From: Andi Kleen <ak@suse.de>
To: "Leonid Grossman" <leonid.grossman@s2io.com>
Cc: hadi@cyberus.ca, netdev@oss.sgi.com
Subject: Re: FW: Submission for S2io 10GbE driver
Date: Sat, 24 Jan 2004 15:58:09 +0100 [thread overview]
Message-ID: <20040124155809.15fe167e.ak@suse.de> (raw)
In-Reply-To: <000001c3e238$62efbb30$0400a8c0@S2IOtech.com>
On Fri, 23 Jan 2004 21:10:28 -0800
"Leonid Grossman" <leonid.grossman@s2io.com> wrote:
> In Linux, there are couple performance issues that we see
> - transmit performance is noticeably worse than in Windows
In Linux 2.6 with TSO?
Other than that I would suggest to enable oprofile on 2.6 and post
the profile numbers on the list.
> - checksum in 2.4 seems to be calculated by the host even if the device
> enables checksum offload
You have to use sendfile() for TX checksum off load. Without that the
data needs to be copied anyways and a copy+csum is about the same cost
as a simple copy.
> - Large Send Offload in 2.6 (no LSO in 2.4) give much smaller boost
> comparing to Windows; on some systems there is no gain from LSO at all.
You mean TSO? Are you sure the test programs submitted big enough
buffers to the TCP stack?
-Andi
next prev parent reply other threads:[~2004-01-24 14:58 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-01-23 21:22 FW: Submission for S2io 10GbE driver Leonid Grossman
2004-01-23 21:54 ` Stephen Hemminger
2004-01-23 21:58 ` Leonid Grossman
2004-01-23 22:22 ` FW: " Andi Kleen
2004-01-24 0:21 ` Stephen Hemminger
2004-01-27 5:32 ` Leonid Grossman
2004-01-27 6:08 ` Jeff Garzik
2004-01-27 6:19 ` Leonid Grossman
2004-02-04 20:44 ` FW: " Leonid Grossman
2004-02-05 0:49 ` Grant Grundler
2004-02-05 1:14 ` Leonid Grossman
2004-02-16 21:16 ` Leonid Grossman
2004-02-16 22:12 ` Jeff Garzik
2004-02-16 23:53 ` Leonid Grossman
2004-02-17 0:11 ` Christoph Hellwig
2004-02-17 0:16 ` Stephen Hemminger
2004-02-28 15:08 ` Submission #3 " Leonid Grossman
2004-02-28 20:21 ` Jeff Garzik
2004-03-12 21:55 ` ravinandan arakali
2004-03-13 2:30 ` Jeff Garzik
2004-03-20 4:35 ` Submission #4 " Leonid Grossman
2004-03-20 9:56 ` Jeff Garzik
2004-03-20 10:00 ` Jeff Garzik
2004-03-22 19:36 ` ravinandan arakali
2004-03-22 19:43 ` Jeff Garzik
2004-03-20 10:48 ` Christoph Hellwig
2004-02-05 1:32 ` FW: Submission " Andi Kleen
2004-02-05 1:51 ` Anton Blanchard
2004-02-05 2:46 ` Leonid Grossman
2004-02-05 3:25 ` Anton Blanchard
2004-02-05 9:27 ` Jeff Garzik
2004-02-05 9:29 ` Jeff Garzik
2004-02-05 22:09 ` Leonid Grossman
2004-02-05 22:34 ` Grant Grundler
2004-02-05 23:23 ` Jes Sorensen
2004-01-24 0:38 ` Francois Romieu
2004-01-24 3:14 ` jamal
2004-01-24 5:10 ` Leonid Grossman
2004-01-24 14:58 ` Andi Kleen [this message]
2004-01-24 17:54 ` jamal
2004-01-24 19:52 ` Leonid Grossman
2004-01-25 19:07 ` jamal
2004-01-25 17:56 ` Leonid Grossman
2004-01-24 18:00 ` jamal
2004-01-24 20:04 ` Leonid Grossman
2004-01-25 19:14 ` jamal
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=20040124155809.15fe167e.ak@suse.de \
--to=ak@suse.de \
--cc=hadi@cyberus.ca \
--cc=leonid.grossman@s2io.com \
--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 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.