From: John Garry <john.garry@huawei.com>
To: Ming Lei <ming.lei@redhat.com>
Cc: Ming Lei <tom.leiming@gmail.com>, Jens Axboe <axboe@kernel.dk>,
"Martin K . Petersen" <martin.petersen@oracle.com>,
linux-block <linux-block@vger.kernel.org>,
James Bottomley <James.Bottomley@hansenpartnership.com>,
Linux SCSI List <linux-scsi@vger.kernel.org>,
Bart Van Assche <bvanassche@acm.org>,
"Hannes Reinecke" <hare@suse.com>,
Keith Busch <keith.busch@intel.com>,
"Thomas Gleixner" <tglx@linutronix.de>,
Don Brace <don.brace@microsemi.com>,
"Kashyap Desai" <kashyap.desai@broadcom.com>,
Sathya Prakash <sathya.prakash@broadcom.com>,
Christoph Hellwig <hch@lst.de>
Subject: Re: [PATCH V2 5/5] blk-mq: Wait for for hctx inflight requests on CPU unplug
Date: Thu, 30 May 2019 10:31:34 +0100 [thread overview]
Message-ID: <0b5945a5-54d8-4d4a-2058-aadd8a4117b6@huawei.com> (raw)
In-Reply-To: <20190530022810.GA16730@ming.t460p>
Hi Ming,
>>
>>> Thinking of this issue further, so far, one doable solution is to
>>> expose reply queues
>>> as blk-mq hw queues, as done by the following patchset:
>>>
>>> https://lore.kernel.org/linux-block/20180205152035.15016-1-ming.lei@redhat.com/
>>
>> I thought that this patchset had fundamental issues, in terms of working for
>> all types of hosts. FYI, I did the backport of latest hisi_sas_v3 to v4.15
>
> Could you explain it a bit about the fundamental issues for all types of
> host?
>
*As I understand*, splitting the tagset has issues with dual-mode HBAs -
as in supporting NVMe and SCSI, as some HBAs do.
> It is just for hosts with multiple reply queues, such as hisi_sas v3,
> megaraid_sas, mpt3sas and hpsa.
>
>> with this patchset (as you may have noticed in my git send mistake), but we
>> have not got to test it yet.
>>
>> On a related topic, we did test exposing reply queues as blk-mq hw queues
>> and generating the host-wide tag internally in the LLDD with sbitmap, and
>> unfortunately we were experiencing a significant performance hit, like 2300K
>> -> 1800K IOPs for 4K read.
>>
>> We need to test this further. I don't understand why we get such a big hit.
>
> The performance regression shouldn't have been introduced in theory, and it is
> because blk_mq_queue_tag_busy_iter() iterates over the same duplicated tags multiple
> times, which can be fixed easily.
>
We are testing further, and I will tentatively say that we're getting
better results (than previously) after fixing something in the LLDD. TBC.
>>
>>>
>>> In which global host-wide tags are shared for all blk-mq hw queues.
>>>
>>> Also we can remove all the reply_map stuff in drivers, then solve the problem of
>>> draining in-flight requests during unplugging CPU in a generic approach.
>>
>> So you're saying that removing this reply queue stuff can make the solution
>> to the problem more generic, but do you have an idea of the overall
>> solution?
>
> 1) convert reply queue into blk-mq hw queue first
>
> 2) then all drivers are in same position wrt. handling requests vs.
> unplugging CPU (shutdown managed IRQ)
>
> The current handling in blk_mq_hctx_notify_dead() is actually wrong,
Yeah, the comment reads that it's going away, but it's actually gone.
> at that time, all CPUs on the hctx are dead, blk_mq_run_hw_queue()
> still dispatches requests on driver's hw queue, and driver is invisible
> to DEAD CPUs mapped to this hctx, and finally interrupt for these
> requests on the hctx are lost.
>
> Frankly speaking, the above 2nd problem is still hard to solve.
>
> 1) take_cpu_down() shutdown managed IRQ first, then run teardown callback
> for states in [CPUHP_AP_ONLINE, CPUHP_AP_OFFLINE) on the to-be-offline
> CPU
>
> 2) However, all runnable tasks are removed from the CPU in the teardown
> callback for CPUHP_AP_SCHED_STARTING, which is run after managed IRQs
> are shutdown. That said it is hard to avoid new request queued to
> the hctx with all DEAD CPUs.
>
> 3) we don't support to freeze queue for specific hctx yet, or that way
> may not be accepted because of extra cost in fast path
>
> 4) once request is allocated, it should be submitted to driver no matter
> if CPU hotplug happens or not. Or free it and re-allocate new request
> on proper sw/hw queue?
>
>>
>>>
>>> Last time, it was reported that the patchset causes performance regression,
>>> which is actually caused by duplicated io accounting in
>>> blk_mq_queue_tag_busy_iter(),
>>> which should be fixed easily.
>>>
>>> What do you think of this approach?
>>
>> It would still be good to have a forward port of this patchset for testing,
>> if we're serious about it. Or at least this bug you mention fixed.
>
> I plan to make this patchset workable on 5.2-rc for your test first.
>
ok, thanks. I assume that we're still open to not adding support for
global tags in blk-mq, but rather the LLDD generating the unique tag
with sbitmap.
Cheers,
John
>
> Thanks,
> Ming
>
> .
>
next prev parent reply other threads:[~2019-05-30 9:31 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-05-27 15:02 [PATCH V2 0/5] blk-mq: Wait for for hctx inflight requests on CPU unplug Ming Lei
2019-05-27 15:02 ` [PATCH V2 1/5] scsi: select reply queue from request's CPU Ming Lei
2019-05-28 5:43 ` Hannes Reinecke
2019-05-28 10:33 ` John Garry
2019-05-29 2:36 ` Ming Lei
2019-05-27 15:02 ` [PATCH V2 2/5] blk-mq: introduce .complete_queue_affinity Ming Lei
2019-05-27 15:02 ` [PATCH V2 3/5] scsi: core: implement callback of .complete_queue_affinity Ming Lei
2019-05-27 15:02 ` [PATCH V2 4/5] scsi: implement .complete_queue_affinity Ming Lei
2019-05-27 15:02 ` [PATCH V2 5/5] blk-mq: Wait for for hctx inflight requests on CPU unplug Ming Lei
2019-05-28 16:50 ` John Garry
2019-05-29 2:28 ` Ming Lei
2019-05-29 2:42 ` Ming Lei
2019-05-29 9:42 ` John Garry
2019-05-29 10:10 ` Ming Lei
2019-05-29 15:33 ` Ming Lei
2019-05-29 16:10 ` John Garry
2019-05-30 2:28 ` Ming Lei
2019-05-30 4:11 ` Ming Lei
2019-05-30 9:31 ` John Garry [this message]
2019-05-30 9:45 ` Ming Lei
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=0b5945a5-54d8-4d4a-2058-aadd8a4117b6@huawei.com \
--to=john.garry@huawei.com \
--cc=James.Bottomley@hansenpartnership.com \
--cc=axboe@kernel.dk \
--cc=bvanassche@acm.org \
--cc=don.brace@microsemi.com \
--cc=hare@suse.com \
--cc=hch@lst.de \
--cc=kashyap.desai@broadcom.com \
--cc=keith.busch@intel.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-scsi@vger.kernel.org \
--cc=martin.petersen@oracle.com \
--cc=ming.lei@redhat.com \
--cc=sathya.prakash@broadcom.com \
--cc=tglx@linutronix.de \
--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).