From: Jens Axboe <axboe@suse.de>
To: Andi Kleen <ak@suse.de>
Cc: Voluspa <lista1@comhem.se>,
akpm@osdl.org, Valdis.Kletnieks@vt.edu, diegocg@gmail.com,
linux-kernel@vger.kernel.org, wfg@mail.ustc.edu.cn
Subject: Re: adaptive readahead overheads
Date: Thu, 8 Jun 2006 16:00:13 +0200 [thread overview]
Message-ID: <20060608140012.GD5207@suse.de> (raw)
In-Reply-To: <p73ac8nu7a5.fsf@verdi.suse.de>
On Thu, Jun 08 2006, Andi Kleen wrote:
> Voluspa <lista1@comhem.se> writes:
>
> > On Thu, 8 Jun 2006 19:37:31 +0800 Fengguang Wu wrote:
> > > I'd like to show some numbers on the pure software overheads come with
> > > the adaptive readahead in daily operations.
> > [...]
> > >
> > > # time find /usr -type f -exec md5sum {} \; >/dev/null
> > >
> > > ARA
> > >
> > > 406.00s user 325.16s system 97% cpu 12:28.17 total
> >
> > Just out of interest, all your figures show an almost maxed out CPU.
>
> It might be because qemu has a poor IO model (old IDE) that is quite
> CPU intensive to drive.
qemu ide supports dma, so it's ok in that respect. It doesn't support
async io for the host though, so all io ends up blocking waiting for io
to complete at the host. I would not advocate using qemu for benching
these things, it's just not (yet) well suited for io testing.
--
Jens Axboe
next prev parent reply other threads:[~2006-06-08 14:00 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-05-30 3:36 Adaptive Readahead V14 - statistics question Voluspa
[not found] ` <20060530064026.GA4950@mail.ustc.edu.cn>
2006-05-30 6:40 ` Wu Fengguang
2006-05-30 16:49 ` Valdis.Kletnieks
2006-05-31 21:06 ` Diego Calleja
2006-05-31 21:50 ` Voluspa
[not found] ` <20060601055143.GA5216@mail.ustc.edu.cn>
2006-06-01 5:51 ` Fengguang Wu
2006-06-01 6:35 ` Voluspa
2006-06-08 8:04 ` Voluspa
[not found] ` <20060608113731.GA5813@mail.ustc.edu.cn>
2006-06-08 11:37 ` adaptive readahead overheads Fengguang Wu
2006-06-08 12:25 ` Voluspa
[not found] ` <20060608123900.GA6885@mail.ustc.edu.cn>
2006-06-08 12:39 ` Fengguang Wu
2006-06-08 13:05 ` Andi Kleen
2006-06-08 14:00 ` Jens Axboe [this message]
[not found] ` <448493E9.9030203@samwel.tk>
[not found] ` <20060606033436.GB6071@mail.ustc.edu.cn>
2006-06-06 3:34 ` Adaptive Readahead V14 - statistics question Wu Fengguang
[not found] <20060604073415.GB5405@mail.ustc.edu.cn>
2006-06-04 7:34 ` [PATCH] readahead: initial method - expected read size - fix fastcall Fengguang Wu
2006-06-04 9:07 ` Andrew Morton
2006-06-04 9:25 ` Arjan van de Ven
2006-06-05 1:17 ` Voluspa
2006-06-05 8:00 ` Arjan van de Ven
[not found] ` <20060606022606.GA6071@mail.ustc.edu.cn>
2006-06-06 2:26 ` Fengguang Wu
2006-06-08 7:31 ` Voluspa
[not found] ` <20060608075722.GA5515@mail.ustc.edu.cn>
2006-06-08 7:57 ` Fengguang Wu
[not found] ` <20060606025728.GA6365@mail.ustc.edu.cn>
2006-06-06 2:57 ` Fengguang Wu
2006-06-08 7:43 ` Voluspa
[not found] ` <20060608081352.GB5515@mail.ustc.edu.cn>
2006-06-08 8:13 ` Fengguang Wu
2006-06-08 8:28 ` Voluspa
[not found] ` <20060608085055.GA5917@mail.ustc.edu.cn>
2006-06-08 8:50 ` Fengguang Wu
2006-06-08 10:04 ` Voluspa
[not found] ` <20060604121328.GA6686@mail.ustc.edu.cn>
2006-06-04 12:13 ` [PATCH] readahead: call scheme - fix fastcall readahead_cache_hit() Fengguang Wu
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=20060608140012.GD5207@suse.de \
--to=axboe@suse.de \
--cc=Valdis.Kletnieks@vt.edu \
--cc=ak@suse.de \
--cc=akpm@osdl.org \
--cc=diegocg@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lista1@comhem.se \
--cc=wfg@mail.ustc.edu.cn \
/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