From: David Chinner <dgc@sgi.com>
To: Mikulas Patocka <mikulas@artax.karlin.mff.cuni.cz>
Cc: Albert Cahalan <acahalan@gmail.com>, linux-kernel@vger.kernel.org
Subject: Re: 2048 CPUs [was: Re: New filesystem for Linux]
Date: Wed, 8 Nov 2006 14:04:29 +1100 [thread overview]
Message-ID: <20061108030429.GQ11034@melbourne.sgi.com> (raw)
In-Reply-To: <Pine.LNX.4.64.0611042332240.20974@artax.karlin.mff.cuni.cz>
On Sat, Nov 04, 2006 at 11:36:49PM +0100, Mikulas Patocka wrote:
> >>Does one Linux kernel run on system with 1024 cpus? I guess it
> >>must fry spinlocks... (or even lockup due to spinlock livelocks)
> >
> >The SGI Altix can have 2048 CPUs.
>
> And does it run one image of Linux? Or more images each on few cpus?
One image.
> How do they solve problem with spinlock livelocks?
By replacing contended spinlocks withsleeping locks, using no-lock
techniques (e.g. per-cpu) or changing the algorithm to remove the
contention point.
w.r.t filesystem locking scalability, you should read this paper:
http://oss.sgi.com/projects/xfs/papers/ols2006/ols-2006-paper.pdf
Cheers,
Dave.
--
Dave Chinner
Principal Engineer
SGI Australian Software Group
prev parent reply other threads:[~2006-11-08 3:04 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <787b0d920611041154l69db46abv4c8c467809ada57c@mail.gmail.com>
2006-11-04 22:36 ` 2048 CPUs [was: Re: New filesystem for Linux] Mikulas Patocka
[not found] ` <787b0d920611050802o460a4000r5ce154e589732a02@mail.gmail.com>
2006-11-06 1:47 ` Mikulas Patocka
2006-11-07 21:26 ` Pavel Machek
2006-11-07 22:36 ` Mikulas Patocka
2006-11-07 23:14 ` Pavel Machek
2006-11-08 18:26 ` Mikulas Patocka
2006-11-10 9:03 ` Pavel Machek
2006-11-10 15:20 ` Mikulas Patocka
2006-11-10 16:20 ` Alan Cox
2006-11-12 14:28 ` Pavel Machek
2006-11-12 20:07 ` Mikulas Patocka
2006-11-14 6:24 ` Albert Cahalan
2006-11-08 3:04 ` David Chinner [this message]
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=20061108030429.GQ11034@melbourne.sgi.com \
--to=dgc@sgi.com \
--cc=acahalan@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mikulas@artax.karlin.mff.cuni.cz \
/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.