On Tue, 2008-02-19 at 01:52 +0900, John Summerfield wrote:
> Pedro Espinoza wrote:
> > Hi Listers:
> >
> > The program appended below takes almost 9 minutes on RHEL 5, RHEL5.1,
> > latest RHEL 4, Centos5.1. However, the same program takes 2m 15
> > seconds on OPensuse 10.2 (2.6.18.8 kernel), and on Fedora 8. The box
> > has 4 dual-core xeon processors, and with 8 GB memory.
> >
> >
> > However, the same program takes 2min 45s on a box that has one
> > dual-core opteron, with RHEL 4 ( 2.6.9-42.0.2.ELsmp SMP).
> >
> > Any pointers appreciated.
> >
> Seriously, how long to run eight of them at once?
>
> The number of CPUs and cores is irrelevant unless you're running
> multiple threads/processes.
>
> I would speculate that F8 and opensuse 10.2 have newer gcc and that that
> makes a significant difference.

I think the issue was:
Fast: ( big hardware + (opensuse 10.2 or Fedora 8)) OR (slow hardware +
older RHEL4)
Slow: ( big hardware + (RHEL5 or latest RHEL4))

Note that (Slow Hardware + older RHEL4) beats (fast hardware + latest
RHEL4) - the other comparisons aren't interesting.

I'm not into reading C, so I have no idea what the test case attempts to
do, however:

Monitoring Top output:

A RHEL5 64 bit machine, uses 100% of a single processor
A F8 32 bit machine, uses 100% of a processor, split across both
processors.

- does 32 bit code or Fedora 8 enable parallelism that does not work on
64 bit code and or RHEL5?

Monitoring Memory usage:
RHEL5: 16% of 1GB = 150MB
F8: 4% of 4GB = 150MB

- therefore I don't think amount of memory in the box makes a
difference.

Pedro: What is the output of `rpm -qif /usr/include/math.h` on each of
those machines?

--
Sam

_______________________________________________
rhelv5-list mailing list
rhelv5-list@(protected)
https://www.redhat.com/mailman/listinfo/rhelv5-list