From: Eric Wong <normalperson@yhbt.net>
To: Phillip Susi <psusi@ubuntu.com>
Cc: Dave Chinner <david@fromorbit.com>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH] fadvise: perform WILLNEED readahead in a workqueue
Date: Fri, 22 Feb 2013 21:13:08 +0000 [thread overview]
Message-ID: <20130222211308.GA13037@dcvr.yhbt.net> (raw)
In-Reply-To: <5127A0A3.6040904@ubuntu.com>
Phillip Susi <psusi@ubuntu.com> wrote:
> > On Sat, Dec 15, 2012 at 12:54:48AM +0000, Eric Wong wrote:
> >> "strace -T" timing on an uncached, one gigabyte file:
> >>
> >> Before: fadvise64(3, 0, 0, POSIX_FADV_WILLNEED) = 0 <2.484832>
> >> After: fadvise64(3, 0, 0, POSIX_FADV_WILLNEED) = 0 <0.000061>
>
> It shouldn't take 2 seconds to queue up some async reads. Are you
> using ext3? The blocks have to be mapped in order to queue the reads,
> and without ext4 extents, this means the indirect blocks have to be
> read and can cause fadvise to block.
You're right, I originally tested on ext3.
I just tested an unpatched 3.7.9 kernel with ext4 and is much faster
(~250ms). I consider ~250ms acceptable for my needs. Will migrate
the rest of my setup to ext4 soon, thanks for the tip!
--
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>
WARNING: multiple messages have this Message-ID (diff)
From: Eric Wong <normalperson@yhbt.net>
To: Phillip Susi <psusi@ubuntu.com>
Cc: Dave Chinner <david@fromorbit.com>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH] fadvise: perform WILLNEED readahead in a workqueue
Date: Fri, 22 Feb 2013 21:13:08 +0000 [thread overview]
Message-ID: <20130222211308.GA13037@dcvr.yhbt.net> (raw)
In-Reply-To: <5127A0A3.6040904@ubuntu.com>
Phillip Susi <psusi@ubuntu.com> wrote:
> > On Sat, Dec 15, 2012 at 12:54:48AM +0000, Eric Wong wrote:
> >> "strace -T" timing on an uncached, one gigabyte file:
> >>
> >> Before: fadvise64(3, 0, 0, POSIX_FADV_WILLNEED) = 0 <2.484832>
> >> After: fadvise64(3, 0, 0, POSIX_FADV_WILLNEED) = 0 <0.000061>
>
> It shouldn't take 2 seconds to queue up some async reads. Are you
> using ext3? The blocks have to be mapped in order to queue the reads,
> and without ext4 extents, this means the indirect blocks have to be
> read and can cause fadvise to block.
You're right, I originally tested on ext3.
I just tested an unpatched 3.7.9 kernel with ext4 and is much faster
(~250ms). I consider ~250ms acceptable for my needs. Will migrate
the rest of my setup to ext4 soon, thanks for the tip!
next prev parent reply other threads:[~2013-02-22 21:13 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-12-15 0:54 [PATCH] fadvise: perform WILLNEED readahead in a workqueue Eric Wong
2012-12-15 0:54 ` Eric Wong
2012-12-15 22:34 ` Alan Cox
2012-12-15 22:34 ` Alan Cox
2012-12-16 0:25 ` Eric Wong
2012-12-16 0:25 ` Eric Wong
2012-12-16 3:03 ` Dave Chinner
2012-12-16 3:03 ` Dave Chinner
2012-12-16 3:35 ` Eric Wong
2012-12-16 3:35 ` Eric Wong
2012-12-16 4:15 ` Dave Chinner
2012-12-16 4:15 ` Dave Chinner
2012-12-16 5:23 ` Eric Wong
2012-12-16 5:23 ` Eric Wong
2012-12-16 21:31 ` Dave Chinner
2012-12-16 21:31 ` Dave Chinner
2012-12-16 8:48 ` Zheng Liu
2012-12-16 8:48 ` Zheng Liu
2012-12-16 2:45 ` Dave Chinner
2012-12-16 2:45 ` Dave Chinner
2012-12-16 3:04 ` Eric Wong
2012-12-16 3:04 ` Eric Wong
2012-12-16 3:09 ` Eric Wong
2012-12-16 3:09 ` Eric Wong
2012-12-16 3:36 ` Dave Chinner
2012-12-16 3:36 ` Dave Chinner
2012-12-16 3:59 ` Eric Wong
2012-12-16 3:59 ` Eric Wong
2012-12-16 4:26 ` Dave Chinner
2012-12-16 4:26 ` Dave Chinner
2012-12-16 5:17 ` Eric Wong
2012-12-16 5:17 ` Eric Wong
2013-02-22 16:45 ` Phillip Susi
2013-02-22 16:45 ` Phillip Susi
2013-02-22 21:13 ` Eric Wong [this message]
2013-02-22 21:13 ` Eric Wong
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=20130222211308.GA13037@dcvr.yhbt.net \
--to=normalperson@yhbt.net \
--cc=david@fromorbit.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=psusi@ubuntu.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.