Le 07/07/2010 11:15, Jirka Hladky a écrit :
> I have also seen you recent change:
>
> ==========================
>
> --list <type|depth>
>
> and replaces
>
> --nodelist with --list numanode (still supported but undocumented)
>
> It should work for core and socket as well.
>
> ==========================
>
> I have downloaded hwloc-1.1a1r2290.tar.bz2
> <http://www.open-mpi.org/software/hwloc/nightly/trunk/hwloc-1.1a1r2290.tar.bz2>but
> apparently the modification is not there yet. If I get right you have
> implemented following, right?
>

I didn't commit this change yet, I was waiting for some feedback first
(not sure if --list and --objects are good names for these options). You
should apply the patch that I sent in my previous mail.

> I have few suggestions regarding error handling in hwloc-calc 1.0.1:
>
> =====================================================
>
> hwloc-calc --nodelist --physical proc:0
>
> => gives nothing back on systems without NUMA. I would expect some
> sort of error message on stderr.
>
> hwloc-calc --nodelist --physical proc:120
>
> =>gives nothing back. On that system, there is NUMA but only 64
> processors. I would expect error message "proc:120 does not exist"
> reported on stderr.
>
>

Those errors are only reported when -v is given (as well as other
verbose messages). You're right, we should always show them.

Brice

Reply via email to