On 02/03/04 14:40 +0530, Rahul Kumar wrote:
> I had recently posted on this but not got a reply/pointer.
> I am narrowing down.
> We have an C application that is NOT improving in performance on
> increasing the # of CPU's - infact the performance degraded. 
Where is your bottleneck? What does the application do?

> In fact the performance on 2.4.20-25 is very poor despite increasing m/c
> configuration.
>From what to what?
 
> The user downloaded and compiled the kernel himself (from linux.org) but
> he still gets the same 10 messages per second throughput only.
Messages? What type of messages?
 
> He recently tried a modified kernel (by HP) that gives him 240 m/sec
> (on the same machine- intel P4), Those guys dont know what has caused
> the drastic improvement, and its not a production worthy version, so we
> cant use it.
So look at the source diffs and the config options chosen?

> Does anyone know about performance issues on the 2.4.25 kernel?
vmstat is your friend to start with.

Devdas Bhagat


-------------------------------------------------------
SF.Net is sponsored by: Speed Start Your Linux Apps Now.
Build and deploy apps & Web services for Linux with
a free DVD software kit from IBM. Click Now!
http://ads.osdn.com/?ad_id=1356&alloc_id=3438&op=click
_______________________________________________
linux-india-help mailing list
[EMAIL PROTECTED]
https://lists.sourceforge.net/lists/listinfo/linux-india-help

Reply via email to