From: Ming Lei <ming.lei@redhat.com>
To: Pankaj Raghav <p.raghav@samsung.com>
Cc: axboe@kernel.dk, hch@lst.de, mcgrof@kernel.org,
gost.dev@samsung.com, linux-block@vger.kernel.org
Subject: Re: [PATCH 0/1] improve brd performance with blk-mq
Date: Mon, 13 Feb 2023 16:10:47 +0800 [thread overview]
Message-ID: <Y+nwh7V5xehxMWDR@T590> (raw)
In-Reply-To: <6035da22-5667-93d5-fe00-62b988425cb5@samsung.com>
On Mon, Feb 13, 2023 at 11:26:22AM +0530, Pankaj Raghav wrote:
> On 2023-02-07 07:13, Ming Lei wrote:
> > On Fri, Feb 03, 2023 at 04:00:05PM +0530, Pankaj Raghav wrote:
> >> Hi Jens,
> >> brd is one of the few block drivers that still uses submit_bio instead
> >> of blk-mq framework. The following patch converts brd to start using
> >> blk-mq framework. Performance gains are pretty evident for read workloads.
> >> The performance numbers are also attached as a part of
> >> the commit log.
> >>
> >> Performance (WD=[read|randread|write|randwrite]):
> >> $ modprobe brd rd_size=1048576 rd_nr=1
> >> $ echo "none" > /sys/block/ram0/queue/scheduler
> >> $ fio --name=<WD> --ioengine=io_uring --iodepth=64 --rw=<WD> --size=1G \
> >> --io_size=20G --loop=4 --cpus_allowed=1 --filename=/dev/ram0 --iodepth=64
> >> --direct=[0/1]
> >>
> >> --direct=0
> >
> > Can you share perf data on other non-io_uring engine often used? The
> > thing is that we still have lots of non-io_uring workloads, which can't
> > be hurt now.
> >
> Sounds good. Does psync and libaio along with io_uring suffice?
Yeah, it should be enough.
Thanks,
Ming
next prev parent reply other threads:[~2023-02-13 8:11 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <CGME20230203103122eucas1p161c0f0b674d26e23cf38466d5415420e@eucas1p1.samsung.com>
2023-02-03 10:30 ` [PATCH 0/1] improve brd performance with blk-mq Pankaj Raghav
2023-02-03 10:30 ` [PATCH] brd: improve " Pankaj Raghav
2023-02-06 15:50 ` Christoph Hellwig
2023-02-06 16:10 ` Pankaj Raghav
2023-02-07 1:43 ` [PATCH 0/1] improve brd " Ming Lei
2023-02-13 5:56 ` Pankaj Raghav
2023-02-13 8:10 ` Ming Lei [this message]
2023-02-14 14:48 ` Pankaj Raghav
2023-02-15 6:47 ` Christoph Hellwig
2023-02-15 23:38 ` Jens Axboe
2023-02-15 23:39 ` Jens Axboe
2023-02-17 14:27 ` Pankaj Raghav
2023-02-17 14:40 ` Jens Axboe
2023-02-17 14:52 ` Pankaj Raghav
2023-02-21 21:59 ` Luis Chamberlain
2023-02-21 23:51 ` Jens Axboe
2023-02-22 22:42 ` Luis Chamberlain
2023-02-22 22:47 ` Jens Axboe
2023-02-22 22:54 ` Luis Chamberlain
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=Y+nwh7V5xehxMWDR@T590 \
--to=ming.lei@redhat.com \
--cc=axboe@kernel.dk \
--cc=gost.dev@samsung.com \
--cc=hch@lst.de \
--cc=linux-block@vger.kernel.org \
--cc=mcgrof@kernel.org \
--cc=p.raghav@samsung.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