glusterd: log appropriate message when locking fails

PROBLEM:

When a transaction is already in progress, and the user tries to
execute another glusterd operation, the second operation fails as
glusterd fails to acquire lock. But to the user, a message like
"Operation failed" does not give ample information about why the
operation failed.

FIX:

Made glusterd_op_txn_begin use and initialise error string, which is
needed to capture failure in the "lock" phase.

Also made gd_sync_task_begin set error string appropriately when
locking fails.

In the process, I had to introduce error string in some glusterd_handle_*
functions. And because I introduced error string in these handlers, I
decided to also set them in places where these handlers could possibly
fail.

HOW I TESTED IT:

For want of a better idea, I "commented out" the call to
"glusterd_unlock", recompiled glusterd and ran two glusterd volume
operations, one after the other. The second operation fails with the
message "Another transaction is in progress. Please try again after
sometime." as expected.

The tests were performed on two volume ops : one of them
synctask'ized (volume start) and the other NOT (volume create).

Change-Id: Ia862972929872ae2f053707a544824d9cadc37be
BUG: 873549
Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
Reviewed-on: http://review.gluster.org/4197
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Anand Avati <avati@redhat.com>

1 files changed, 24 insertions, 16 deletions

diff --git a/xlators/mgmt/glusterd/src/glusterd-rebalance.c b/xlators/mgmt/glusterd/src/glusterd-rebalance.c
index d942baa5502..3698b82cff0 100644
--- a/xlators/mgmt/glusterd/src/glusterd-rebalance.c
+++ b/xlators/mgmt/glusterd/src/glusterd-rebalance.c
@@ -371,16 +371,19 @@ out:
 int
 glusterd_handle_defrag_volume (rpcsvc_request_t *req)
 {
-        int32_t                 ret     = -1;
-        gf_cli_req              cli_req = {{0,}};
-        glusterd_conf_t        *priv    = NULL;
-        dict_t                 *dict    = NULL;
-        char                   *volname = NULL;
-        gf_cli_defrag_type      cmd     = 0;
+        int32_t                 ret       = -1;
+        gf_cli_req              cli_req   = {{0,}};
+        glusterd_conf_t        *priv      = NULL;
+        dict_t                 *dict      = NULL;
+        char                   *volname   = NULL;
+        gf_cli_defrag_type      cmd       = 0;
+        char                    msg[2048] = {0,};
+        xlator_t               *this      = NULL;
 
         GF_ASSERT (req);
+        this = THIS;
 
-        priv = THIS->private;
+        priv = this->private;
 
         ret = xdr_to_generic (req->msg[0], &cli_req, (xdrproc_t)xdr_gf_cli_req);
         if (ret < 0) {
@@ -396,24 +399,26 @@ glusterd_handle_defrag_volume (rpcsvc_request_t *req)
                                         cli_req.dict.dict_len,
                                         &dict);
                 if (ret < 0) {
-                        gf_log ("glusterd", GF_LOG_ERROR,
+                        gf_log (this->name, GF_LOG_ERROR,
                                 "failed to "
                                 "unserialize req-buffer to dictionary");
+                        snprintf (msg, sizeof (msg), "Unable to decode the "
+                                  "command");
                         goto out;
                 }
         }
 
         ret = dict_get_str (dict, "volname", &volname);
         if (ret) {
-                gf_log (THIS->name, GF_LOG_ERROR,
-                        "Failed to get volname");
+                snprintf (msg, sizeof (msg), "Failed to get volume name");
+                gf_log (this->name, GF_LOG_ERROR, "%s", msg);
                 goto out;
         }
 
         ret = dict_get_int32 (dict, "rebalance-command", (int32_t*)&cmd);
         if (ret) {
-                gf_log (THIS->name, GF_LOG_ERROR,
-                        "Failed to get command");
+                snprintf (msg, sizeof (msg), "Failed to get command");
+                gf_log (this->name, GF_LOG_ERROR, "%s", msg);
                 goto out;
         }
 
@@ -424,9 +429,10 @@ glusterd_handle_defrag_volume (rpcsvc_request_t *req)
         if ((cmd == GF_DEFRAG_CMD_STATUS) ||
               (cmd == GF_DEFRAG_CMD_STOP)) {
                 ret = glusterd_op_begin (req, GD_OP_DEFRAG_BRICK_VOLUME,
-                                                  dict);
+                                         dict, msg, sizeof (msg));
         } else
-                ret = glusterd_op_begin (req, GD_OP_REBALANCE, dict);
+                ret = glusterd_op_begin (req, GD_OP_REBALANCE, dict,
+                                         msg, sizeof (msg));
 
 out:
 
@@ -434,8 +440,10 @@ out:
         glusterd_op_sm ();
 
         if (ret) {
-                ret = glusterd_op_send_cli_response (GD_OP_REBALANCE, ret, 0, req,
-                                                     dict, "operation failed");
+                if (msg[0] == '\0')
+                        snprintf (msg, sizeof (msg), "Operation failed");
+                ret = glusterd_op_send_cli_response (GD_OP_REBALANCE, ret, 0,
+                                                     req, dict, msg);
                 if (dict)
                         dict_unref (dict);
         }