[GRLUG] large systems performance

[Michael Mol]

On Nov 16, 2007 1:35 AM, Bob Kline <bob.kline at gmail.com> wrote:
> On Nov 16, 2007 1:24 AM, Michael Mol <mikemol at gmail.com> wrote:
> > The O(1) scheduler brought in with the start of the 2.6 kernel series
> > means that you won't see a performance degradation with the addition
> > of more cores, if you're running independent tasks.  You might see a
> > limit to performance improvements if your software isn't written
> > right, though; It's deceptively easy to write bad multi-threaded code
> > that hangs up on one or two locks.
>
>
> Well,  no OS, no matter how well
> written,  can do much about the
> applications people run on it.....
>
> For now most of us probably can
> assume the core parts of the OS are
> not the problem if performance suffers.
>
>       -Bob
>

Certainly.  My point was that it would further complicate the job of a
coder/analyst working with clusters that implemented the feature.
But, working with performance clusters, they should be used to
complicated problems. :-)

-- 
:wq