From: Stephen Frost <sfrost@snowman.net>
To: Ingo Molnar <mingo@elte.hu>
Cc: "Stephen C. Tweedie" <sct@redhat.com>,
Rik van Riel <riel@conectiva.com.br>,
"David S. Miller" <davem@redhat.com>,
hch@caldera.de, netdev@oss.sgi.com, linux-kernel@vger.kernel.org
Subject: Re: [PLEASE-TESTME] Zerocopy networking patch, 2.4.0-1
Date: Tue, 9 Jan 2001 10:25:25 -0500 [thread overview]
Message-ID: <20010109102525.Q26953@ns> (raw)
In-Reply-To: <20010109141806.F4284@redhat.com> <Pine.LNX.4.30.0101091532150.4368-100000@e2>
In-Reply-To: <Pine.LNX.4.30.0101091532150.4368-100000@e2>; from mingo@elte.hu on Tue, Jan 09, 2001 at 03:40:56PM +0100
[-- Attachment #1: Type: text/plain, Size: 2153 bytes --]
* Ingo Molnar (mingo@elte.hu) wrote:
>
> On Tue, 9 Jan 2001, Stephen C. Tweedie wrote:
>
> > but it just doesn't apply when you look at some other applications,
> > such as streaming out video data or performing fileserving in a
> > high-performance compute cluster where you are serving bulk data.
> > The multimedia and HPC worlds typically operate on datasets which are
> > far too large to cache, so you want to keep them in memory as little
> > as possible when you ship them over the wire.
>
> i'd love to first see these kinds of applications (under Linux) before
> designing for them. Eg. if an IO operation (eg. streaming video webcast)
> does a DMA from a camera card to an outgoing networking card, would it be
> possible to access the packet data in case of a TCP retransmit? Basically
> these applications are limited enough in scope to justify even temporary
> 'hacks' that enable them - and once we *see* things in action, we could
> design for them. Not the other way around.
Well, I know I for one use a system that you might have heard
of called 'MOSIX'. It's a (kinda large) kernel patch with some user-space
tools but allows for migration of processes between machines without
modifying any code. There are some limitations (threaded applications and
shared memory and whatnot) but it works very well for the rendering work
we use it for. We use radiance which in general has pretty little inter-
process communication and what it has is done through the filesystem.
Now, the interesting bit here is that the processes can grow to be
pretty large (200M+, up as high as 500M, higher if we let it ;) ) and what
happens with MOSIX is that entire processes get sent over the wire to
other machines for work. MOSIX will also attempt to rebalance the load on
all of the machines in the cluster and whatnot so it can often be moving
processes back and forth.
So, anyhow, this is just an fyi if you weren't aware of it that I
believe more than a few people are using MOSIX these days for similar
appliactions and that it's availible at http://www.mosix.org if you're
curious.
Stephen
[-- Attachment #2: Type: application/pgp-signature, Size: 232 bytes --]
next prev parent reply other threads:[~2001-01-09 15:26 UTC|newest]
Thread overview: 119+ messages / expand[flat|nested] mbox.gz Atom feed top
2001-01-08 1:24 [PLEASE-TESTME] Zerocopy networking patch, 2.4.0-1 David S. Miller
2001-01-08 10:39 ` Christoph Hellwig
2001-01-08 10:34 ` David S. Miller
2001-01-08 18:05 ` Rik van Riel
2001-01-08 21:07 ` David S. Miller
2001-01-09 10:23 ` Ingo Molnar
2001-01-09 10:31 ` Christoph Hellwig
2001-01-09 10:31 ` David S. Miller
2001-01-09 11:28 ` Christoph Hellwig
2001-01-09 11:42 ` David S. Miller
2001-01-09 12:04 ` Ingo Molnar
2001-01-09 14:25 ` Stephen C. Tweedie
2001-01-09 14:33 ` Alan Cox
2001-01-09 15:00 ` Ingo Molnar
2001-01-09 15:27 ` Stephen C. Tweedie
2001-01-09 16:16 ` Ingo Molnar
2001-01-09 16:37 ` Alan Cox
2001-01-09 16:48 ` Ingo Molnar
2001-01-09 17:29 ` Alan Cox
2001-01-09 17:38 ` Jens Axboe
2001-01-09 18:38 ` Ingo Molnar
2001-01-09 19:54 ` Andrea Arcangeli
2001-01-09 20:10 ` Ingo Molnar
2001-01-10 0:00 ` Andrea Arcangeli
2001-01-09 20:12 ` Jens Axboe
2001-01-09 23:20 ` Andrea Arcangeli
2001-01-09 23:34 ` Jens Axboe
2001-01-09 23:52 ` Andrea Arcangeli
2001-01-17 5:16 ` Rik van Riel
2001-01-09 17:56 ` Chris Evans
2001-01-09 18:41 ` Ingo Molnar
2001-01-09 22:58 ` [patch]: ac4 blk (was Re: [PLEASE-TESTME] Zerocopy networking patch, 2.4.0-1) Jens Axboe
2001-01-09 19:20 ` [PLEASE-TESTME] Zerocopy networking patch, 2.4.0-1 J Sloan
2001-01-09 18:10 ` Stephen C. Tweedie
2001-01-09 15:38 ` Benjamin C.R. LaHaise
2001-01-09 16:40 ` Ingo Molnar
2001-01-09 17:30 ` Benjamin C.R. LaHaise
2001-01-09 18:12 ` Stephen C. Tweedie
2001-01-09 18:35 ` Ingo Molnar
2001-01-09 17:53 ` Christoph Hellwig
2001-01-09 21:13 ` David S. Miller
2001-01-09 19:14 ` Linus Torvalds
2001-01-09 20:07 ` Ingo Molnar
2001-01-09 20:15 ` Linus Torvalds
2001-01-09 20:36 ` Christoph Hellwig
2001-01-09 20:55 ` Linus Torvalds
2001-01-09 21:12 ` Christoph Hellwig
2001-01-09 21:26 ` Linus Torvalds
2001-01-10 7:42 ` Christoph Hellwig
2001-01-10 8:05 ` Linus Torvalds
2001-01-10 8:33 ` Christoph Hellwig
2001-01-10 8:37 ` Andrew Morton
2001-01-10 23:32 ` Linus Torvalds
2001-01-19 15:55 ` Andrew Scott
2001-01-17 14:05 ` Rik van Riel
2001-01-18 0:53 ` Christoph Hellwig
2001-01-18 1:13 ` Linus Torvalds
2001-01-18 17:50 ` Christoph Hellwig
2001-01-18 18:04 ` Linus Torvalds
2001-01-18 21:12 ` Albert D. Cahalan
2001-01-19 1:52 ` 2.4.1-pre8 video/ohci1394 compile problem ebi4
2001-01-19 6:55 ` [PLEASE-TESTME] Zerocopy networking patch, 2.4.0-1 Linus Torvalds
2001-01-09 23:06 ` Benjamin C.R. LaHaise
2001-01-09 23:54 ` Linus Torvalds
2001-01-10 7:51 ` Gerd Knorr
2001-01-12 1:42 ` Stephen C. Tweedie
2001-01-09 11:05 ` Ingo Molnar
2001-01-09 18:27 ` Christoph Hellwig
2001-01-09 19:19 ` Ingo Molnar
2001-01-09 14:18 ` Stephen C. Tweedie
2001-01-09 14:40 ` Ingo Molnar
2001-01-09 14:51 ` Alan Cox
2001-01-09 15:17 ` Stephen C. Tweedie
2001-01-09 15:37 ` Ingo Molnar
2001-01-09 21:18 ` David S. Miller
2001-01-09 22:25 ` Linus Torvalds
2001-01-10 15:21 ` Stephen C. Tweedie
2001-01-09 15:25 ` Stephen Frost [this message]
2001-01-09 15:40 ` Ingo Molnar
2001-01-09 15:48 ` Stephen Frost
2001-01-10 1:14 ` Dave Zarzycki
2001-01-10 1:14 ` David S. Miller
2001-01-10 2:18 ` Dave Zarzycki
2001-01-10 1:19 ` Ingo Molnar
2001-01-10 2:56 ` storage over IP (was Re: [PLEASE-TESTME] Zerocopy networking patch, 2.4.0-1) dean gaudet
2001-01-10 2:58 ` David S. Miller
2001-01-10 3:18 ` dean gaudet
2001-01-10 3:09 ` David S. Miller
2001-01-10 3:05 ` storage over IP (was Re: [PLEASE-TESTME] Zerocopy networking patch, Alan Cox
2001-01-08 21:56 ` [PLEASE-TESTME] Zerocopy networking patch, 2.4.0-1 Jes Sorensen
2001-01-08 21:48 ` David S. Miller
2001-01-08 22:32 ` Jes Sorensen
2001-01-08 22:36 ` David S. Miller
2001-01-09 12:12 ` Ingo Molnar
2001-01-08 22:43 ` Stephen Frost
2001-01-08 22:37 ` David S. Miller
2001-01-09 13:52 ` Trond Myklebust
2001-01-09 13:42 ` David S. Miller
2001-01-09 15:27 ` Trond Myklebust
2001-01-09 21:19 ` David S. Miller
2001-01-10 9:21 ` Trond Myklebust
-- strict thread matches above, loose matches on Subject: below --
2001-01-09 13:08 Stephen Landamore
2001-01-09 13:24 ` Ingo Molnar
2001-01-09 13:47 ` Andrew Morton
2001-01-09 19:15 ` Dan Hollis
2001-01-09 19:14 ` Dan Hollis
2001-01-09 22:03 ` David S. Miller
2001-01-09 22:58 ` Dan Hollis
2001-01-09 22:59 ` Ingo Molnar
2001-01-09 23:11 ` Dan Hollis
2001-01-10 3:24 ` Chris Wedgwood
2001-01-09 17:46 Manfred Spraul
2001-01-10 8:41 Manfred Spraul
2001-01-10 8:31 ` David S. Miller
2001-01-10 11:25 ` Ingo Molnar
2001-01-10 12:03 ` Manfred Spraul
2001-01-10 12:07 ` Ingo Molnar
2001-01-10 16:18 ` Jamie Lokier
2001-01-13 15:43 ` yodaiken
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=20010109102525.Q26953@ns \
--to=sfrost@snowman.net \
--cc=davem@redhat.com \
--cc=hch@caldera.de \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=netdev@oss.sgi.com \
--cc=riel@conectiva.com.br \
--cc=sct@redhat.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