When a LLDD can't dispatch a request to a specific zone, it will return
BLK_STS_ZONE_RESOURCE indicating this request needs to be delayed, e.g.
because the zone it will be dispatched to is still write-locked.
If this happens set the request aside in a local list to continue trying
dispatching requests such as READ requests or a WRITE/ZONE_APPEND
requests targetting other zones. This way we can still keep a high queue
depth without starving other requests even if one request can't be
served due to zone write-locking.
All requests put aside in the local list due to BLK_STS_ZONE_RESOURCE
are placed back at the head of the dispatch list for retrying the next
time the device queues are run again.
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@xxxxxxx>
---
block/blk-mq.c | 27 +++++++++++++++++++++++++++
drivers/scsi/scsi_lib.c | 1 +
2 files changed, 28 insertions(+)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index f7ab75ef4d0e..89eb062825a7 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1195,6 +1195,19 @@ static void blk_mq_handle_dev_resource(struct request *rq,
__blk_mq_requeue_request(rq);
}
+static void blk_mq_handle_zone_resource(struct request *rq,
+ struct list_head *zone_list)
+{
+ /*
+ * If we end up here it is because we cannot dispatch a request to a
+ * specific zone due to LLD level zone-write locking or other zone
+ * related resource not being available. In this case, set the request
+ * aside in zone_list for retrying it later.
+ */
+ list_add(&rq->queuelist, zone_list);
+ __blk_mq_requeue_request(rq);
+}
+
/*
* Returns true if we did some work AND can potentially do more.
*/
@@ -1206,6 +1219,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
bool no_tag = false;
int errors, queued;
blk_status_t ret = BLK_STS_OK;
+ LIST_HEAD(zone_list);
if (list_empty(list))
return false;
@@ -1264,6 +1278,16 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) {
blk_mq_handle_dev_resource(rq, list);
break;
+ } else if (ret == BLK_STS_ZONE_RESOURCE) {
+ /*
+ * Move the request to zone_list and keep going through
+ * the dipatch list to find more requests the drive
+ * accepts.
+ */
+ blk_mq_handle_zone_resource(rq, &zone_list);
+ if (list_empty(list))
+ break;
+ continue;
}
if (unlikely(ret != BLK_STS_OK)) {
@@ -1275,6 +1299,9 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
queued++;
} while (!list_empty(list));
+ if (!list_empty(&zone_list))
+ list_splice_tail_init(&zone_list, list);
+
hctx->dispatched[queued_to_index(queued)]++;
/*
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 610ee41fa54c..ea327f320b7f 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1706,6 +1706,7 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
case BLK_STS_OK:
break;
case BLK_STS_RESOURCE:
+ case BLK_STS_ZONE_RESOURCE:
if (atomic_read(&sdev->device_busy) ||
scsi_device_blocked(sdev))
ret = BLK_STS_DEV_RESOURCE;
--
2.24.1
