public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Wu Fengguang <wfg@mail.ustc.edu.cn>
To: Greg Banks <gnb@sgi.com>
Cc: linux-kernel@vger.kernel.org, Andrew Morton <akpm@osdl.org>,
	Neil Brown <neilb@cse.unsw.edu.au>
Subject: Re: [PATCH 11/12] readahead: nfsd support
Date: Sat, 17 Dec 2005 21:35:18 +0800	[thread overview]
Message-ID: <20051217133518.GA5444@mail.ustc.edu.cn> (raw)
In-Reply-To: <20051217000522.GB30278@sgi.com>

On Sat, Dec 17, 2005 at 11:05:22AM +1100, Greg Banks wrote:
> On Fri, Dec 16, 2005 at 09:07:49PM +0800, Wu Fengguang wrote:
> > ------------------------------------------------------------------------
> > Here is some test output(8 nfsd; local mount with tcp,rsize=8192):
> 
> What are the numbers when you use a more realistic rsize like 32768? 

Here they are.  The normal data are now much better, and come close to that of
the serialized ones.

NORMAL

readahead_ratio = 8, ra_max = 1024kb (old logic)
48.36s real  2.22s system  1.51s user  7209+4110 cs  diff $NFSFILE $NFSFILE2
readahead_ratio = 70, ra_max = 1024kb (new logic)
30.04s real  2.46s system  1.33s user  5420+2492 cs  diff $NFSFILE $NFSFILE2

readahead_ratio = 8, ra_max = 1024kb
92.99s real  10.32s system  3.23s user  145004+1826 cs  diff -r $NFSDIR $NFSDIR2 > /dev/null
readahead_ratio = 70, ra_max = 1024kb
90.96s real  10.68s system  3.22s user  144414+2520 cs  diff -r $NFSDIR $NFSDIR2 > /dev/null

SERIALIZED

readahead_ratio = 8, ra_max = 1024kb
47.58s real  2.10s system  1.27s user  7933+1357 cs  diff $NFSFILE $NFSFILE2
readahead_ratio = 70, ra_max = 1024kb
29.46s real  2.41s system  1.38s user  5590+2613 cs  diff $NFSFILE $NFSFILE2

readahead_ratio = 8, ra_max = 1024kb
93.02s real  10.67s system  3.25s user  144850+2286 cs  diff -r $NFSDIR $NFSDIR2 > /dev/null
readahead_ratio = 70, ra_max = 1024kb
91.15s real  11.04s system  3.31s user  144432+2814 cs  diff -r $NFSDIR $NFSDIR2 > /dev/null

Regards,
Wu

  reply	other threads:[~2005-12-17 13:11 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-12-16 13:07 [PATCH 00/12] Adaptive read-ahead V10 Wu Fengguang
2005-12-16 13:07 ` [PATCH 01/12] radixtree: look-aside cache Wu Fengguang
2005-12-16 13:07 ` [PATCH 02/12] readahead: some preparation Wu Fengguang
2005-12-16 13:07 ` [PATCH 03/12] readahead: call scheme Wu Fengguang
2005-12-16 13:07 ` [PATCH 04/12] readahead: parameters Wu Fengguang
2005-12-16 13:07 ` [PATCH 05/12] readahead: state based method Wu Fengguang
2005-12-16 13:07 ` [PATCH 06/12] readahead: context " Wu Fengguang
2005-12-16 13:07 ` [PATCH 07/12] readahead: other methods Wu Fengguang
2005-12-16 13:07 ` [PATCH 08/12] readahead: events accounting Wu Fengguang
2005-12-16 13:07 ` [PATCH 09/12] readahead: laptop mode support Wu Fengguang
2005-12-16 13:07 ` [PATCH 10/12] readahead: disable look-ahead for loopback file Wu Fengguang
2005-12-16 13:07 ` [PATCH 11/12] readahead: nfsd support Wu Fengguang
2005-12-17  0:05   ` Greg Banks
2005-12-17 13:35     ` Wu Fengguang [this message]
2005-12-16 13:07 ` [PATCH 12/12] readahead: improve interactivity 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=20051217133518.GA5444@mail.ustc.edu.cn \
    --to=wfg@mail.ustc.edu.cn \
    --cc=akpm@osdl.org \
    --cc=gnb@sgi.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=neilb@cse.unsw.edu.au \
    /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