Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 17 Feb 1998 22:25:33 +0100
From:      Eivind Eklund <eivind@yes.no>
To:        Luigi Rizzo <luigi@labinfo.iet.unipi.it>, Eivind Eklund <eivind@yes.no>
Cc:        plm@xs4all.nl, freebsd-current@FreeBSD.ORG
Subject:   Re: cvs commit: src/usr.sbin/ppp command.c datalink.c datalink.h          defs.h vars.c vars.h
Message-ID:  <19980217222533.63111@follo.net>
In-Reply-To: <199802171950.UAA01120@labinfo.iet.unipi.it>; from Luigi Rizzo on Tue, Feb 17, 1998 at 08:50:15PM %2B0100
References:  <19980217203309.39822@follo.net> <199802171950.UAA01120@labinfo.iet.unipi.it>

next in thread | previous in thread | raw e-mail | index | archive | help
On Tue, Feb 17, 1998 at 08:50:15PM +0100, Luigi Rizzo wrote:
> there are a few things I would like (eventually) to go into ppp,
> so i am just throwing a few ideas here... i don't have the time to work
> on these things now, although I might look at them in the summer.
> 
> * Fair Queueing support (i don't think it is already there, just a
>   priority for interactive packets ?)
>   the code could be grabbed from the ALTQ package recently announced on
>   this list. Not necessarily the full package, just the FQ stuff could
>   help;
> 

This is on my list of things that must be done.  I can't guarantee
when I'll come to it, but if others don't take of them, I will.


> * "preemption" . 
>   I don't think ppp allows this, but perhaps it could be possible to
>   implement preemption of long packets (or transfer them in smaller
>   'cells') so that interactive traffic does not suffer exceedingly
>   large delays... is there any work on this ?
>   (the alternative -- lowering MTU -- is not that attractive i
>   believe, since it causes some overhead even if the last hop has
>   proper header compression)


I'm not certain how this can be handled.  A possibility might be to
fragment the packets for just that connection, ie, in effect lower the
MTU for just part of the use.

I believe some smart heuristics would be necessary to make this work well.

Eivind.

To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-current" in the body of the message



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?19980217222533.63111>