From 1e86ac48af137a3cfd48cba727e7abe132dfc8de Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Thu, 4 Aug 2011 10:33:08 +0200 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_main.c | 2 +- drivers/block/drbd/drbd_receiver.c | 10 +++++----- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 56569a803331..8658dac2853a 100644 --- 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 bb92671d1f16..aa6c52c80e2e 100644 --- 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; -- 2.39.2