From: jamal <hadi@cyberus.ca>
To: netdev@vger.kernel.org
Cc: Krishna Kumar2 <krkumar2@in.ibm.com>,
Evgeniy Polyakov <johnpol@2ka.mipt.ru>,
Gagan Arneja <gaagaan@gmail.com>,
Sridhar Samudrala <sri@us.ibm.com>,
Rick Jones <rick.jones2@hp.com>
Subject: [WIP][PATCHES] Network xmit batching
Date: Wed, 06 Jun 2007 09:49:21 -0400 [thread overview]
Message-ID: <1181137761.4068.22.camel@localhost> (raw)
[-- Attachment #1: Type: text/plain, Size: 2180 bytes --]
Folks,
While Krishna and I have been attempting this on the side, progress has
been rather slow - so this is to solicit for more participation so we
can get this over with faster. Success (myself being conservative when
it comes to performance) requires testing on a wide variety of hardware.
The results look promising - certainly from a pktgen perspective where
performance has been known in some cases to go up over 50%.
Tests by Sridhar on a low number of TCP flows also indicate improved
performance as well as lowered CPU use.
I have setup the current state of my patches against Linus tree at:
git://git.kernel.org/pub/scm/linux/kernel/git/hadi/batch-lin26.git
This is also clean against 2.6.22-rc4. So if you want just a diff that
will work against 2.6.22-rc4 - i can send it to you.
I also have a tree against Daves net-2.6 at
git://git.kernel.org/pub/scm/linux/kernel/git/hadi/batch-net26.git
but iam abandoning that effort until we get this stable due to the
occasional bug that cropped up(like e1000).
I am attaching a pktgen script. There is one experimental parameter
called "batch_low" - for starters just leave it at 0 in order to reduce
experimental variance. If you have solid results you can muck around
with it.
KK has a netperf script he has been using - if you know netperf your
help will really be appreciated in testing it on your hardware.
KK, can you please post your script?
Testing with forwarding and bridging will also be appreaciated.
Above that, suggestions to changes as long as they are based on
verifiable results or glaringly obvious changes are welcome. My
preference at the moment is to flesh out the patch as is and then
improve on it later if it shows it has some value on a wide variety of
apps. As the subject is indicating this is a WIP and as all eulas
suggest "subject to change without notice".
If you help out, when you post your results, can you please say what
hardware and setup was?
The only real driver that has been changed is e1000 for now. KK is
working on something infiniband related and i plan (if noone beats me)
to get tg3 working. It would be nice if someone converted some 10G
ethernet driver.
cheers,
jamal
[-- Attachment #2: pktgen.batch-1-1 --]
[-- Type: application/x-shellscript, Size: 1389 bytes --]
next reply other threads:[~2007-06-06 13:49 UTC|newest]
Thread overview: 57+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-06-06 13:49 jamal [this message]
2007-06-07 6:16 ` [WIP][PATCHES] Network xmit batching Krishna Kumar2
2007-06-07 11:43 ` jamal
2007-06-07 16:13 ` Evgeniy Polyakov
2007-06-07 22:23 ` jamal
2007-06-08 8:38 ` Evgeniy Polyakov
2007-06-08 11:31 ` jamal
2007-06-08 12:09 ` Evgeniy Polyakov
2007-06-08 13:07 ` jamal
2007-06-08 21:02 ` Evgeniy Polyakov
2007-06-08 5:05 ` Krishna Kumar2
2007-06-19 13:21 ` Evgeniy Polyakov
2007-06-19 13:33 ` Evgeniy Polyakov
2007-06-19 14:00 ` Evgeniy Polyakov
2007-06-19 14:09 ` Evgeniy Polyakov
2007-06-19 16:32 ` jamal
2007-06-19 16:44 ` Evgeniy Polyakov
2007-06-19 16:28 ` jamal
2007-06-19 16:35 ` Evgeniy Polyakov
2007-06-19 16:45 ` Evgeniy Polyakov
2007-06-19 17:35 ` Robert Olsson
2007-06-19 17:48 ` jamal
2007-06-19 17:55 ` Evgeniy Polyakov
2007-06-28 0:05 ` [WIP][PATCHES] Network xmit batching - tg3 support jamal
2007-07-02 21:20 ` Matt Carlson
2007-07-03 0:21 ` Michael Chan
2007-07-03 13:26 ` jamal
2007-07-04 4:19 ` Krishna Kumar2
2007-07-04 13:22 ` jamal
2007-07-03 13:09 ` jamal
2007-07-03 19:31 ` Matt Carlson
2007-07-04 1:59 ` jamal
2007-07-03 21:30 ` David Miller
2007-06-19 22:28 ` [WIP][PATCHES] Network xmit batching David Miller
2007-06-21 15:54 ` FSCKED clock sources WAS(Re: " jamal
2007-06-21 16:08 ` jamal
2007-06-21 16:55 ` Benjamin LaHaise
2007-06-25 16:59 ` jamal
2007-06-25 17:08 ` Benjamin LaHaise
2007-06-25 17:16 ` jamal
2007-06-21 16:45 ` Evgeniy Polyakov
2007-06-25 16:58 ` jamal
2007-06-19 16:24 ` jamal
2007-06-21 21:00 ` Rick Jones
2007-06-22 9:59 ` Evgeniy Polyakov
2007-06-25 17:35 ` Rick Jones
2007-06-07 8:42 ` Krishna Kumar2
2007-06-07 12:16 ` jamal
2007-06-08 5:06 ` Krishna Kumar2
2007-06-08 11:14 ` jamal
2007-06-08 11:31 ` Krishna Kumar2
2007-06-08 11:43 ` jamal
2007-06-08 18:00 ` Rick Jones
2007-06-08 17:27 ` Rick Jones
2007-06-09 0:17 ` jamal
2007-06-09 0:40 ` Rick Jones
2007-06-07 22:42 ` 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=1181137761.4068.22.camel@localhost \
--to=hadi@cyberus.ca \
--cc=gaagaan@gmail.com \
--cc=johnpol@2ka.mipt.ru \
--cc=krkumar2@in.ibm.com \
--cc=netdev@vger.kernel.org \
--cc=rick.jones2@hp.com \
--cc=sri@us.ibm.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).