login
Header Space

 
 

Re: Kernel 2.4 vs 2.6 Traffic Controller performance

Score:
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
To: <linux-kernel@...>
Date: Tuesday, October 2, 2007 - 8:17 pm

On Wed, 3 Oct 2007 08:05:30 +0800
Sonny <smaniaol@gmail.com> wrote:


Some related thoughts:
1. Make sure you have the iperf yield fix in place. Otherwise iperf eats
   cpu.

2. Proper mailing lists are: netdev@vger.kernel.org and lartc@mailman.ds9a.nl

3. The latest versions of 2.6 use different clock measurement that
should be better than older 2.4 (where there are three choices).
The new clock is finer resolution (at slightly higher overhead), which
should make accuracy higher but might increase cpu usage.

-- 
Stephen Hemminger <shemminger@linux-foundation.org>

-
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
Re: Kernel 2.4 vs 2.6 Traffic Controller performance, Stephen Hemminger, (Tue Oct 2, 8:17 pm)
speck-geostationary