bt_wait_ptr() will increase 'wait_index', however, if blk_mq_get_tag()
get a tag successfully after bt_wait_ptr() is called and before
sbitmap_prepare_to_wait() is called, then the 'ws' is skipped. This
behavior might cause 8 waitqueues to be unbalanced.
Move bt_wait_ptr() later should reduce the problem when the disk is
under high io preesure.
In the meantime, instead of calling bt_wait_ptr() during every loop,
calling bt_wait_ptr() only if destination hw queue is changed, which
should reduce the unfairness further.
Signed-off-by: Yu Kuai <yukuai3@xxxxxxxxxx>
---
block/blk-mq-tag.c | 11 ++++++-----
1 file changed, 6 insertions(+), 5 deletions(-)
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 68ac23d0b640..5ad85063e91e 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -131,7 +131,7 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
{
struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
struct sbitmap_queue *bt;
- struct sbq_wait_state *ws;
+ struct sbq_wait_state *ws = NULL;
DEFINE_SBQ_WAIT(wait);
unsigned int tag_offset;
int tag;
@@ -155,7 +155,6 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
if (data->flags & BLK_MQ_REQ_NOWAIT)
return BLK_MQ_NO_TAG;
- ws = bt_wait_ptr(bt, data->hctx);
do {
struct sbitmap_queue *bt_prev;
@@ -174,6 +173,8 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
if (tag != BLK_MQ_NO_TAG)
break;
+ if (!ws)
+ ws = bt_wait_ptr(bt, data->hctx);
sbitmap_prepare_to_wait(bt, ws, &wait, TASK_UNINTERRUPTIBLE);
tag = __blk_mq_get_tag(data, bt);
@@ -199,10 +200,10 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
* previous queue for compensating the wake up miss, so
* other allocations on previous queue won't be starved.
*/
- if (bt != bt_prev)
+ if (bt != bt_prev) {
sbitmap_queue_wake_up(bt_prev);
-
- ws = bt_wait_ptr(bt, data->hctx);
+ ws = bt_wait_ptr(bt, data->hctx);
+ }
} while (1);
sbitmap_finish_wait(bt, ws, &wait);
--
2.31.1
