cluster/dht: Prevent dht_access from going into a loop.

If access fails with ENOTCONN, do not wind to same subvol.
We wind to first-up-subvol if access fails with ENOTCONN.
In few cases, if dht has only 1 subvolume, and access fails with
ENOTCONN, we go into a infinite loop of winding to same subvol

The fix is to check if we previously wound to same subvol, and
fail if first-up-subvol is same.

Change-Id: Ib5d3ce7d33e8ea09147905a7df1ed280874fa549
BUG: 983431
Signed-off-by: shishir gowda <sgowda@redhat.com>
Reviewed-on: http://review.gluster.org/5319
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Anand Avati <avati@redhat.com>

3 files changed, 40 insertions, 1 deletions

diff --git a/xlators/cluster/dht/src/dht-common.h b/xlators/cluster/dht/src/dht-common.h
index d00d5686428..2be7629941f 100644
--- a/xlators/cluster/dht/src/dht-common.h
+++ b/xlators/cluster/dht/src/dht-common.h
@@ -445,6 +445,7 @@ int dht_iatt_merge (xlator_t                 *this, struct iatt *to, struct iatt
 xlator_t *dht_subvol_get_hashed (xlator_t *this, loc_t *loc);
 xlator_t *dht_subvol_get_cached (xlator_t *this, inode_t *inode);
 xlator_t *dht_subvol_next (xlator_t *this, xlator_t *prev);
+xlator_t *dht_subvol_next_available (xlator_t *this, xlator_t *prev);
 int       dht_subvol_cnt (xlator_t *this, xlator_t *subvol);
 
 int dht_hash_compute (xlator_t *this, int type, const char *name, uint32_t *hash_p);
diff --git a/xlators/cluster/dht/src/dht-helper.c b/xlators/cluster/dht/src/dht-helper.c
index 23fc1ff962e..1cf343d24ac 100644
--- a/xlators/cluster/dht/src/dht-helper.c
+++ b/xlators/cluster/dht/src/dht-helper.c
@@ -505,7 +505,36 @@ out:
         return next;
 }
 
+/* This func wraps around, if prev is actually the last subvol.
+ */
+xlator_t *
+dht_subvol_next_available (xlator_t *this, xlator_t *prev)
+{
+        dht_conf_t *conf = NULL;
+        int         i = 0;
+        xlator_t   *next = NULL;
 
+        conf = this->private;
+        if (!conf)
+                goto out;
+
+        for (i = 0; i < conf->subvolume_cnt; i++) {
+                if (conf->subvolumes[i] == prev) {
+                        /* if prev is last in conf->subvolumes, then wrap
+                         * around.
+                         */
+                        if ((i + 1) < conf->subvolume_cnt) {
+                                next = conf->subvolumes[i + 1];
+                        } else {
+                                next = conf->subvolumes[0];
+                        }
+                        break;
+                }
+        }
+
+out:
+        return next;
+}
 int
 dht_subvol_cnt (xlator_t *this, xlator_t *subvol)
 {
diff --git a/xlators/cluster/dht/src/dht-inode-read.c b/xlators/cluster/dht/src/dht-inode-read.c
index d9b311fe219..10f59ab26a1 100644
--- a/xlators/cluster/dht/src/dht-inode-read.c
+++ b/xlators/cluster/dht/src/dht-inode-read.c
@@ -501,18 +501,27 @@ dht_access_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
         int          ret = -1;
         dht_local_t *local = NULL;
         xlator_t    *subvol = NULL;
+        call_frame_t *prev = NULL;
 
         local = frame->local;
+        prev = cookie;
 
+        if (!prev || !prev->this)
+                goto out;
         if (local->call_cnt != 1)
                 goto out;
         if ((op_ret == -1) && (op_errno == ENOTCONN) &&
             IA_ISDIR(local->loc.inode->ia_type)) {
 
-                subvol = dht_first_up_subvol (this);
+                subvol = dht_subvol_next_available (this, prev->this);
                 if (!subvol)
                         goto out;
 
+                /* check if we are done with visiting every node */
+                if (subvol == local->cached_subvol) {
+                        goto out;
+                }
+
                 STACK_WIND (frame, dht_access_cbk, subvol, subvol->fops->access,
                             &local->loc, local->rebalance.flags, NULL);
                 return 0;