From: "jianchao.wang" <jianchao.w.wang@oracle.com>
To: Ming Lei <tom.leiming@gmail.com>
Cc: Jens Axboe <axboe@kernel.dk>, Ming Lei <ming.lei@redhat.com>,
linux-block <linux-block@vger.kernel.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH V6 3/5] blk-mq: ensure hctx to be ran on mapped cpu when issue directly
Date: Wed, 14 Nov 2018 11:38:16 +0800 [thread overview]
Message-ID: <6fa5f24c-727a-5d20-7677-da4ac3e173f9@oracle.com> (raw)
In-Reply-To: <CACVXFVNZ1p4wV6S_FRyKssbUT9CV-aXZ=iRGQ-tY05v_7vxPnw@mail.gmail.com>
On 11/14/18 11:02 AM, Ming Lei wrote:
> On Wed, Nov 14, 2018 at 10:15 AM jianchao.wang
> <jianchao.w.wang@oracle.com> wrote:
>>
>> Hi Jens
>>
>> Thanks for your kindly response.
>>
>> On 11/13/18 9:44 PM, Jens Axboe wrote:
>>> On 11/13/18 2:56 AM, Jianchao Wang wrote:
>>>> When issue request directly and the task is migrated out of the
>>>> original cpu where it allocates request, hctx could be ran on
>>>> the cpu where it is not mapped.
>>>> To fix this,
>>>> - insert the request forcibly if BLK_MQ_F_BLOCKING is set.
>>>> - check whether the current is mapped to the hctx, if not, insert
>>>> forcibly.
>>>> - invoke __blk_mq_issue_directly under preemption disabled.
>>>
>>> I'm not too crazy about this one, adding a get/put_cpu() in the hot
>>> path, and a cpumask test. The fact is that most/no drivers care
>>> about strict placement. We always try to do so, if convenient,
>>> since it's faster, but this seems to be doing the opposite.
>>>
>>> I'd be more inclined to have a driver flag if it needs guaranteed
>>> placement, using one an ops BLK_MQ_F_STRICT_CPU flag or similar.
>>>
>>> What do you think?
>>>
>>
>> I'd inclined blk-mq should comply with a unified rule, no matter the
>> issuing directly path or inserting one. Then blk-mq would have a simpler
>> model. And also this guarantee could be a little good for drivers,
>> especially the case where cpu and hw queue mapping is 1:1.
>
> I guess it is quite hard to respect this rule 100%, such as in case of
> CPU hotplug.
>
Yes, it is indeed the case.
Looks like this patch is contentious.
I will drop this one and post later as a standalone one if necessary.
Thanks
Jianchao
next prev parent reply other threads:[~2018-11-14 3:38 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-11-13 9:56 [PATCH V6 0/5] blk-mq: refactor and fix on issue request directly Jianchao Wang
2018-11-13 9:56 ` [PATCH V6 1/5] blk-mq: refactor the code of " Jianchao Wang
2018-11-13 9:56 ` [PATCH V6 2/5] blk-mq: fix issue directly case when q is stopped or quiesced Jianchao Wang
2018-11-13 9:56 ` [PATCH V6 3/5] blk-mq: ensure hctx to be ran on mapped cpu when issue directly Jianchao Wang
2018-11-13 13:44 ` Jens Axboe
2018-11-14 2:15 ` jianchao.wang
2018-11-14 3:02 ` Ming Lei
2018-11-14 3:38 ` jianchao.wang [this message]
2018-11-13 9:56 ` [PATCH V6 4/5] blk-mq: issue directly with bypass 'false' in blk_mq_sched_insert_requests Jianchao Wang
2018-11-13 9:56 ` [PATCH V6 5/5] blk-mq: replace and kill blk_mq_request_issue_directly Jianchao Wang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=6fa5f24c-727a-5d20-7677-da4ac3e173f9@oracle.com \
--to=jianchao.w.wang@oracle.com \
--cc=axboe@kernel.dk \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=ming.lei@redhat.com \
--cc=tom.leiming@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).