Re: Stacker: april 15 release

From: Serge Hallyn (serue@private)
Date: Mon Apr 18 2005 - 07:20:14 PDT


On Mon, 2005-04-18 at 08:40 -0400, Stephen Smalley wrote:
> On Fri, 2005-04-15 at 18:10 -0500, Serge Hallyn wrote:
> > On www.sf.net/projects/lsm-stacker there is a new stacker release.
> 
> Naturally down for maintenance.

Argh.  In the meantime, I am attaching the files:
   include/linux/security-stack.h
   security/stacker.c
   security/security.c


> >   Some
> > performance results on x86 are attached.  To summarize:
> > 
> >                                Plain            Stack
> > ---------------------------------------------------------------
> > unixbench final score:         520.9            522.6
> > dbench avg 10 runs:            198 stdev 1      205 stdev 1
> > hackbench:                     17 stdev 5       18 stdev 7
> > kernbench (sys time):          28.45 stdev .04  28.35 stdev .08
> > 
> > So hackbench is the only one which is not actually faster with stacking.
> 
> Always good when additional processing makes things go faster ;)
> Any progress on getting the tests run via the IBM test harness,
> including profiling data too?

Not yet.  I plan to start a new attempt today.

> Any testing of the scalability impact of the patch, e.g. on a large SMP
> box?

Hopefully that will come with using the test harness.  I'll create a few
partitions with varying # cpus.  Unfortunately for me, that will then be
ppc, not x86, where I have always gotten worse stacker performance
results...

thanks,
-serge
-- 
Serge Hallyn <serue@private>







This archive was generated by hypermail 2.1.3 : Mon Apr 18 2005 - 07:35:29 PDT