From ed635cb0674d6e4303d1a2e27d9e6e80b451a338 Mon Sep 17 00:00:00 2001 From: Lars Ellenberg Date: Mon, 5 Nov 2012 11:54:30 +0100 Subject: drbd: if the replication link breaks during handshake, keep retrying The 8.3.12 commit drbd: Bugfix for the connection behavior fixes a "wasted established connection", if a former connection attempt failed during its early stages. However it opened a window for a regression, if a connection attempt fails during its last stages. The result was a terminated receiver thread, that left behind the supposedly transient "C_UNCONNECTED" state. Any later requests to change the connection state fail, as they wait for the connection state to "stabilize". Fix: short circuit and keep retrying to restablish a new connection, if we don't reach C_WF_REPORT_PARAMS. Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 9a9d4fd..1599a1a 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -1051,7 +1051,7 @@ randomize: rcu_read_unlock(); rv = conn_request_state(tconn, NS(conn, C_WF_REPORT_PARAMS), CS_VERBOSE); - if (rv < SS_SUCCESS) { + if (rv < SS_SUCCESS || tconn->cstate != C_WF_REPORT_PARAMS) { clear_bit(STATE_SENT, &tconn->flags); return 0; } -- cgit v0.10.2