From: William Lee Irwin III <wli@holomorphy.com>
To: Takao Indoh <indou.takao@soft.fujitsu.com>
Cc: Mike Fedyk <mfedyk@matchmail.com>, linux-kernel@vger.kernel.org
Subject: Re: cache limit
Date: Tue, 2 Sep 2003 04:30:38 -0700 [thread overview]
Message-ID: <20030902113038.GK4306@holomorphy.com> (raw)
In-Reply-To: <23C371405B0858indou.takao@soft.fujitsu.com>
On Tue, Sep 02, 2003 at 07:52:51PM +0900, Takao Indoh wrote:
> According to this information, many I/O increase pagecache and cause
> memory shortage.
> fadvise may be effective, but fadvise always releases cache
> even if there are enough free memory, and may degrade performance.
> In the case of /proc tunable,
> pagecache is not released until system memory become lack.
[...]
> If so, limiting pagecache seems to be effective for DBMS.
There are reasons why databases use raw io and direct io; this is one
of them. I'd say the kernel shouldn't try to engage in such tunable
shenanigans.
-- wli
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
On Tue, Sep 02, 2003 at 07:52:51PM +0900, Takao Indoh wrote:
> According to this information, many I/O increase pagecache and cause
> memory shortage.
> fadvise may be effective, but fadvise always releases cache
> even if there are enough free memory, and may degrade performance.
> In the case of /proc tunable,
> pagecache is not released until system memory become lack.
[...]
> If so, limiting pagecache seems to be effective for DBMS.
There are reasons why databases use raw io and direct io; this is one
of them. I'd say the kernel shouldn't try to engage in such tunable
shenanigans.
-- wli
next prev parent reply other threads:[~2003-09-02 11:29 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-08-19 4:39 cache limit Anthony R.
2003-08-19 4:57 ` Nuno Silva
2003-08-19 5:33 ` Denis Vlasenko
2003-08-19 6:20 ` Andrew Morton
2003-08-19 9:05 ` J.A. Magallon
2003-08-19 9:16 ` Andrew Morton
2003-08-19 9:28 ` J.A. Magallon
2003-08-19 9:43 ` Andrew Morton
2003-08-19 13:32 ` Erik Andersen
2003-08-19 20:56 ` Andrew Morton
2003-08-19 14:28 ` Anthony R.
2003-08-19 18:26 ` Mike Fedyk
2003-08-19 5:42 ` Nick Piggin
2003-08-21 0:49 ` Takao Indoh
2003-08-21 23:47 ` Mike Fedyk
2003-08-25 2:45 ` Takao Indoh
2003-08-25 4:11 ` William Lee Irwin III
2003-08-25 22:58 ` Mike Fedyk
2003-08-26 9:46 ` William Lee Irwin III
2003-08-27 9:36 ` Takao Indoh
2003-08-27 9:45 ` William Lee Irwin III
2003-08-27 11:14 ` Takao Indoh
2003-08-27 11:36 ` William Lee Irwin III
2003-09-02 10:52 ` Takao Indoh
2003-09-02 11:30 ` William Lee Irwin III [this message]
2003-09-02 17:21 ` Mike Fedyk
2003-08-27 16:01 ` Joseph Malicki
[not found] <m6Bv.3ys.1@gated-at.bofh.it>
[not found] ` <mLY8.dO.5@gated-at.bofh.it>
2003-08-21 9:52 ` Ihar 'Philips' Filipau
2003-08-25 7:17 ` Takao Indoh
[not found] <n7lV.2HA.19@gated-at.bofh.it>
[not found] ` <ofAJ.4dx.9@gated-at.bofh.it>
[not found] ` <ogZM.5KJ.1@gated-at.bofh.it>
[not found] ` <oyDw.5FP.33@gated-at.bofh.it>
2003-08-26 10:15 ` Ihar 'Philips' Filipau
2003-08-26 17:46 ` Mike Fedyk
[not found] <oJ5P.699.21@gated-at.bofh.it>
[not found] ` <oJ5P.699.23@gated-at.bofh.it>
[not found] ` <oJ5P.699.25@gated-at.bofh.it>
[not found] ` <oJ5P.699.27@gated-at.bofh.it>
[not found] ` <oJ5P.699.19@gated-at.bofh.it>
[not found] ` <oQh2.4bQ.13@gated-at.bofh.it>
2003-08-26 19:08 ` Ihar 'Philips' Filipau
2003-08-26 19:23 ` Mike Fedyk
2003-08-27 10:21 ` Ihar 'Philips' Filipau
2003-08-27 11:07 ` Nick Piggin
[not found] <000801c36cb1$454d4950$1001a8c0@etofmv650>
2003-08-27 16:02 ` YoshiyaETO
-- strict thread matches above, loose matches on Subject: below --
2003-08-27 16:03 Joseph Malicki
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=20030902113038.GK4306@holomorphy.com \
--to=wli@holomorphy.com \
--cc=indou.takao@soft.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mfedyk@matchmail.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox