drbd: Avoid NetworkFailure state during disconnect
Disconnecting is a cluster wide state change. In case the peer node agrees
to the state transition, it sends back the fact on the meta-data connection
and closes both sockets.
In case the node node that initiated the state transfer sees the closing
action on the data-socket, before the P_STATE_CHG_REPLY packet, it was
going into one of the network failure states.
At least with the fencing option set to something else thatn "dont-care",
the unclean shutdown of the connection causes a short IO freeze or
a fence operation.
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_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 0eefbeb..1a8f698 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -522,7 +522,6 @@
conn_err(tconn, "sock_recvmsg returned %d\n", rv);
break;
} else if (rv == 0) {
- conn_info(tconn, "sock was shut down by peer\n");
break;
} else {
/* signal came in, or peer/link went down,
@@ -535,9 +534,25 @@
set_fs(oldfs);
+ if (rv == 0) {
+ if (test_bit(DISCONNECT_SENT, &tconn->flags)) {
+ long t;
+ rcu_read_lock();
+ t = rcu_dereference(tconn->net_conf)->ping_timeo * HZ/10;
+ rcu_read_unlock();
+
+ t = wait_event_timeout(tconn->ping_wait, tconn->cstate < C_WF_REPORT_PARAMS, t);
+
+ if (t)
+ goto out;
+ }
+ conn_info(tconn, "sock was shut down by peer\n");
+ }
+
if (rv != size)
conn_request_state(tconn, NS(conn, C_BROKEN_PIPE), CS_HARD);
+out:
return rv;
}
@@ -894,6 +909,7 @@
.door_bell = COMPLETION_INITIALIZER_ONSTACK(ad.door_bell),
};
+ clear_bit(DISCONNECT_SENT, &tconn->flags);
if (conn_request_state(tconn, NS(conn, C_WF_CONNECTION), CS_VERBOSE) < SS_SUCCESS)
return -2;
@@ -5316,6 +5332,18 @@
received += rv;
buf += rv;
} else if (rv == 0) {
+ if (test_bit(DISCONNECT_SENT, &tconn->flags)) {
+ long t;
+ rcu_read_lock();
+ t = rcu_dereference(tconn->net_conf)->ping_timeo * HZ/10;
+ rcu_read_unlock();
+
+ t = wait_event_timeout(tconn->ping_wait,
+ tconn->cstate < C_WF_REPORT_PARAMS,
+ t);
+ if (t)
+ break;
+ }
conn_err(tconn, "meta connection shut down by peer.\n");
goto reconnect;
} else if (rv == -EAGAIN) {