afr: not resolve splitbrains when copies are of same size

Automatic Splitbrain with size as policy must
not resolve splitbrains when the copies are of same size.
Determining if the sizes of copies are same and
returning -1 in that case.

updates: bz#1655052

Change-Id: I3d8e8b4d7962b070ed16c3ee02a1e5a926fd5eab
Signed-off-by: Iraj Jamali <ijamali@redhat.com>

2 files changed, 80 insertions, 18 deletions

diff --git a/tests/bugs/replicate/bug-1655052-sbrain-policy-same-size.t b/tests/bugs/replicate/bug-1655052-sbrain-policy-same-size.t
new file mode 100755
index 00000000000..319736e1157
--- /dev/null
+++ b/tests/bugs/replicate/bug-1655052-sbrain-policy-same-size.t
@@ -0,0 +1,55 @@
+#!/bin/bash
+
+#Test the split-brain resolution CLI commands.
+. $(dirname $0)/../../include.rc
+. $(dirname $0)/../../volume.rc
+
+cleanup;
+
+TEST glusterd
+TEST pidof glusterd
+
+#Create replica 2 volume
+TEST $CLI volume create $V0 replica 2 $H0:$B0/${V0}{0,1}
+TEST $CLI volume set $V0 performance.write-behind off
+TEST $CLI volume set $V0 cluster.self-heal-daemon off
+TEST $CLI volume set $V0 cluster.entry-self-heal off
+TEST $CLI volume set $V0 cluster.data-self-heal off
+TEST $CLI volume set $V0 cluster.metadata-self-heal off
+TEST $CLI volume start $V0
+TEST $GFS --volfile-id=/$V0 --volfile-server=$H0 $M0
+TEST touch $M0/file
+
+############ Healing using favorite-child-policy = size and size of bricks is same #################
+TEST kill_brick $V0 $H0 $B0/${V0}1
+TEST dd if=/dev/urandom of=$M0/file bs=1024 count=1024
+TEST $CLI volume start $V0 force
+EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" brick_up_status $V0 $H0 $B0/${V0}1
+EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" afr_child_up_status $V0 1
+TEST kill_brick $V0 $H0 $B0/${V0}0
+TEST dd if=/dev/urandom of=$M0/file bs=1024 count=1024
+
+TEST $CLI volume start $V0 force
+EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" brick_up_status $V0 $H0 $B0/${V0}0
+EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" afr_child_up_status $V0 0
+TEST $CLI volume set $V0 cluster.self-heal-daemon on
+EXPECT_WITHIN $PROCESS_UP_TIMEOUT "Y" glustershd_up_status
+EXPECT_WITHIN $CHILD_UP_TIMEOUT "1" afr_child_up_status_in_shd $V0 0
+EXPECT_WITHIN $CHILD_UP_TIMEOUT "1" afr_child_up_status_in_shd $V0 1
+TEST $CLI volume heal $V0
+
+#file still in split-brain
+EXPECT_WITHIN $HEAL_TIMEOUT "2" get_pending_heal_count $V0
+cat $M0/file > /dev/null
+EXPECT_NOT "^0$" echo $?
+
+#We know that both bricks have same size file
+TEST $CLI volume set $V0 cluster.favorite-child-policy size
+TEST $CLI volume heal $V0
+EXPECT_WITHIN $HEAL_TIMEOUT "2" get_pending_heal_count $V0
+cat $M0/file > /dev/null
+EXPECT_NOT "^0$" echo $?
+
+EXPECT_WITHIN $UMOUNT_TIMEOUT "Y" force_umount $M0
+cleanup
+
diff --git a/xlators/cluster/afr/src/afr-self-heal-common.c b/xlators/cluster/afr/src/afr-self-heal-common.c
index ccbaca37784..226876154d7 100644
--- a/xlators/cluster/afr/src/afr-self-heal-common.c
+++ b/xlators/cluster/afr/src/afr-self-heal-common.c
@@ -1163,7 +1163,8 @@ afr_sh_fav_by_ctime(xlator_t *this, struct afr_reply *replies, inode_t *inode)
 }
 
 /*
- * afr_sh_fav_by_size: Choose favorite child by size.
+ * afr_sh_fav_by_size: Choose favorite child by size
+ * when not all files are of zero size.
  */
 int
 afr_sh_fav_by_size(xlator_t *this, struct afr_reply *replies, inode_t *inode)
@@ -1175,25 +1176,31 @@ afr_sh_fav_by_size(xlator_t *this, struct afr_reply *replies, inode_t *inode)
 
     priv = this->private;
     for (i = 0; i < priv->child_count; i++) {
-        if (replies[i].valid == 1) {
-            gf_msg_debug(this->name, 0,
-                         "Child:%s file size = %" PRIu64 " for gfid %s",
-                         priv->children[i]->name, replies[i].poststat.ia_size,
-                         uuid_utoa(inode->gfid));
-            if (replies[i].poststat.ia_type == IA_IFDIR) {
-                gf_msg(this->name, GF_LOG_ERROR, 0,
-                       AFR_MSG_SBRAIN_FAV_CHILD_POLICY,
-                       "Cannot perform selfheal on %s. "
-                       "Size policy is not applicable to directories.",
-                       uuid_utoa(inode->gfid));
-                break;
-            }
-            if (replies[i].poststat.ia_size > cmp_sz) {
-                cmp_sz = replies[i].poststat.ia_size;
-                fav_child = i;
-            }
+        if (!replies[i].valid) {
+            continue;
+        }
+        gf_msg_debug(this->name, 0,
+                     "Child:%s file size = %" PRIu64 " for gfid %s",
+                     priv->children[i]->name, replies[i].poststat.ia_size,
+                     uuid_utoa(inode->gfid));
+        if (replies[i].poststat.ia_type == IA_IFDIR) {
+            gf_msg(this->name, GF_LOG_ERROR, 0, AFR_MSG_SBRAIN_FAV_CHILD_POLICY,
+                   "Cannot perform selfheal on %s. "
+                   "Size policy is not applicable to directories.",
+                   uuid_utoa(inode->gfid));
+            break;
+        }
+        if (replies[i].poststat.ia_size > cmp_sz) {
+            cmp_sz = replies[i].poststat.ia_size;
+            fav_child = i;
+        } else if (replies[i].poststat.ia_size == cmp_sz) {
+            fav_child = -1;
         }
     }
+    if (fav_child == -1) {
+        gf_msg(this->name, GF_LOG_ERROR, 0, AFR_MSG_SPLIT_BRAIN,
+               "No bigger file");
+    }
     return fav_child;
 }