| Message ID | 20240313214218.1736147-1-bvanassche@acm.org (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | Revert "block/mq-deadline: use correct way to throttling write requests" | expand |
On Wed, 13 Mar 2024 14:42:18 -0700, Bart Van Assche wrote: > The code "max(1U, 3 * (1U << shift) / 4)" comes from the Kyber I/O > scheduler. The Kyber I/O scheduler maintains one internal queue per hwq > and hence derives its async_depth from the number of hwq tags. Using > this approach for the mq-deadline scheduler is wrong since the > mq-deadline scheduler maintains one internal queue for all hwqs > combined. Hence this revert. > > [...] Applied, thanks! [1/1] Revert "block/mq-deadline: use correct way to throttling write requests" commit: 256aab46e31683d76d45ccbedc287b4d3f3e322b Best regards,
Hi Bart, Jens and Zhiguo, On 14/03/24 03:12, Bart Van Assche wrote: > The code "max(1U, 3 * (1U << shift) / 4)" comes from the Kyber I/O > scheduler. The Kyber I/O scheduler maintains one internal queue per hwq > and hence derives its async_depth from the number of hwq tags. Using > this approach for the mq-deadline scheduler is wrong since the > mq-deadline scheduler maintains one internal queue for all hwqs > combined. Hence this revert. > Thanks a lot for helping with this performance regression[1]. Regards, Harshit [1] https://lore.kernel.org/all/5ce2ae5d-61e2-4ede-ad55-551112602401@oracle.com/ > Cc: stable@vger.kernel.org > Cc: Damien Le Moal <dlemoal@kernel.org> > Cc: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com> > Cc: Zhiguo Niu <Zhiguo.Niu@unisoc.com> > Fixes: d47f9717e5cf ("block/mq-deadline: use correct way to throttling write requests") > Signed-off-by: Bart Van Assche <bvanassche@acm.org> > --- > block/mq-deadline.c | 3 +-- > 1 file changed, 1 insertion(+), 2 deletions(-) > > diff --git a/block/mq-deadline.c b/block/mq-deadline.c > index f958e79277b8..02a916ba62ee 100644 > --- a/block/mq-deadline.c > +++ b/block/mq-deadline.c > @@ -646,9 +646,8 @@ static void dd_depth_updated(struct blk_mq_hw_ctx *hctx) > struct request_queue *q = hctx->queue; > struct deadline_data *dd = q->elevator->elevator_data; > struct blk_mq_tags *tags = hctx->sched_tags; > - unsigned int shift = tags->bitmap_tags.sb.shift; > > - dd->async_depth = max(1U, 3 * (1U << shift) / 4); > + dd->async_depth = max(1UL, 3 * q->nr_requests / 4); > > sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, dd->async_depth); > }
diff --git a/block/mq-deadline.c b/block/mq-deadline.c index f958e79277b8..02a916ba62ee 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -646,9 +646,8 @@ static void dd_depth_updated(struct blk_mq_hw_ctx *hctx) struct request_queue *q = hctx->queue; struct deadline_data *dd = q->elevator->elevator_data; struct blk_mq_tags *tags = hctx->sched_tags; - unsigned int shift = tags->bitmap_tags.sb.shift; - dd->async_depth = max(1U, 3 * (1U << shift) / 4); + dd->async_depth = max(1UL, 3 * q->nr_requests / 4); sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, dd->async_depth); }
The code "max(1U, 3 * (1U << shift) / 4)" comes from the Kyber I/O scheduler. The Kyber I/O scheduler maintains one internal queue per hwq and hence derives its async_depth from the number of hwq tags. Using this approach for the mq-deadline scheduler is wrong since the mq-deadline scheduler maintains one internal queue for all hwqs combined. Hence this revert. Cc: stable@vger.kernel.org Cc: Damien Le Moal <dlemoal@kernel.org> Cc: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com> Cc: Zhiguo Niu <Zhiguo.Niu@unisoc.com> Fixes: d47f9717e5cf ("block/mq-deadline: use correct way to throttling write requests") Signed-off-by: Bart Van Assche <bvanassche@acm.org> --- block/mq-deadline.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)