From: Kashyap Desai <kashyap.desai@broadcom.com>
To: Ming Lei <ming.lei@redhat.com>
Cc: Bart Van Assche <bvanassche@acm.org>,
linux-scsi@vger.kernel.org,
"Martin K . Petersen" <martin.petersen@oracle.com>,
James Bottomley <James.Bottomley@hansenpartnership.com>,
Jens Axboe <axboe@kernel.dk>,
"Ewan D . Milne" <emilne@redhat.com>,
Omar Sandoval <osandov@fb.com>, Christoph Hellwig <hch@lst.de>,
Hannes Reinecke <hare@suse.de>,
Laurence Oberman <loberman@redhat.com>,
Bart Van Assche <bart.vanassche@wdc.com>,
Sathya Prakash Veerichetty <sathya.prakash@broadcom.com>
Subject: RE: [RFC PATCH V4 2/2] scsi: core: don't limit per-LUN queue depth for SSD
Date: Wed, 23 Oct 2019 13:16:48 +0530 [thread overview]
Message-ID: <1c40066e1f3361f2b6c8f90b4115ad01@mail.gmail.com> (raw)
In-Reply-To: <20191023012838.GB18083@ming.t460p>
V4 2/2] scsi: core: don't limit per-LUN queue depth
> for SSD
>
> On Fri, Oct 18, 2019 at 12:00:07AM +0530, Kashyap Desai wrote:
> > > On 10/9/19 2:32 AM, Ming Lei wrote:
> > > > @@ -354,7 +354,8 @@ void scsi_device_unbusy(struct scsi_device
> > > > *sdev,
> > > struct scsi_cmnd *cmd)
> > > > if (starget->can_queue > 0)
> > > > atomic_dec(&starget->target_busy);
> > > >
> > > > - atomic_dec(&sdev->device_busy);
> > > > + if (!blk_queue_nonrot(sdev->request_queue))
> > > > + atomic_dec(&sdev->device_busy);
> > > > }
> > > >
> > >
> > > Hi Ming,
> > >
> > > Does this patch impact the meaning of the queue_depth sysfs
> > > attribute (see also sdev_store_queue_depth()) and also the queue
> > > depth ramp up/down mechanism (see also
> scsi_handle_queue_ramp_up())?
> > > Have you considered to enable/disable busy tracking per LUN
> > > depending on whether or not sdev-
> > > >queue_depth < shost->can_queue?
> > >
> > > The megaraid and mpt3sas drivers read sdev->device_busy directly. Is
> > > the current version of this patch compatible with these drivers?
> >
> > We need to know per scsi device outstanding in mpt3sas and
> > megaraid_sas driver.
>
> Is the READ done in fast path or slow path? If it is on slow path, it
should be
> easy to do via blk_mq_in_flight_rw().
READ is done in fast path.
>
> > Can we get supporting API from block layer (through SML) ? something
> > similar to "atomic_read(&hctx->nr_active)" which can be derived from
> > sdev->request_queue->hctx ?
> > At least for those driver which is nr_hw_queue = 1, it will be useful
> > and we can avoid sdev->device_busy dependency.
>
> If you mean to add new atomic counter, we just move the .device_busy
into
> blk-mq, that can become new bottleneck.
How about below ? We define and use below API instead of
"atomic_read(&scp->device->device_busy) >" and it is giving expected
value. I have not captured performance impact on max IOPs profile.
Inline unsigned long sdev_nr_inflight_request(struct request_queue *q)
{
struct blk_mq_hw_ctx *hctx;
unsigned long nr_requests = 0;
int i;
queue_for_each_hw_ctx(q, hctx, i)
nr_requests += atomic_read(&hctx->nr_active);
return nr_requests;
}
Kashyap
>
>
> thanks,
> Ming
next prev parent reply other threads:[~2019-10-23 7:46 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-10-09 9:32 [PATCH V4 0/2] scsi: avoid atomic operations in IO path Ming Lei
2019-10-09 9:32 ` [PATCH V4 1/2] scsi: core: avoid host-wide host_busy counter for scsi_mq Ming Lei
2019-10-09 16:14 ` Bart Van Assche
2019-10-23 8:52 ` John Garry
2019-10-24 0:58 ` Ming Lei
2019-10-24 9:19 ` John Garry
2019-10-24 21:24 ` Ming Lei
2019-10-25 8:58 ` John Garry
2019-10-25 9:43 ` Ming Lei
2019-10-25 10:13 ` John Garry
2019-10-25 21:53 ` Ming Lei
2019-10-28 9:42 ` John Garry
2019-10-09 9:32 ` [RFC PATCH V4 2/2] scsi: core: don't limit per-LUN queue depth for SSD Ming Lei
2019-10-09 16:05 ` Bart Van Assche
2019-10-10 0:43 ` Ming Lei
2019-10-17 18:30 ` Kashyap Desai
2019-10-23 1:28 ` Ming Lei
2019-10-23 7:46 ` Kashyap Desai [this message]
2019-10-24 1:09 ` Ming Lei
2019-10-25 10:04 ` Kashyap Desai
2019-10-25 21:58 ` Ming Lei
2019-11-04 9:30 ` Kashyap Desai
2019-11-05 0:23 ` Ming Lei
2019-10-23 0:30 ` [scsi] cc2f854c79: suspend_stress.fail kernel test robot
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=1c40066e1f3361f2b6c8f90b4115ad01@mail.gmail.com \
--to=kashyap.desai@broadcom.com \
--cc=James.Bottomley@hansenpartnership.com \
--cc=axboe@kernel.dk \
--cc=bart.vanassche@wdc.com \
--cc=bvanassche@acm.org \
--cc=emilne@redhat.com \
--cc=hare@suse.de \
--cc=hch@lst.de \
--cc=linux-scsi@vger.kernel.org \
--cc=loberman@redhat.com \
--cc=martin.petersen@oracle.com \
--cc=ming.lei@redhat.com \
--cc=osandov@fb.com \
--cc=sathya.prakash@broadcom.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).