All of lore.kernel.org
 help / color / mirror / Atom feed
From: Wu Fengguang <fengguang.wu@intel.com>
To: Martin Bligh <mbligh@google.com>
Cc: Jens Axboe <jens.axboe@oracle.com>,
	Chad Talbott <ctalbott@google.com>,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	Michael Rubin <mrubin@google.com>,
	sandeen@redhat.com, Andrew Morton <akpm@linux-foundation.org>,
	Peter Zijlstra <peterz@infradead.org>
Subject: Re: Bug in kernel 2.6.31, Slow wb_kupdate writeout
Date: Sat, 1 Aug 2009 13:03:54 +0800	[thread overview]
Message-ID: <20090801050354.GA16648@localhost> (raw)
In-Reply-To: <20090801045345.GA16011@localhost>

On Sat, Aug 01, 2009 at 12:53:46PM +0800, Wu Fengguang wrote:
> On Sat, Aug 01, 2009 at 12:03:13PM +0800, Wu Fengguang wrote:

> I can see the growth when I increased the dd size to 2GB,
> and the dd throughput decreased from 82.5MB/s to 60.9MB/s.

The raw disk write throughput seems to be 60MB/s:

        wfg ~% dd if=/dev/zero of=/opt/vm/200M bs=1M count=200 oflag=direct
        200+0 records in
        200+0 records out
        209715200 bytes (210 MB) copied, 3.48137 s, 60.2 MB/s

read throughput is a bit better:

        wfg ~% dd of=/dev/null if=/opt/vm/200M bs=1M count=200 iflag=direct
        200+0 records in
        200+0 records out
        209715200 bytes (210 MB) copied, 2.66606 s, 78.7 MB/s

        # hdparm -tT /dev/hda

        /dev/hda:
         Timing cached reads:   10370 MB in  1.99 seconds = 5213.70 MB/sec
         Timing buffered disk reads:  216 MB in  3.03 seconds =  71.22 MB/sec

And sync writes are pretty slow:

        wfg ~% dd if=/dev/zero of=/opt/vm/200M bs=1M count=200 oflag=sync
        200+0 records in
        200+0 records out
        209715200 bytes (210 MB) copied, 10.4741 s, 20.0 MB/s

Thanks,
Fengguang

WARNING: multiple messages have this Message-ID (diff)
From: Wu Fengguang <fengguang.wu@intel.com>
To: Martin Bligh <mbligh@google.com>
Cc: Jens Axboe <jens.axboe@oracle.com>,
	Chad Talbott <ctalbott@google.com>,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	Michael Rubin <mrubin@google.com>,
	sandeen@redhat.com, Andrew Morton <akpm@linux-foundation.org>,
	Peter Zijlstra <peterz@infradead.org>
Subject: Re: Bug in kernel 2.6.31, Slow wb_kupdate writeout
Date: Sat, 1 Aug 2009 13:03:54 +0800	[thread overview]
Message-ID: <20090801050354.GA16648@localhost> (raw)
In-Reply-To: <20090801045345.GA16011@localhost>

On Sat, Aug 01, 2009 at 12:53:46PM +0800, Wu Fengguang wrote:
> On Sat, Aug 01, 2009 at 12:03:13PM +0800, Wu Fengguang wrote:

> I can see the growth when I increased the dd size to 2GB,
> and the dd throughput decreased from 82.5MB/s to 60.9MB/s.

The raw disk write throughput seems to be 60MB/s:

        wfg ~% dd if=/dev/zero of=/opt/vm/200M bs=1M count=200 oflag=direct
        200+0 records in
        200+0 records out
        209715200 bytes (210 MB) copied, 3.48137 s, 60.2 MB/s

read throughput is a bit better:

        wfg ~% dd of=/dev/null if=/opt/vm/200M bs=1M count=200 iflag=direct
        200+0 records in
        200+0 records out
        209715200 bytes (210 MB) copied, 2.66606 s, 78.7 MB/s

        # hdparm -tT /dev/hda

        /dev/hda:
         Timing cached reads:   10370 MB in  1.99 seconds = 5213.70 MB/sec
         Timing buffered disk reads:  216 MB in  3.03 seconds =  71.22 MB/sec

And sync writes are pretty slow:

        wfg ~% dd if=/dev/zero of=/opt/vm/200M bs=1M count=200 oflag=sync
        200+0 records in
        200+0 records out
        209715200 bytes (210 MB) copied, 10.4741 s, 20.0 MB/s

Thanks,
Fengguang

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  reply	other threads:[~2009-08-01  5:04 UTC|newest]

Thread overview: 64+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-07-28 19:11 Bug in kernel 2.6.31, Slow wb_kupdate writeout Chad Talbott
2009-07-28 19:11 ` Chad Talbott
2009-07-28 21:49 ` Martin Bligh
2009-07-28 21:49   ` Martin Bligh
2009-07-29  7:15   ` Martin Bligh
2009-07-29  7:15     ` Martin Bligh
2009-07-29 11:43     ` Wu Fengguang
2009-07-29 11:43       ` Wu Fengguang
2009-07-29 14:11       ` Martin Bligh
2009-07-29 14:11         ` Martin Bligh
2009-07-30  1:06         ` Wu Fengguang
2009-07-30  1:06           ` Wu Fengguang
2009-07-30  1:12           ` Martin Bligh
2009-07-30  1:12             ` Martin Bligh
2009-07-30  1:57             ` Wu Fengguang
2009-07-30  1:57               ` Wu Fengguang
2009-07-30  2:59               ` Martin Bligh
2009-07-30  2:59                 ` Martin Bligh
2009-07-30  4:08                 ` Wu Fengguang
2009-07-30  4:08                   ` Wu Fengguang
2009-07-30 19:55                   ` Martin Bligh
2009-07-30 19:55                     ` Martin Bligh
2009-08-01  2:02                     ` Wu Fengguang
2009-08-01  2:02                       ` Wu Fengguang
2009-07-30  0:19       ` Martin Bligh
2009-07-30  0:19         ` Martin Bligh
2009-07-30  1:28         ` Martin Bligh
2009-07-30  1:28           ` Martin Bligh
2009-07-30  2:09           ` Wu Fengguang
2009-07-30  2:09             ` Wu Fengguang
2009-07-30  2:57             ` Martin Bligh
2009-07-30  2:57               ` Martin Bligh
2009-07-30  3:19               ` Wu Fengguang
2009-07-30  3:19                 ` Wu Fengguang
2009-07-30 20:33                 ` Martin Bligh
2009-07-30 20:33                   ` Martin Bligh
2009-08-01  2:58                   ` Wu Fengguang
2009-08-01  2:58                     ` Wu Fengguang
2009-08-01  4:10                   ` Wu Fengguang
2009-08-01  4:10                     ` Wu Fengguang
2009-07-30  1:49         ` Wu Fengguang
2009-07-30  1:49           ` Wu Fengguang
2009-07-30 21:39 ` Jens Axboe
2009-07-30 21:39   ` Jens Axboe
2009-07-30 22:01   ` Martin Bligh
2009-07-30 22:01     ` Martin Bligh
2009-07-30 22:17     ` Jens Axboe
2009-07-30 22:17       ` Jens Axboe
2009-07-30 22:34       ` Martin Bligh
2009-07-30 22:34         ` Martin Bligh
2009-07-30 22:43         ` Jens Axboe
2009-07-30 22:43           ` Jens Axboe
2009-07-30 22:48           ` Martin Bligh
2009-07-30 22:48             ` Martin Bligh
2009-07-31  7:50             ` Peter Zijlstra
2009-07-31  7:50               ` Peter Zijlstra
2009-08-01  4:03             ` Wu Fengguang
2009-08-01  4:03               ` Wu Fengguang
2009-08-01  4:53               ` Wu Fengguang
2009-08-01  4:53                 ` Wu Fengguang
2009-08-01  5:03                 ` Wu Fengguang [this message]
2009-08-01  5:03                   ` Wu Fengguang
2009-08-01  4:02         ` Wu Fengguang
2009-08-01  4:02           ` Wu Fengguang

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=20090801050354.GA16648@localhost \
    --to=fengguang.wu@intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=ctalbott@google.com \
    --cc=jens.axboe@oracle.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mbligh@google.com \
    --cc=mrubin@google.com \
    --cc=peterz@infradead.org \
    --cc=sandeen@redhat.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.