netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Juliusz Chroboczek <Juliusz.Chroboczek@pps.jussieu.fr>
To: Patrick McHardy <kaber@trash.net>
Cc: Andi Kleen <andi@firstfloor.org>, netdev@vger.kernel.org
Subject: Re: [PATCH] Stochastic Fair Blue queue discipline
Date: Wed, 09 Apr 2008 17:48:52 +0200	[thread overview]
Message-ID: <7ifxtvghaz.fsf@lanthane.pps.jussieu.fr> (raw)
In-Reply-To: <47FB9315.5030109@trash.net> (Patrick McHardy's message of "Tue\, 08 Apr 2008 17\:45\:25 +0200")

>>> I'd suggest to use the flow classifier for this. For simplicity
>>> you could attach a default classifier that uses the same keys as
>>> this one.

>> I'm not sure I know what you're speaking about.  Could you please
>> point me at code somewhere?

> Check out a recent tree (either Linus' current tree or ideally
> the net-2.6.26.git tree from
>
> git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6.26.git
>
> and look at net/sched/cls_flow.c and the recent changes to
> net/sched/sch_sfq.c for external classifiers.

Thanks for the pointer.  Unfortunately, it will need some changes to
work with sfb -- since we do double-buffering, we need some overlap
between the old and new classifiers when we choose to reclassify.  I'm
not quite sure how to do that.

Other than that, it will require some changes to sfb (which currently
assumes we can get an arbitrary amount of hash data for a single
packet, while the classifiers only give 32 bits), but these changes
are a good thing -- 32 bits should be enough.

Would you have an example of how this stuff is configured from
user-space?

> There are also a number of other incompatible changes that your
> patch needs to be adapter to, most importantly the use of the new
> netlink infrastructure.

Done, thanks for the pointer.

                                        Juliusz

  reply	other threads:[~2008-04-09 15:49 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-04-07 22:37 [PATCH] Stochastic Fair Blue queue discipline Juliusz Chroboczek
2008-04-08  0:04 ` Patrick McHardy
2008-04-08  0:56   ` Patrick McHardy
2008-04-08 15:28   ` Juliusz Chroboczek
2008-04-08  8:20 ` Andi Kleen
2008-04-08 12:11   ` Patrick McHardy
2008-04-08 15:39     ` Juliusz Chroboczek
2008-04-08 15:45       ` Patrick McHardy
2008-04-09 15:48         ` Juliusz Chroboczek [this message]
2008-04-09 16:00           ` Patrick McHardy
2008-04-08 15:38   ` Juliusz Chroboczek
2008-04-08 16:32     ` Andi Kleen
2008-04-08 17:35       ` Juliusz Chroboczek
2008-04-08 17:53         ` Andi Kleen
2008-04-09 15:45           ` Juliusz Chroboczek
2008-04-09 17:49             ` Andi Kleen
2008-04-10  1:23               ` Patrick McHardy
2008-04-10  1:38                 ` Patrick McHardy
2008-04-10 11:17                   ` Juliusz Chroboczek
2008-04-11 13:07                     ` Patrick McHardy
2008-04-10 14:04                   ` Stephen Hemminger
2008-04-10  7:36                 ` Andi Kleen
2008-04-08 16:44 ` Patrick McHardy

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=7ifxtvghaz.fsf@lanthane.pps.jussieu.fr \
    --to=juliusz.chroboczek@pps.jussieu.fr \
    --cc=andi@firstfloor.org \
    --cc=kaber@trash.net \
    --cc=netdev@vger.kernel.org \
    /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).