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 <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>

diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 56569a803331bd892df9c3e4b32c672d83c25fb5..8658dac2853ab2340273a72abdf4d6a173d8d1d7 100644 (file)
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -1318,7 +1318,7 @@ __drbd_set_state(struct drbd_conf *mdev, union drbd_state ns,
                drbd_thread_stop_nowait(&mdev->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->receiver);
 

diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index bb92671d1f161342427beaa1cea43983bc7246f7..aa6c52c80e2ecaf6b99af47e3a704fa313c74c40 100644 (file)
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -888,17 +888,12 @@ retry:
                }
        }
 
-       if (drbd_request_state(mdev, NS(conn, C_WF_REPORT_PARAMS)) < SS_SUCCESS)
-               return 0;
-
        sock->sk->sk_sndtimeo = mdev->net_conf->timeout*HZ/10;
        sock->sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT;
 
        atomic_set(&mdev->packet_seq, 0);
        mdev->peer_seq = 0;
 
-       drbd_thread_start(&mdev->asender);
-
        if (drbd_send_protocol(mdev) == -1)
                return -1;
        drbd_send_sync_param(mdev, &mdev->sync_conf);
@@ -907,6 +902,11 @@ retry:
        drbd_send_state(mdev);
        clear_bit(USE_DEGR_WFC_T, &mdev->flags);
        clear_bit(RESIZE_PENDING, &mdev->flags);
+
+       if (drbd_request_state(mdev, NS(conn, C_WF_REPORT_PARAMS)) < SS_SUCCESS)
+               return 0;
+
+       drbd_thread_start(&mdev->asender);
        mod_timer(&mdev->request_timer, jiffies + HZ); /* just start it here. */
 
        return 1;