ksummit.lists.linux.dev archive mirror
 help / color / mirror / Atom feed
From: Bart Van Assche <bart.vanassche@sandisk.com>
To: Linus Walleij <linus.walleij@linaro.org>,
	Greg KH <gregkh@linuxfoundation.org>
Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>,
	ksummit-discuss@lists.linux-foundation.org,
	Jens Axboe <axboe@fb.com>,
	hare@suse.de, Tejun Heo <tj@kernel.org>,
	osandov@osandov.com, Christoph Hellwig <hch@lst.de>
Subject: Re: [Ksummit-discuss] [TECH TOPIC] Addressing long-standing high-latency problems related to I/O
Date: Fri, 16 Sep 2016 11:10:54 +0200	[thread overview]
Message-ID: <e833f782-4db9-2de2-b7e8-99ddfb998936@sandisk.com> (raw)
In-Reply-To: <CACRpkdZqXTuPVs8mLLXE=G7VETe+K6MJDFYGTz_LnDWqaJik8g@mail.gmail.com>

On 09/16/2016 10:59 AM, Linus Walleij wrote:
> - What will subsystems (especially my pet peeve about MMC/SD
>   which is single-queue by nature) that experience a performance
>   regression with a switch to mq do? Not switch until mq has a
>   scheduling policy? Switch and suck up the performance regression,
>   multiplied by the number of Android handheld devices on the
>   planet?
>
> I only have handwavy arguments about the latter being the
> case which is why I'm working on a patch to MMC/SD to
> switch to mq as an RFT. It's taking some time though, alas
> I'm not very smart.

Hello Linus,

What was your reference when comparing blk-mq MMC/SD performance with 
the current implementation? Which I/O scheduler was used when measuring 
performance with the traditional block layer? If it was not noop, how 
does blk-mq performance of MMC/SD compare to the performance of the 
current implementation with noop scheduler?

Thanks,

Bart.

  reply	other threads:[~2016-09-16  9:10 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-09-16  7:55 Paolo Valente
2016-09-16  8:24 ` Greg KH
2016-09-16  8:59   ` Linus Walleij
2016-09-16  9:10     ` Bart Van Assche [this message]
2016-09-16 11:24       ` Linus Walleij
2016-09-16 11:46         ` Arnd Bergmann
2016-09-16 13:10           ` Paolo Valente
2016-09-16 13:36           ` Linus Walleij
2016-09-16 11:53         ` Bart Van Assche
2016-09-22  9:18     ` Ulf Hansson
2016-09-22 11:06       ` Linus Walleij
2016-09-16 15:15   ` James Bottomley
2016-09-16 18:48     ` Paolo Valente
2016-09-16 19:36       ` James Bottomley
2016-09-16 20:13         ` Paolo Valente
2016-09-19  8:17           ` Jan Kara
2016-09-17 10:31         ` Linus Walleij
2016-09-21 13:51         ` Grant Likely
2016-09-21 14:30 ` Bart Van Assche
2016-09-21 14:37   ` Paolo Valente

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=e833f782-4db9-2de2-b7e8-99ddfb998936@sandisk.com \
    --to=bart.vanassche@sandisk.com \
    --cc=axboe@fb.com \
    --cc=b.zolnierkie@samsung.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=hare@suse.de \
    --cc=hch@lst.de \
    --cc=ksummit-discuss@lists.linux-foundation.org \
    --cc=linus.walleij@linaro.org \
    --cc=osandov@osandov.com \
    --cc=tj@kernel.org \
    /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