From: Werner Almesberger <Werner.Almesberger@epfl.ch>
To: Jeff Garzik <jgarzik@mandrakesoft.com>
Cc: netdev@oss.sgi.com,
Linux Knernel Mailing List <linux-kernel@vger.kernel.org>
Subject: Re: New net features for added performance
Date: Sun, 25 Feb 2001 13:22:49 +0100 [thread overview]
Message-ID: <20010225132249.J18271@almesberger.net> (raw)
In-Reply-To: <3A9842DC.B42ECD7A@mandrakesoft.com>
In-Reply-To: <3A9842DC.B42ECD7A@mandrakesoft.com>; from jgarzik@mandrakesoft.com on Sat, Feb 24, 2001 at 06:25:16PM -0500
Jeff Garzik wrote:
> 1) Rx Skb recycling.
Sounds like a potentially useful idea. To solve the most immediate memory
pressure problems, maybe VM could provide some function that does a kfree
in cases of memory shortage, and that does nothing otherwise, so the
driver could offer to free the skb after netif_rx. You still need to go
over the list in idle periods, though.
> 2) Tx packet grouping.
Hmm, I think we need an estimate of how long a packet train you'd usually
get. A flag looks reasonably inexpensive. Estimated numbers sound like
over-engineering.
> Disadvantages? Can this sort of knowledge be obtained by a netdevice
> right now, without any kernel modifications?
Question is what the hardware really needs. If you can change the
interrupt point easily, it's probably cheapest to do all the work in
hard_start_xmit.
> 3) Slabbier packet allocation.
Hmm, this may actually be worse during bursts: if you burst exceeds
the preallocated size, you have to perform more expensive/slower
operations (e.g. running a tasklet) to refill your cache.
- Werner
--
_________________________________________________________________________
/ Werner Almesberger, ICA, EPFL, CH Werner.Almesberger@epfl.ch /
/_IN_N_032__Tel_+41_21_693_6621__Fax_+41_21_693_6610_____________________/
next prev parent reply other threads:[~2001-02-25 12:23 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2001-02-24 23:25 New net features for added performance Jeff Garzik
2001-02-24 23:48 ` Andi Kleen
2001-02-25 0:03 ` Jeff Garzik
2001-02-25 0:12 ` Andi Kleen
2000-01-01 0:19 ` Pavel Machek
2001-03-04 1:19 ` LILO error with 2.4.3-pre1 Steven J. Hill
2001-03-04 1:39 ` Keith Owens
2001-03-04 2:27 ` Tom Sightler
2001-03-04 21:32 ` Mircea Damian
2001-03-04 23:05 ` Guest section DW
2001-03-04 2:39 ` Andre Tomt
2001-03-04 3:32 ` Steven J. Hill
2001-03-04 13:35 ` Alan Cox
2001-02-25 0:13 ` New net features for added performance Jeff Garzik
2001-02-25 0:16 ` Andi Kleen
2001-02-25 11:49 ` Rusty Russell
2001-02-26 23:48 ` David S. Miller
2001-02-27 0:03 ` Andi Kleen
2001-02-27 0:08 ` David S. Miller
2001-02-27 2:53 ` Jeremy Jackson
2001-02-27 19:59 ` kuznet
2001-02-25 1:55 ` Michael Richardson
2001-02-25 2:32 ` Jeremy Jackson
2001-02-25 3:23 ` Chris Wedgwood
2001-02-25 12:41 ` Werner Almesberger
2001-02-25 13:57 ` Chris Wedgwood
2001-02-25 2:38 ` Noah Romer
2001-03-03 23:32 ` Jes Sorensen
2001-02-25 12:01 ` Andrew Morton
2001-02-25 15:11 ` Jeremy Jackson
2001-02-25 12:22 ` Werner Almesberger [this message]
2001-03-12 15:08 ` Jes Sorensen
2001-02-25 13:08 ` Jonathan Morton
2001-02-26 23:46 ` David S. Miller
2001-02-27 0:07 ` Jeff Garzik
2001-02-27 0:10 ` David S. Miller
2001-03-01 21:06 ` Jes Sorensen
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=20010225132249.J18271@almesberger.net \
--to=werner.almesberger@epfl.ch \
--cc=jgarzik@mandrakesoft.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