netdev
[Top] [All Lists]

Re: NAPI, e100, and system performance problem

To: Arthur Kepner <akepner@xxxxxxx>
Subject: Re: NAPI, e100, and system performance problem
From: Jamal Hadi Salim <hadi@xxxxxxxx>
Date: Mon, 25 Apr 2005 08:16:19 -0400
Cc: "David S. Miller" <davem@xxxxxxxxxxxxx>, ak@xxxxxx, gnb@xxxxxxx, jesse.brandeburg@xxxxxxxxx, netdev@xxxxxxxxxxx, davem@xxxxxxxxxx
In-reply-to: <1114429267.7669.160.camel@localhost.localdomain>
Organization: ZNYX Networks
References: <C925F8B43D79CC49ACD0601FB68FF50C03A633C7@orsmsx408> <Pine.LNX.4.61.0504180943290.15052@linux.site> <1113855967.7436.39.camel@localhost.localdomain> <20050419055535.GA12211@sgi.com> <m1hdhzyrdz.fsf@muc.de> <1114173195.7679.30.camel@localhost.localdomain> <20050422172108.GA10598@muc.de> <1114193902.7978.39.camel@localhost.localdomain> <20050422183004.GC10598@muc.de> <Pine.LNX.4.61.0504221131350.15052@linux.site> <20050422115230.6037a362.davem@davemloft.net> <Pine.LNX.4.61.0504241845070.2934@linux.site> <1114429267.7669.160.camel@localhost.localdomain>
Reply-to: hadi@xxxxxxxx
Sender: netdev-bounce@xxxxxxxxxxx
After looking closely at the data:
To reduce the work, 20 and 40% should be enough.
But lets rule out the tg3 and also test with e1000 and UDP.

cheers,
jamal

On Mon, 2005-25-04 at 07:41 -0400, jamal wrote:
> Actually, it may be sufficient to collect data for 20, 40, and 80% link
> utilization for napi, napi+dmiller_mchan and nonapi
> 
> Same for the e1000.
> 
> cheers,
> jamal
> 


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