brick it is important to have at least 1 pending op because without completing pre-op fop won't come. The other possibility is when fop completes but at the time of post-op after decrementing pending counts on others just before decrementing its own pending count, the brick dies. Fix: Fix witness detection code in afr_self_heal_find_direction() BUG: 1322253 Change-Id: Ia7e76482c0a46e775e269bb96ec1b9490a3ac18f Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.org/13811 Smoke: Gluster Build System CentOS-regression: Gluster Build System NetBSD-regression: NetBSD Build System Reviewed-by: Ravishankar N --- xlators/cluster/afr/src/afr-self-heal-common.c | 26 +++++++++++++++++++------- 1 file changed, 19 insertions(+), 7 deletions(-) (limited to 'xlators/cluster') diff --git a/xlators/cluster/afr/src/afr-self-heal-common.c b/xlators/cluster/afr/src/afr-self-heal-common.c index 3f4e9703546..be4cc75910e 100644 --- a/xlators/cluster/afr/src/afr-self-heal-common.c +++ b/xlators/cluster/afr/src/afr-self-heal-common.c @@ -696,15 +696,27 @@ afr_selfheal_find_direction (call_frame_t *frame, xlator_t *this, } } - /* In afr-v1 if a file is self-accused but didn't have any pending - * operations on others then it is similar to 'dirty' in afr-v2. - * Consider such cases as witness. - */ - for (i = 0; i < priv->child_count; i++) { - if (self_accused[i] && !pending[i]) - witness[i] += matrix[i][i]; + /* One more class of witness similar to dirty in v2 is where no pending + * exists but we have self-accusing markers. This can happen in afr-v1 + * if the brick crashes just after doing xattrop on self but + * before xattrop on the other xattrs on the brick in pre-op. */ + if (AFR_COUNT (pending, priv->child_count) == 0) { + for (i = 0; i < priv->child_count; i++) { + if (self_accused[i]) + witness[i] += matrix[i][i]; + } + } else { + /* In afr-v1 if a file is self-accused and has pending + * operations on others then it is similar to 'dirty' in afr-v2. + * Consider such cases as witness. + */ + for (i = 0; i < priv->child_count; i++) { + if (self_accused[i] && pending[i]) + witness[i] += matrix[i][i]; + } } + /* count the number of dirty fops witnessed */ for (i = 0; i < priv->child_count; i++) witness[i] += dirty[i]; -- cgit