All of lore.kernel.org
 help / color / mirror / Atom feed
From: Vladimir Trebicky <trebicky@xhost.cz>
To: lartc@vger.kernel.org
Subject: Re: [LARTC] re: SFQ variant
Date: Sun, 14 Sep 2003 07:37:10 +0000	[thread overview]
Message-ID: <marc-lartc-106352515404690@msgid-missing> (raw)

First, thanks for reply ;-)

DC> Clearly you'll have to identify which IPs belong the the same users.
DC> I suggest doing this by a bunch of rules that set marks.  In fact
DC> you can set the marks to numbers 1, 2, ... <#users>.
DC> Then you can replace the sfq hash function with the mark.

You're right, I'll use esfq and simply change an input to the hash
function to the part of packet which contains the mark.

DC> Of course, you have to make sure you have enough queues. 
DC> This gives equal access to every mark.

Or I will set the marks from 0-x so that the hash function will do
nothing and the hash function index will be also the mark number then.

DC> If you want to give different shares to different marks then of course
DC> you have to specify how much.  The easiest way I see to do that is to
DC> use different quanta for different marks.

I don't know what's quanta :( But I'd rather know how to connect some
other other priorization. How is CBQ (or HTB) working when an ESFQ is
connected to it? ESFQ is then created on every CBQ class? Or there is
only one ESFQ strangely connected to all of the CBQ classes?

Thanks,

-- 
Regards,
 Vladimir Trebicky                            mailto:trebicky@xhost.cz

_______________________________________________
LARTC mailing list / LARTC@mailman.ds9a.nl
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/

                 reply	other threads:[~2003-09-14  7:37 UTC|newest]

Thread overview: [no followups] expand[flat|nested]  mbox.gz  Atom feed

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=marc-lartc-106352515404690@msgid-missing \
    --to=trebicky@xhost.cz \
    --cc=lartc@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 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.