dht: block/handle create op falling to decommissioned brick

Problem:
Post remove-brick start till commit phase, the client layout
may not be in sync with disk layout because of lack of lookup.
Hence,a create call may fall on the decommissioned brick.

Solution:
Will acquire a lock on hashed subvol. So that a fix-layout or
selfheal can not step on layout while reading the layout.

Even if we read a layout before remove-brick fix-layout and the
file falls on the decommissioned brick, the file should be
migrated to a new brick as per the fix-layout.

Change-Id: If84a12ec34f981adb2b9b224e80f535cfe5bf9f2
BUG: 1232378
Signed-off-by: Susant Palai <spalai@redhat.com>
Reviewed-on: http://review.gluster.org/11260
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Raghavendra G <rgowdapp@redhat.com>

1 files changed, 15 insertions, 3 deletions

diff --git a/xlators/cluster/dht/src/dht-selfheal.c b/xlators/cluster/dht/src/dht-selfheal.c
index ca0507bda44..42ab822a701 100644
--- a/xlators/cluster/dht/src/dht-selfheal.c
+++ b/xlators/cluster/dht/src/dht-selfheal.c
@@ -209,7 +209,7 @@ unlock:
 
         if (is_last_call (this_call_cnt)) {
                 if (local->op_ret == 0) {
-                        dht_refresh_layout_done (frame);
+                        local->refresh_layout_done (frame);
                 } else {
                         goto err;
                 }
@@ -219,7 +219,8 @@ unlock:
         return 0;
 
 err:
-        dht_selfheal_dir_finish (frame, this, -1);
+        local->refresh_layout_unlock (frame, this, -1);
+
         return 0;
 }
 
@@ -285,7 +286,7 @@ dht_refresh_layout (call_frame_t *frame)
         return 0;
 
 out:
-        dht_selfheal_dir_finish (frame, this, -1);
+        local->refresh_layout_unlock (frame, this, -1);
         return 0;
 }
 
@@ -294,10 +295,21 @@ int32_t
 dht_selfheal_layout_lock_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
                               int32_t op_ret, int32_t op_errno, dict_t *xdata)
 {
+        dht_local_t     *local = NULL;
+
+        local = frame->local;
+
+        if (!local) {
+                goto err;
+        }
+
         if (op_ret < 0) {
                 goto err;
         }
 
+        local->refresh_layout_unlock = dht_selfheal_dir_finish;
+        local->refresh_layout_done = dht_refresh_layout_done;
+
         dht_refresh_layout (frame);
         return 0;