From: ebiederm@xmission.com (Eric W. Biederman)
To: Nadia Derbey <Nadia.Derbey@bull.net>
Cc: Andrew Morton <akpm@osdl.org>, linux-kernel@vger.kernel.org
Subject: Re: [RFC][PATCH 6/6] automatic tuning applied to some kernel components
Date: Wed, 07 Feb 2007 14:18:57 -0700 [thread overview]
Message-ID: <m1mz3poeda.fsf@ebiederm.dsl.xmission.com> (raw)
In-Reply-To: <45B61E50.6020607@bull.net> (Nadia Derbey's message of "Tue, 23 Jan 2007 15:40:16 +0100")
Nadia Derbey <Nadia.Derbey@bull.net> writes:
>
> 2) why autotuning:
> There are at least 3 cases where it can be useful
> . for workloads that are known to need a big amount of a given resource type
> (say shared memories), but we don't know what the maximum amount needed will be
> . to solve the case of multiple applications running on a single system, and
> that need the same tunable to be adjusted to feet their needs
> . to make a system correctly react to eventual peak loads for a given resource
> usage, i.e. make it tune up *and down* as needed.
>
> In all these cases, the akt framework will enable the kernel to adapt to
> increasing / decreasing resource consumption:
> 1) avoid allocating "a priori" a big amount of memory that will be used only in
> extreme cases. This is the effect of doing an "echo <huge_value>
>> /proc/sys/kernel/shmmni"
>
> 2) the system will come back to the default values as soon as the peak load is
> over.
At least the ipc ones are supposed to be DOS limits not behavior
modifiers. I do admit from looking at the code that there are some
consequences of increasing things like shmmni. However I think we
would be better off with better data structures and implementations
that remove these consequences than this autotuning of
denial-of-service limits.
i.e. I think you are treating the symptom not the problem.
Does this make sense?
Eric
next prev parent reply other threads:[~2007-02-07 21:19 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-01-16 6:15 [RFC][PATCH 0/6] Automatice kernel tunables (AKT) Nadia.Derbey
2007-01-16 6:15 ` [RFC][PATCH 1/6] Tunable structure and registration routines Nadia.Derbey
2007-01-25 0:32 ` Randy Dunlap
2007-01-25 16:26 ` Nadia Derbey
2007-01-25 16:34 ` Randy Dunlap
2007-01-25 17:01 ` Nadia Derbey
2007-01-16 6:15 ` [RFC][PATCH 2/6] auto_tuning activation Nadia.Derbey
2007-01-16 6:15 ` [RFC][PATCH 3/6] tunables associated kobjects Nadia.Derbey
2007-01-16 6:15 ` [RFC][PATCH 4/6] min and max kobjects Nadia.Derbey
2007-01-24 22:41 ` Randy Dunlap
2007-01-25 16:34 ` Nadia Derbey
2007-01-16 6:15 ` [RFC][PATCH 5/6] per namespace tunables Nadia.Derbey
2007-01-24 22:41 ` Randy Dunlap
2007-01-16 6:15 ` [RFC][PATCH 6/6] automatic tuning applied to some kernel components Nadia.Derbey
2007-01-22 19:56 ` Andrew Morton
2007-01-23 14:40 ` Nadia Derbey
2007-02-07 21:18 ` Eric W. Biederman [this message]
2007-02-09 12:27 ` Nadia Derbey
2007-02-09 18:35 ` Eric W. Biederman
2007-02-13 9:06 ` Nadia Derbey
2007-02-13 10:10 ` Eric W. Biederman
2007-02-15 7:07 ` Nadia Derbey
2007-02-15 7:49 ` Eric W. Biederman
2007-02-15 8:25 ` Nadia Derbey
2007-02-14 13:56 Al Boldi
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=m1mz3poeda.fsf@ebiederm.dsl.xmission.com \
--to=ebiederm@xmission.com \
--cc=Nadia.Derbey@bull.net \
--cc=akpm@osdl.org \
--cc=linux-kernel@vger.kernel.org \
/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;
as well as URLs for NNTP newsgroup(s).