public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Wu Fengguang <fengguang.wu@intel.com>
To: Fernando Silveira <fsilveira@gmail.com>
Cc: "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: Re: I/O and pdflush
Date: Tue, 1 Sep 2009 16:14:58 +0800	[thread overview]
Message-ID: <20090901081458.GD1446@localhost> (raw)
In-Reply-To: <6afc6d4a0908310733l6426e21fu11d826f6ffa6a2af@mail.gmail.com>

On Mon, Aug 31, 2009 at 10:33:43PM +0800, Fernando Silveira wrote:
> On Mon, Aug 31, 2009 at 11:07, Wu Fengguang<fengguang.wu@intel.com> wrote:
> > On Mon, Aug 31, 2009 at 10:01:13PM +0800, Wu Fengguang wrote:
> >> On Mon, Aug 31, 2009 at 10:00:06PM +0800, Wu Fengguang wrote:
> >> > Hi Fernando,
> >> >
> >> > What's your SSD's IO parameters? Ie. output of this command:
> >> >
> >> >         grep -r . /sys/block/sda/queue/
> >> >
> >> > Please replace 'sda' with your SSD device name.
> >>
> >> Oh I guess it's sdc:
> >>
> >>          grep -r . /sys/block/sdc/queue/
> 
> Here is it:
> 
> # grep -r . /sys/block/sdc/queue/
> /sys/block/sdc/queue/nr_requests:128
> /sys/block/sdc/queue/read_ahead_kb:128
> /sys/block/sdc/queue/max_hw_sectors_kb:128
> /sys/block/sdc/queue/max_sectors_kb:128
> /sys/block/sdc/queue/scheduler:noop anticipatory [deadline] cfq
> /sys/block/sdc/queue/hw_sector_size:512
> /sys/block/sdc/queue/rotational:0
> /sys/block/sdc/queue/nomerges:0
> /sys/block/sdc/queue/rq_affinity:0
> /sys/block/sdc/queue/iostats:1
> /sys/block/sdc/queue/iosched/read_expire:500
> /sys/block/sdc/queue/iosched/write_expire:5000
> /sys/block/sdc/queue/iosched/writes_starved:2
> /sys/block/sdc/queue/iosched/front_merges:1
> /sys/block/sdc/queue/iosched/fifo_batch:16
> #
> 
> These are probably default settings.
> 
> > BTW, would you run "iostat -x 1 5" (which will run 5 seconds) when
> > doing I/O in ideal throughput, and when in 25MB/s thoughput state?
> 
> Both files are attached (25mbps = 25MB/s, 80mbps = 80MB/s).

The iostat reported IO size is 64kb, which is half of max_sectors_kb=128.
It is strange why the optimal 128kb IO size is not reached in both cases:

        Device:         rrqm/s   wrqm/s     r/s     w/s    rsec/s   wsec/s  avgrq-sz avgqu-sz   await  svctm  %util
case 1: sdc               0.00 69088.00     0.00  552.00     0.00 70656.00    128.00   142.75  386.39   1.81 100.10
case 2: sdc               0.00 153504.00    0.00 1200.00     0.00 153600.00   128.00   138.35  115.76   0.83 100.10

Fernando, could you try increasing these deadline parameters by 10
times?

        echo 160   > /sys/block/sdc/queue/iosched/fifo_batch
        echo 50000 > /sys/block/sdc/queue/iosched/write_expire

And try cfq iosched if that still fails? The iostat outputs would be
enough during the tests.

Thanks,
Fengguang

  reply	other threads:[~2009-09-01  8:50 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-07-11 17:27 I/O and pdflush Fernando Silveira
2009-07-12  8:04 ` Wu Fengguang
2009-08-28 21:48   ` Fernando Silveira
2009-08-29 10:12     ` Wu Fengguang
2009-08-29 10:21       ` Wu Fengguang
2009-08-31 13:24         ` Fernando Silveira
2009-08-31 14:00           ` Wu Fengguang
2009-08-31 14:01             ` Wu Fengguang
2009-08-31 14:07               ` Wu Fengguang
2009-08-31 14:33                 ` Fernando Silveira
2009-09-01  8:14                   ` Wu Fengguang [this message]
     [not found]                     ` <6afc6d4a0909010710l2cf77fbbmb1ab192ed12a7efc@mail.gmail.com>
2009-09-02  3:05                       ` Wu Fengguang
     [not found]                         ` <6afc6d4a0909020429l2bfecee9xd00527fcaa323751@mail.gmail.com>
     [not found]                           ` <20090902125057.GA7982@localhost>
     [not found]                             ` <6afc6d4a0909031346qda0b17coe4c60250fcac827f@mail.gmail.com>
2009-09-04  2:21                               ` Wu Fengguang
2009-09-04  2:34                                 ` Wu Fengguang
     [not found] <cWOyL-3Ys-15@gated-at.bofh.it>
2009-08-31 21:57 ` Daniel J Blueman
2009-09-01 14:33   ` Fernando Silveira

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=20090901081458.GD1446@localhost \
    --to=fengguang.wu@intel.com \
    --cc=fsilveira@gmail.com \
    --cc=linux-kernel@vger.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