From: "David Schwartz" <davids@webmaster.com>
To: "David Stevens" <dlstevens@us.ibm.com>,
"Netdev" <netdev@oss.sgi.com>,
leonid.grossman@s2io.com,
"Linux Kernel" <linux-kernel@vger.kernel.org>
Subject: Re: The ultimate TOE design
Date: Wed, 15 Sep 2004 13:16:36 -0700 [thread overview]
Message-ID: <WorldClient-F200409151316.AA16360002@webmaster.com> (raw)
In-Reply-To: <OF8783A4F6.D566336C-ON88256F10.006E51CE-88256F10.006EDA93@us.ibm.com>
David Stevens wrote:
> I've never understood why people are so interested in off-loading
> networking. Isn't that just a multi-processor system where you can't
> use any of the network processor cycles for anything else? And, of
> course, to be cheap, the network processor will be slower, and much
> harder to debug and update software.
The issues of debugging the network processor software and maintaining it is
certainly a legitimate one. However, nothing stops you from using the extra
network processor cycles for other purposes.
> If the PCI bus is too slow, or MTU's too small, wouldn't
> it be better to fix those directly and use a fast host processor that
> can
> also do other things when not needed for networking? And why have
> memory on a NIC that can't be used by other things?
This isn't an either-or. Processors are cheap. Memory is cheap.
> Why don't we off-load filesystems to disks instead? Or a graphics
> card that implements X ? :-) I'd rather have shared system resources--
> more flexible. :-)
It's not one or the other. If, for example, your network card, graphics
card, and hard drive controller all use a common instruction set and are all
interconnected by a fast bus, code can be fairly mobile and run wherever
it's the most efficient. Nothing stops the OS from offloading internal tasks
to these processors as well.
The only real stumbling blocks have been cost/volume considerations and the
fact that the central processor(s) can be so fast, and the I/O so slow in
comparison, that there's not much to gain.
DS
next prev parent reply other threads:[~2004-09-15 20:16 UTC|newest]
Thread overview: 69+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-09-15 19:33 The ultimate TOE design Jeff Garzik
2004-09-15 20:04 ` Paul Jakma
2004-09-15 19:14 ` Alan Cox
2004-09-15 20:41 ` Jeff Garzik
2004-09-15 21:01 ` David S. Miller
2004-09-15 21:08 ` Jeff Garzik
2004-09-15 21:13 ` David S. Miller
2004-09-15 21:23 ` Jeff Garzik
2004-09-15 21:29 ` David S. Miller
2004-09-15 22:26 ` Jeff Garzik
2004-09-15 23:29 ` Leonid Grossman
2004-09-24 13:07 ` Lennert Buytenhek
2004-09-24 13:21 ` Leonid Grossman
2004-09-24 18:09 ` Lennert Buytenhek
2004-09-24 19:39 ` Joel Jaeggli
2004-09-16 0:57 ` jamal
2004-09-16 5:25 ` Leonid Grossman
2004-09-16 9:29 ` Lincoln Dale
2004-09-16 12:19 ` Alan Cox
2004-09-16 13:33 ` Andi Kleen
2004-09-16 12:57 ` Alan Cox
2004-09-16 22:37 ` Lincoln Dale
2004-09-17 13:38 ` Jörn Engel
2004-09-15 22:31 ` Jeff Garzik
2004-09-15 21:15 ` Michael Richardson
2004-09-15 20:53 ` David S. Miller
2004-09-16 1:05 ` Andrea Arcangeli
2004-09-15 21:10 ` David Lang
2004-09-15 23:05 ` Paul Jakma
2004-09-15 20:26 ` Neil Horman
2004-09-15 21:03 ` Wes Felter
2004-09-15 21:15 ` Jeff Garzik
2004-09-15 21:35 ` Wes Felter
2004-09-15 21:42 ` Jeff Garzik
2004-09-15 21:25 ` Imran Badr
2004-09-16 11:37 ` Neil Horman
2004-09-16 5:51 ` Matt Porter
2004-09-15 21:36 ` Deepak Saxena
2004-09-15 23:03 ` Paul Jakma
2004-09-24 13:11 ` Lennert Buytenhek
2004-09-15 21:59 ` Tony Lee
2004-09-15 20:11 ` David Stevens
2004-09-15 20:16 ` David Schwartz [this message]
2004-09-15 20:25 ` Jeff Garzik
2004-09-15 20:54 ` Neil Horman
2004-09-15 20:31 ` Bill Rugolsky Jr.
2004-09-15 21:41 ` Joel Jaeggli
2004-09-16 6:33 ` Valdis.Kletnieks
2004-09-17 6:46 ` Eric Mudama
2004-09-17 14:15 ` Alan Cox
2004-09-17 20:27 ` Valdis.Kletnieks
2004-09-17 20:36 ` David Lang
2004-09-17 23:20 ` Tony Lee
2004-09-17 23:36 ` Leonid Grossman
2004-09-22 23:25 ` Eric Mudama
2004-09-15 21:36 ` John Heffner
2004-09-15 21:46 ` David S. Miller
2004-09-16 6:20 ` Andi Kleen
2004-09-16 13:10 ` Leonid Grossman
2004-09-16 16:18 ` Nivedita Singhvi
2004-09-16 20:34 ` Leonid Grossman
2004-09-22 20:18 ` Nivedita Singhvi
2004-09-23 4:46 ` Leonid Grossman
2004-09-15 23:16 ` James Morris
2004-09-15 23:37 ` Leonid Grossman
2004-09-15 23:52 ` John Heffner
2004-09-16 1:43 ` James Morris
2004-09-16 9:03 ` Lars Marowsky-Bree
[not found] <1095328673.1063.130.camel@jzny.localdomain>
2004-09-16 14:57 ` Leonid Grossman
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=WorldClient-F200409151316.AA16360002@webmaster.com \
--to=davids@webmaster.com \
--cc=dlstevens@us.ibm.com \
--cc=leonid.grossman@s2io.com \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@oss.sgi.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;
as well as URLs for NNTP newsgroup(s).