From 0a5693e82c90479a012c903915fa970c7bf22593 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Tue, 9 Mar 2010 14:14:51 -0600 Subject: [PATCH] libiscsi: Fix recovery slowdown regression commit 4ae0a6c15efcc37e94e3f30e3533bdec03c53126 upstream. We could be failing/stopping a connection due to libiscsi starting recovery/cleanup, but the xmit path or scsi eh thread path could be dropping the connection at the same time. As a result the session->state gets set to failed instead of in recovery. We end up not blocking the session and so the replacement timeout never gets started and we only end up failing the IO when scsi_softirq_done sees that the cmd has been running for (cmd->allowed + 1) * rq->timeout secs. We used to fail the IO right away so users are seeing a long delay when using dm-multipath. This problem was added in 2.6.28. Signed-off-by: Mike Christie Signed-off-by: James Bottomley Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/libiscsi.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index c28a712fd4db..e6b67f2d3229 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -3027,14 +3027,15 @@ static void iscsi_start_session_recovery(struct iscsi_session *session, session->state = ISCSI_STATE_TERMINATE; else if (conn->stop_stage != STOP_CONN_RECOVER) session->state = ISCSI_STATE_IN_RECOVERY; + + old_stop_stage = conn->stop_stage; + conn->stop_stage = flag; spin_unlock_bh(&session->lock); del_timer_sync(&conn->transport_timer); iscsi_suspend_tx(conn); spin_lock_bh(&session->lock); - old_stop_stage = conn->stop_stage; - conn->stop_stage = flag; conn->c_stage = ISCSI_CONN_STOPPED; spin_unlock_bh(&session->lock); -- 2.39.5