Before dispatching a zoned write from the FIFO list, check whether there
are any zoned writes in the RB-tree for a lower LBA for the same zone.
This patch ensures that zoned writes happen in order even if at_head is
set for some writes for a zone and not for others.
Cc: Damien Le Moal <damien.lemoal@xxxxxxxxxxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Ming Lei <ming.lei@xxxxxxxxxx>
Signed-off-by: Bart Van Assche <bvanassche@xxxxxxx>
---
block/mq-deadline.c | 18 ++++++++++++------
1 file changed, 12 insertions(+), 6 deletions(-)
diff --git a/block/mq-deadline.c b/block/mq-deadline.c
index 2de6c63190d8..ed0da04c51ec 100644
--- a/block/mq-deadline.c
+++ b/block/mq-deadline.c
@@ -341,7 +341,7 @@ static struct request *
deadline_fifo_request(struct deadline_data *dd, struct dd_per_prio *per_prio,
enum dd_data_dir data_dir)
{
- struct request *rq;
+ struct request *rq, *rb_rq, *next;
unsigned long flags;
if (list_empty(&per_prio->fifo_list[data_dir]))
@@ -353,13 +353,19 @@ deadline_fifo_request(struct deadline_data *dd, struct dd_per_prio *per_prio,
/*
* Look for a write request that can be dispatched, that is one with
- * an unlocked target zone. For some HDDs, breaking a sequential
- * write stream can lead to lower throughput, so make sure to preserve
- * sequential write streams, even if that stream crosses into the next
- * zones and these zones are unlocked.
+ * an unlocked target zone. For each write request from the FIFO list,
+ * check whether an earlier write request exists in the RB tree. For
+ * some HDDs, breaking a sequential write stream can lead to lower
+ * throughput, so make sure to preserve sequential write streams, even
+ * if that stream crosses into the next zones and these zones are
+ * unlocked.
*/
spin_lock_irqsave(&dd->zone_lock, flags);
- list_for_each_entry(rq, &per_prio->fifo_list[DD_WRITE], queuelist) {
+ list_for_each_entry_safe(rq, next, &per_prio->fifo_list[DD_WRITE],
+ queuelist) {
+ rb_rq = deadline_from_pos(per_prio, data_dir, blk_rq_pos(rq));
+ if (rb_rq && blk_rq_pos(rb_rq) < blk_rq_pos(rq))
+ rq = rb_rq;
if (blk_req_can_dispatch_to_zone(rq) &&
(blk_queue_nonrot(rq->q) ||
!deadline_is_seq_write(dd, rq)))
