From 823bd832a60dcf4bf9c162112f34f2f1783d0eaa Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Thu, 8 Nov 2012 15:04:36 +0100 Subject: [PATCH] drbd: Bugfix for the connection behavior If we get into the C_BROKEN_PIPE cstate once, the state engine set the thi->t_state of the receiver thread to restarting. But with the while loop in drbdd_init() a new connection gets established. After the call into drbdd() returns immediately since the thi->t_state is not RUNNING. The restart of drbd_init() then resets thi->t_state to RUNNING. I.e. after entering C_BROKEN_PIPE once, the next successful established connection gets wasted. The two parts of the fix: * Do not cause the thread to restart if we detect the issue with the sockets while we are in C_WF_CONNECTION. * Make sure that all actions that would have set us to C_BROKEN_PIPE happen before the state change to C_WF_REPORT_PARAMS. Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg --- drivers/block/drbd/drbd_receiver.c | 10 +++++----- drivers/block/drbd/drbd_state.c | 2 +- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 8d52121..fff5565 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -987,14 +987,9 @@ retry: } } - if (conn_request_state(tconn, NS(conn, C_WF_REPORT_PARAMS), CS_VERBOSE) < SS_SUCCESS) - return 0; - sock->sk->sk_sndtimeo = timeout; sock->sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT; - drbd_thread_start(&tconn->asender); - if (drbd_send_protocol(tconn) == -EOPNOTSUPP) return -1; @@ -1008,6 +1003,11 @@ retry: } rcu_read_unlock(); + if (conn_request_state(tconn, NS(conn, C_WF_REPORT_PARAMS), CS_VERBOSE) < SS_SUCCESS) + return 0; + + drbd_thread_start(&tconn->asender); + return h; out_release_sockets: diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c index 1132d87..ecc5e27 100644 --- a/drivers/block/drbd/drbd_state.c +++ b/drivers/block/drbd/drbd_state.c @@ -1055,7 +1055,7 @@ __drbd_set_state(struct drbd_conf *mdev, union drbd_state ns, drbd_thread_stop_nowait(&mdev->tconn->receiver); /* Upon network failure, we need to restart the receiver. */ - if (os.conn > C_TEAR_DOWN && + if (os.conn > C_WF_CONNECTION && ns.conn <= C_TEAR_DOWN && ns.conn >= C_TIMEOUT) drbd_thread_restart_nowait(&mdev->tconn->receiver); -- 2.7.4