Re: IDE performance drop between 2.4.23 and 2.6.0 - pinpointed!

[Pawel Dziekonski <pawel.dziekonski@pwr.wroc.pl>]

On sob, 03 sty 2004 at 11:46:36  +0100, szonyi calin wrote:
>  --- Pawel Dziekonski <pawel.dziekonski@pwr.wroc.pl> a écrit : >
> hi,
> > 
> > same problem here however it seems that i have pinpointed it
> > )at least
> > for me):
> > 

> from the manpage of hdparm: -t     Perform timings of device reads for
> benchmark and compari- son  purposes.   For  meaningful  results,
> this operation should be repeated 2-3 times on an otherwise inactive
> sys- tem  (no  other active processes) with at least a couple of
> megabytes of free memory. 

> if the above conditions are not met your test is irrelevant 

those conditions were met. trust me  - i have just copied and pasted some
of the results :^)

ps. btw, for last 5 years 2.6.0 this is a 1st example of a situation
where hdparm gives me so unstable results. i think this is because of
the nature of as-scheduler. maybe i'm wrong.

-- 
Pawel Dziekonski <pawel.dziekonski|@|pwr.wroc.pl>, KDM WCSS avatar:0:0:
Wroclaw Networking & Supercomputing Center, HPC Department
-> See message headers for privacy policy info.