netdev
[Top] [All Lists]

Re: [RFC] TCP Vegas for 2.6

To: Nivedita Singhvi <niv@xxxxxxxxxx>
Subject: Re: [RFC] TCP Vegas for 2.6
From: Stephen Hemminger <shemminger@xxxxxxxx>
Date: Tue, 9 Mar 2004 11:03:23 -0800
Cc: John Heffner <jheffner@xxxxxxx>, Andi Kleen <ak@xxxxxxx>, linux-net <linux-net@xxxxxxxxxxxxxxx>, netdev@xxxxxxxxxxx
In-reply-to: <404E1374.5050600@us.ibm.com>
Organization: Open Source Development Lab
References: <20040309180331.GC11604@wotan.suse.de> <Pine.NEB.4.33.0403091307090.5230-100000@dexter.psc.edu> <20040309102206.33c1720c@dell_ss3.pdx.osdl.net> <404E1374.5050600@us.ibm.com>
Sender: netdev-bounce@xxxxxxxxxxx
On Tue, 09 Mar 2004 10:56:52 -0800
Nivedita Singhvi <niv@xxxxxxxxxx> wrote:

> Stephen Hemminger wrote:
> 
> > Every case I tested has vegas faster than the default reno.  It is 
> > especially
> > noticeable over the DSL.  The current implementation is not ready to be 
> > turned
> > on by default though.
> 
> Stephen, just a question regarding your testing.
> (To save me some effort ;-)). What tests did you
> run, which testcases, and if it wasn't some standard
> benchmark, will you consider inclusion of those tests into
> the LTP or equivalent?

I used ttcp and netperf, but the tests aren't as interesting as setting up the
toplogies, like 1G Ethernet; Ethernet -> PPP -> Ethernet and Ethernet -> IRDA 
-> Ethernet
and DSL connections through SSH.   Plus, LTP (and are local automated test 
machines)
don't seem to be setup for multi-machine tests.


<Prev in Thread] Current Thread [Next in Thread>