[Mono-devel-list] Language Shootout - problems with Mono times

[Paolo Molaro]

On 09/01/04 Isaac Gouy wrote:
> > I'm not sure how we could help, here: this looks like a libc/kernel
> > bug in resource usage accounting. Maybe mono's usage of threads
> > confuses it.
> 
> Are we talking about the 'helper process'? 

I tried by running a separate mono (which just sits there waiting fro a
keystroke) so the helper process is not run when executing sieve, but it
makes no difference.

> What do you mean by "mono's usage of threads"?

The only thing that comes to mind is that mono executes code in a
subthread, not in the thread that executes main(). A quick pthread test
shows that time behaves correctly in this case, though, so it may be
something else that confuses the kernel.

> My ancient Linux 2.4.19 Gentoo gives both sensible results and too
> small  results. (Not sure which version the other guys are using.)

Kernel 2.2.20 has the same behaviour: sometimes the results are correct
and sometimes not.

lupus

-- 
-----------------------------------------------------------------
lupus at debian.org                                     debian/rules
lupus at ximian.com                             Monkeys do it better