Re: Stacker performance results

From: Serge Hallyn (serue@private)
Date: Wed Mar 16 2005 - 15:34:35 PST

On Wed, 2005-03-16 at 14:40 -0800, Gerrit Huizenga wrote:
> Hi Serge, do you happen to have oprofile data for these runs?

Hi, Gerrit,

no, I don't.  Thanks for the suggestion.  I should rerun and get those,

> However, in all cases, your numbers indicate a significant, measurable,
> large regression.  I wouldn't have expected so much degradation from
> a simple stacker.

I agree, and simply timing kernel compiles does not show this
degradation either.

> If you have a friend in austin who can help you submit a job to
> the internal ABAT harness with your patches, enable oprofile data

That was my original intent, but I've been having trouble using ABAT for
testing on selinux systems.  My second plan had been to put my test
system on ABAT (with known good installed policy), but that also failed.
As it turns out that may have been a DNS problem, so perhaps I'll try
that again.

Currently I'm running 30 lmbench runs per kernel...

Serge Hallyn <serue@private>

This archive was generated by hypermail 2.1.3 : Wed Mar 16 2005 - 15:33:48 PST