From ddad856d371b1cbc80e1a195e9d81edb1be31371 Mon Sep 17 00:00:00 2001 From: Emmanuel Dreyfus Date: Mon, 29 Apr 2013 17:05:03 +0200 Subject: Fix spurious brick disconnects Spurious disconnect were caused by a race condition inside rpc_transport_ref()/rpc_transport_unref() that allowed the refcount to drop to zero while the transport was still in use. The race condition is made possible because of an uninitiaized mutex produced when socket_server_event_handler() copies the transport BUG: 764655 Change-Id: I34fe097a0ac21b0dbf58f5eed84880e3fd9814f2 Signed-off-by: Emmanuel Dreyfus Reviewed-on: http://review.gluster.org/4900 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi Reviewed-by: Anand Avati --- rpc/rpc-transport/socket/src/socket.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/rpc/rpc-transport/socket/src/socket.c b/rpc/rpc-transport/socket/src/socket.c index 78127cd1c..8b7aa4f2f 100644 --- a/rpc/rpc-transport/socket/src/socket.c +++ b/rpc/rpc-transport/socket/src/socket.c @@ -2474,6 +2474,15 @@ socket_server_event_handler (int fd, int idx, void *data, if (!new_trans) goto unlock; + ret = pthread_mutex_init(&new_trans->lock, NULL); + if (ret == -1) { + gf_log (this->name, GF_LOG_WARNING, + "pthread_mutex_init() failed: %s", + strerror (errno)); + close (new_sock); + goto unlock; + } + new_trans->name = gf_strdup (this->name); memcpy (&new_trans->peerinfo.sockaddr, &new_sockaddr, -- cgit