glusterd: Disable transport before cleaning up rpc object

        Backport of http://review.gluster.org/5000

Problem:
rpc_transport object, which is part of rpc_clnt, is destroyed
prematurely. This is because, rpc_transport object is ref'd by socket
layer and rpc layer. These ref's, until the synctask'izing of
operations, were unref'd sequentially in the epoll thread.
With more threads at play, the sequential unref guarantee is off.

Fix:
Shutting down the transport before proceeding with cleaning up of
rpc_clnt object would serialize the unref's on the rpc_transport object
and thus eliminating the race.

Also, we don't store the address of brickinfo in brick's rpc notify
function, to avoid the possibility of referring a freed brickinfo.
Instead we use a string based id to 'reach' the corresponding brickinfo.

Change-Id: If2739e2eeaee1e8b071ab2b6754b7ea0f81cfceb
BUG: 962619
Signed-off-by: Krishnan Parthasarathi <kparthas@redhat.com>
Reviewed-on: http://review.gluster.org/5214
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Vijay Bellur <vbellur@redhat.com>

1 files changed, 46 insertions, 2 deletions

diff --git a/xlators/mgmt/glusterd/src/glusterd-handler.c b/xlators/mgmt/glusterd/src/glusterd-handler.c
index d4b7dc93f16..095f1966d87 100644
--- a/xlators/mgmt/glusterd/src/glusterd-handler.c
+++ b/xlators/mgmt/glusterd/src/glusterd-handler.c
@@ -3356,6 +3356,43 @@ glusterd_handle_cli_clearlocks_volume (rpcsvc_request_t *req)
                                             __glusterd_handle_cli_clearlocks_volume);
 }
 
+static int
+get_brickinfo_from_brickid (char *brickid, glusterd_brickinfo_t **brickinfo)
+{
+        glusterd_volinfo_t      *volinfo    = NULL;
+        char                    *volid_str  = NULL;
+        char                    *brick      = NULL;
+        char                    *brickid_dup = NULL;
+        uuid_t                  volid       = {0};
+        int                     ret         = -1;
+
+        brickid_dup = gf_strdup (brickid);
+        if (!brickid_dup)
+                goto out;
+
+        volid_str = brickid_dup;
+        brick = strchr (brickid_dup, ':');
+        *brick = '\0';
+        brick++;
+        if (!volid_str || !brick)
+                goto out;
+
+        uuid_parse (volid_str, volid);
+        ret = glusterd_volinfo_find_by_volume_id (volid, &volinfo);
+        if (ret)
+                goto out;
+
+        ret = glusterd_volume_brickinfo_get_by_brick (brick, volinfo,
+                                                      brickinfo);
+        if (ret)
+                goto out;
+
+        ret = 0;
+out:
+        GF_FREE (brickid_dup);
+        return ret;
+}
+
 int
 __glusterd_brick_rpc_notify (struct rpc_clnt *rpc, void *mydata,
                           rpc_clnt_event_t event, void *data)
@@ -3363,10 +3400,15 @@ __glusterd_brick_rpc_notify (struct rpc_clnt *rpc, void *mydata,
         xlator_t                *this = NULL;
         glusterd_conf_t         *conf = NULL;
         int                     ret = 0;
+        char                    *brickid = NULL;
         glusterd_brickinfo_t    *brickinfo = NULL;
 
-        brickinfo = mydata;
-        if (!brickinfo)
+        brickid = mydata;
+        if (!brickid)
+                return 0;
+
+        ret = get_brickinfo_from_brickid (brickid, &brickinfo);
+        if (ret)
                 return 0;
 
         this = THIS;
@@ -3385,6 +3427,8 @@ __glusterd_brick_rpc_notify (struct rpc_clnt *rpc, void *mydata,
         case RPC_CLNT_DISCONNECT:
                 gf_log (this->name, GF_LOG_DEBUG, "got RPC_CLNT_DISCONNECT");
                 glusterd_set_brick_status (brickinfo, GF_BRICK_STOPPED);
+                if (rpc_clnt_is_disabled (rpc))
+                        GF_FREE (brickid);
                 break;
 
         default: