summaryrefslogtreecommitdiff
path: root/drivers/nvme
diff options
context:
space:
mode:
authorUday Shankar <ushankar@purestorage.com>2023-05-25 21:22:04 +0300
committerKeith Busch <kbusch@kernel.org>2023-05-31 06:57:42 +0300
commitc7275ce6a5fd32ca9f5a6294ed89cf0523181af9 (patch)
tree9751bb1f78691a18d83a3a84aa5f84cb052397b4 /drivers/nvme
parent774a9636514764ddc0d072ae0d1d1c01a47e6ddd (diff)
downloadlinux-c7275ce6a5fd32ca9f5a6294ed89cf0523181af9.tar.xz
nvme: improve handling of long keep alives
Upon keep alive completion, nvme_keep_alive_work is scheduled with the same delay every time. If keep alive commands are completing slowly, this may cause a keep alive timeout. The following trace illustrates the issue, taking KATO = 8 and TBKAS off for simplicity: 1. t = 0: run nvme_keep_alive_work, send keep alive 2. t = ε: keep alive reaches controller, controller restarts its keep alive timer 3. t = 4: host receives keep alive completion, schedules nvme_keep_alive_work with delay 4 4. t = 8: run nvme_keep_alive_work, send keep alive Here, a keep alive having RTT of 4 causes a delay of at least 8 - ε between the controller receiving successive keep alives. With ε small, the controller is likely to detect a keep alive timeout. Fix this by calculating the RTT of the keep alive command, and adjusting the scheduling delay of the next keep alive work accordingly. Reported-by: Costa Sapuntzakis <costa@purestorage.com> Reported-by: Randy Jennings <randyj@purestorage.com> Signed-off-by: Uday Shankar <ushankar@purestorage.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Keith Busch <kbusch@kernel.org>
Diffstat (limited to 'drivers/nvme')
-rw-r--r--drivers/nvme/host/core.c16
1 files changed, 15 insertions, 1 deletions
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index dbfca1b925f8..3ec38e2b9173 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1199,6 +1199,20 @@ static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq,
struct nvme_ctrl *ctrl = rq->end_io_data;
unsigned long flags;
bool startka = false;
+ unsigned long rtt = jiffies - (rq->deadline - rq->timeout);
+ unsigned long delay = nvme_keep_alive_work_period(ctrl);
+
+ /*
+ * Subtract off the keepalive RTT so nvme_keep_alive_work runs
+ * at the desired frequency.
+ */
+ if (rtt <= delay) {
+ delay -= rtt;
+ } else {
+ dev_warn(ctrl->device, "long keepalive RTT (%u ms)\n",
+ jiffies_to_msecs(rtt));
+ delay = 0;
+ }
blk_mq_free_request(rq);
@@ -1217,7 +1231,7 @@ static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq,
startka = true;
spin_unlock_irqrestore(&ctrl->lock, flags);
if (startka)
- nvme_queue_keep_alive_work(ctrl);
+ queue_delayed_work(nvme_wq, &ctrl->ka_work, delay);
return RQ_END_IO_NONE;
}