From 69fa964632fe18a11a80ead0d09ef3399b08144a Mon Sep 17 00:00:00 2001 From: James Smart Date: Wed, 21 Jun 2017 17:43:21 -0700 Subject: nvme_fc: fix error recovery on link down. Currently, the fc transport invokes nvme_fc_error_recovery() on every io in which the transport detects an error. Which means: a) it's really noisy on large io loads that all get hit by a link down. b) we repeatively call nvme_stop_queues() even though queues are stopped upon the first error or as first steps of reset_work. Correct by: Errors are only meaningful if the controller is in the LIVE state. Thus, enact the reset_work only if LIVE. If called repeatively, state will have already transitioned. There's no need to stop the queues here. Let the first steps of reset_work do the queue stopping. Signed-off-by: James Smart Signed-off-by: Sagi Grimberg Signed-off-by: Jens Axboe --- drivers/nvme/host/fc.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'drivers/nvme/host/fc.c') diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 9444495343ac..ed87214fdc0e 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1749,16 +1749,16 @@ nvme_fc_nvme_ctrl_freed(struct nvme_ctrl *nctrl) static void nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg) { + /* only proceed if in LIVE state - e.g. on first error */ + if (ctrl->ctrl.state != NVME_CTRL_LIVE) + return; + dev_warn(ctrl->ctrl.device, "NVME-FC{%d}: transport association error detected: %s\n", ctrl->cnum, errmsg); dev_warn(ctrl->ctrl.device, "NVME-FC{%d}: resetting controller\n", ctrl->cnum); - /* stop the queues on error, cleanup is in reset thread */ - if (ctrl->queue_count > 1) - nvme_stop_queues(&ctrl->ctrl); - if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING)) { dev_err(ctrl->ctrl.device, "NVME-FC{%d}: error_recovery: Couldn't change state " -- cgit v1.2.3