From: Dave Chinner <david@fromorbit.com>
To: Taras Glek <tglek@mozilla.com>
Cc: linux-kernel@vger.kernel.org
Subject: Re: Downsides to madvise/fadvise(willneed) for application startup
Date: Tue, 6 Apr 2010 09:17:46 +1000 [thread overview]
Message-ID: <20100405231746.GB3335@dastard> (raw)
In-Reply-To: <4BBA6776.5060804@mozilla.com>
On Mon, Apr 05, 2010 at 03:43:02PM -0700, Taras Glek wrote:
> Hello,
> I am working on improving Mozilla startup times. It turns out that
> page faults(caused by lack of cooperation between user/kernelspace)
> are the main cause of slow startup. I need some insights from
> someone who understands linux vm behavior.
>
> Current Situation:
> The dynamic linker mmap()s executable and data sections of our
> executable but it doesn't call madvise().
> By default page faults trigger 131072byte reads. To make matters
Try tuning /sys/block/<dev>/queue/read_ahead_kb and see if that
makes any difference - that's the default maximum readahead for the
given block device and defaults to 128k.
There has been some recent work to increase the default readahead
size, so if changing the default improves performance then perhaps
a fix for your problem is already in the works?
Cheers,
Dave.
--
Dave Chinner
david@fromorbit.com
next prev parent reply other threads:[~2010-04-05 23:18 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-04-05 22:43 Downsides to madvise/fadvise(willneed) for application startup Taras Glek
2010-04-05 23:17 ` Dave Chinner [this message]
2010-04-05 23:52 ` Roland Dreier
2010-04-06 22:09 ` Taras Glek
2010-04-06 9:51 ` Johannes Weiner
2010-04-06 9:51 ` Johannes Weiner
2010-04-06 21:57 ` Taras Glek
2010-04-06 21:57 ` Taras Glek
2010-04-06 22:26 ` Johannes Weiner
2010-04-06 22:26 ` Johannes Weiner
2010-04-06 22:39 ` Taras Glek
2010-04-06 22:39 ` Taras Glek
2010-04-07 2:24 ` Wu Fengguang
2010-04-07 2:24 ` Wu Fengguang
2010-04-07 2:54 ` Taras Glek
2010-04-07 2:54 ` Taras Glek
2010-04-07 4:06 ` Minchan Kim
2010-04-07 4:06 ` Minchan Kim
2010-04-07 7:14 ` Wu Fengguang
2010-04-07 7:14 ` Wu Fengguang
2010-04-07 7:33 ` Minchan Kim
2010-04-07 7:33 ` Minchan Kim
2010-04-07 7:47 ` Wu Fengguang
2010-04-07 7:47 ` Wu Fengguang
2010-04-07 8:06 ` Minchan Kim
2010-04-07 8:06 ` Minchan Kim
2010-04-07 8:13 ` Wu Fengguang
2010-04-07 8:13 ` Wu Fengguang
2010-04-07 7:38 ` Wu Fengguang
2010-04-07 7:38 ` Wu Fengguang
2010-04-08 17:44 ` Taras Glek
2010-04-08 17:44 ` Taras Glek
2010-04-12 2:27 ` Wu Fengguang
2010-04-12 2:27 ` Wu Fengguang
2010-04-12 3:25 ` Minchan Kim
2010-04-12 3:25 ` Minchan Kim
2010-04-12 4:58 ` Wu Fengguang
2010-04-12 4:58 ` Wu Fengguang
2010-04-12 4:43 ` drepper
2010-04-12 4:46 ` Taras Glek
2010-04-12 4:46 ` Taras Glek
2010-04-12 4:50 ` Wu Fengguang
2010-04-12 4:50 ` Wu Fengguang
2010-04-12 8:50 ` Andi Kleen
2010-04-15 22:53 ` Andrew Morton
2010-04-15 23:21 ` Zan Lynx
2010-04-15 20:42 ` Andrew Morton
2010-04-16 11:41 ` Andi Kleen
2010-04-16 12:23 ` Theodore Tso
2010-04-16 12:23 ` Theodore Tso
2010-04-16 0:41 ` Taras Glek
2010-04-15 22:21 ` Andrew Morton
2010-04-16 2:37 ` Taras Glek
2010-04-16 11:40 ` Andi Kleen
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=20100405231746.GB3335@dastard \
--to=david@fromorbit.com \
--cc=linux-kernel@vger.kernel.org \
--cc=tglek@mozilla.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.