Help Needed: 4G/4G Kernel Testing

[Sean Bruno]

Which kernel release did the change take place?  I noted a significant
problem with multiple(40+) java processes once I went from 2.5.6-1.319
to 2.5.6-1.322.

I didn't want to say anything yet, because I don't know the failure
reason(beta java 1.5 in combination with a beta distribution on a newly
released kernel, lol).

Is this possible since the java app in question(home brew) is firing off
a ridiculous amount of threads per process(+- 30 each)?

On Sat, 2004-04-17 at 15:25, Alan Cox wrote:
> On Sat, Apr 17, 2004 at 09:51:03PM +0100, Dave Jones wrote:
> > > Dunno about bug numbers but its also about 10% slower on my laptop
> > > (PII/266) than non 4G/4G. Thats a well known property so hardly needs
> > > a bug number.
> > 
> > It's somewhat strange that a few weeks ago when 4g/4g was temporarily
> > disabled, absolutely *no-one* said "Hey, it got 10% faster!"
> > Either no-one tested those kernels, or the slowdowns only affect
> > certain workloads. From past mails, iirc your workloads weren't anything
> > out of the ordinary, which makes me scratch my head a little.
> 
> The slowdown affects interactive workloads not batch ones except network
> stuff (zillions of interrupts ?). It could also be that its much less
> visible on faster boxes 8)
> 
> Either way if nobody notices it then thatsa good argument not to care
-- 
Sean Bruno
Telecommunications Engineer
Metro One Telecommunications
Desk (503)524-1632
Cell (503)358-6832