Re: [PATCH V8 1/7] blk-mq-sched: fix scheduler bad performance

[PATCH V8 0/7] blk-mq-sched: improve sequential I/O performance · Ming Lei <hidden> · 2017-10-13
[PATCH V8 1/7] blk-mq-sched: fix scheduler bad performance · Ming Lei <hidden> · 2017-10-13
Re: [PATCH V8 1/7] blk-mq-sched: fix scheduler bad performance · Jens Axboe <axboe@kernel.dk> · 2017-10-13
[PATCH V8 2/7] blk-mq-sched: move actual dispatching into one helper · Ming Lei <hidden> · 2017-10-13
[PATCH V8 3/7] sbitmap: introduce __sbitmap_for_each_set() · Ming Lei <hidden> · 2017-10-13
[PATCH V8 4/7] blk-mq: introduce .get_budget and .put_budget in blk_mq_ops · Ming Lei <hidden> · 2017-10-13
Re: [PATCH V8 4/7] blk-mq: introduce .get_budget and .put_budget in blk_mq_ops · Jens Axboe <axboe@kernel.dk> · 2017-10-13
[PATCH V8 5/7] blk-mq-sched: improve dispatching from sw queue · Ming Lei <hidden> · 2017-10-13
[PATCH V8 6/7] SCSI: allow to pass null rq to scsi_prep_state_check() · Ming Lei <hidden> · 2017-10-13
[PATCH V8 7/7] SCSI: implement .get_budget and .put_budget for blk-mq · Ming Lei <hidden> · 2017-10-13

From: Jens Axboe <axboe@kernel.dk>
Date: 2017-10-13 17:30:20
Also in: linux-scsi, lkml

On 10/13/2017 11:24 AM, Ming Lei wrote:

When hw queue is busy, we shouldn't take requests from
scheduler queue any more, otherwise it is difficult to do
IO merge.

This patch fixes the awful IO performance on some
SCSI devices(lpfc, qla2xxx, ...) when mq-deadline/kyber
is used by not taking requests if hw queue is busy.

This looks fine to me, but needs a much better patch title.
"fix scheduler bad performance" tells you nothing.

-- 
Jens Axboe

`h`	back out one level
`j`	next message in thread
`k`	previous message in thread
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help