From 5046f18d5bd9ad7638b32c3b304ff39a74c064df Mon Sep 17 00:00:00 2001 From: Junxiao Bi Date: Thu, 9 Oct 2014 15:25:11 -0700 Subject: ocfs2: don't fire quorum before connection established Firing quorum before connection established can cause unexpected node to reboot. Assume there are 3 nodes in the cluster, Node 1, 2, 3. Node 2 and 3 have wrong ip address of Node 1 in cluster.conf and global heartbeat is enabled in the cluster. After the heatbeats are started on these three nodes, Node 1 will reboot due to quorum fencing. It is similar case if Node 1's networking is not ready when starting the global heartbeat. The reboot is not friendly as customer is not fully ready for ocfs2 to work. Fix it by not allowing firing quorum before the connection is established. In this case, ocfs2 will wait until the wrong configuration is fixed or networking is up to continue. Also update the log to guide the user where to check when connection is not built for a long time. Signed-off-by: Junxiao Bi Reviewed-by: Srinivas Eeda Cc: Joel Becker Cc: Mark Fasheh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/cluster/tcp.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index 56cebba2390c..509e6d5415e2 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -536,7 +536,7 @@ static void o2net_set_nn_state(struct o2net_node *nn, if (nn->nn_persistent_error || nn->nn_sc_valid) wake_up(&nn->nn_sc_wq); - if (!was_err && nn->nn_persistent_error) { + if (was_valid && !was_err && nn->nn_persistent_error) { o2quo_conn_err(o2net_num_from_nn(nn)); queue_delayed_work(o2net_wq, &nn->nn_still_up, msecs_to_jiffies(O2NET_QUORUM_DELAY_MS)); @@ -1721,7 +1721,8 @@ static void o2net_connect_expired(struct work_struct *work) spin_lock(&nn->nn_lock); if (!nn->nn_sc_valid) { printk(KERN_NOTICE "o2net: No connection established with " - "node %u after %u.%u seconds, giving up.\n", + "node %u after %u.%u seconds, check network and" + " cluster configuration.\n", o2net_num_from_nn(nn), o2net_idle_timeout() / 1000, o2net_idle_timeout() % 1000); -- cgit v1.2.3