cluster/afr: Fix all locked_on bricks are sinks check in self-heals

Problem:
Counts may give wrong results when the number of bricks is > 2. If the
locks are acquired on one source and sink, but the source accuses even the
down sink then there will be 2 sinks and lock is acquired on 2 bricks so
even when there is a clear source and sink **_finalize_source functions think
the file/directory is in split-brain.

Fix:
Check that all the bricks which are locked are sinks.

Change-Id: Ia43790e8e1bfb5e72a3d0b56bcad94abd0dc58ab
BUG: 1128721
Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
Reviewed-on: http://review.gluster.org/8456
Reviewed-by: Ravishankar N <ravishankar@redhat.com>
Reviewed-by: Krutika Dhananjay <kdhananj@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>

1 files changed, 15 insertions, 19 deletions

diff --git a/xlators/cluster/afr/src/afr-self-heal-entry.c b/xlators/cluster/afr/src/afr-self-heal-entry.c
index 9e714b0263c..dc1546c7403 100644
--- a/xlators/cluster/afr/src/afr-self-heal-entry.c
+++ b/xlators/cluster/afr/src/afr-self-heal-entry.c
@@ -430,24 +430,21 @@ afr_selfheal_entry_do (call_frame_t *frame, xlator_t *this, fd_t *fd,
 
 static int
 __afr_selfheal_entry_finalize_source (xlator_t *this, unsigned char *sources,
-				      unsigned char *sinks,
+				      unsigned char *healed_sinks,
 				      unsigned char *locked_on,
 				      struct afr_reply *replies)
 {
 	int i = 0;
 	afr_private_t *priv = NULL;
 	int source = -1;
-	int locked_count = 0;
 	int sources_count = 0;
-	int sinks_count = 0;
 
 	priv = this->private;
 
-	locked_count = AFR_COUNT (locked_on, priv->child_count);
 	sources_count = AFR_COUNT (sources, priv->child_count);
-	sinks_count = AFR_COUNT (sinks, priv->child_count);
 
-	if (locked_count == sinks_count || !sources_count) {
+	if ((AFR_CMP (locked_on, healed_sinks, priv->child_count) == 0)
+            || !sources_count) {
 		return -1;
 	}
 
@@ -471,7 +468,6 @@ __afr_selfheal_entry_prepare (call_frame_t *frame, xlator_t *this, fd_t *fd,
 	int ret = -1;
 	int source = -1;
 	afr_private_t *priv = NULL;
-	int i = 0;
 
 	priv = this->private;
 
@@ -486,7 +482,18 @@ __afr_selfheal_entry_prepare (call_frame_t *frame, xlator_t *this, fd_t *fd,
 	if (ret)
 		return ret;
 
-	source = __afr_selfheal_entry_finalize_source (this, sources, sinks,
+        /* Initialize the healed_sinks[] array optimistically to
+           the intersection of to-be-healed (i.e sinks[]) and
+           the list of servers which are up (i.e locked_on[]).
+
+           As we encounter failures in the healing process, we
+           will unmark the respective servers in the healed_sinks[]
+           array.
+        */
+        AFR_INTERSECT (healed_sinks, sinks, locked_on, priv->child_count);
+
+	source = __afr_selfheal_entry_finalize_source (this, sources,
+                                                       healed_sinks,
 						       locked_on, replies);
 	if (source < 0) {
 		/* If source is < 0 (typically split-brain), we perform a
@@ -494,17 +501,6 @@ __afr_selfheal_entry_prepare (call_frame_t *frame, xlator_t *this, fd_t *fd,
 	}
 	*source_p = source;
 
-	for (i = 0; i < priv->child_count; i++)
-		/* Initialize the healed_sinks[] array optimistically to
-		   the intersection of to-be-healed (i.e sinks[]) and
-		   the list of servers which are up (i.e locked_on[]).
-
-		   As we encounter failures in the healing process, we
-		   will unmark the respective servers in the healed_sinks[]
-		   array.
-		*/
-		healed_sinks[i] = sinks[i] && locked_on[i];
-
 	return ret;
 }