On 02/06/13 02:03, Samuel Thibault wrote:
> Eugene Loh, le Wed 06 Feb 2013 07:50:02 +0100, a écrit :
>> How about adding a check upon entry to hwloc_solaris_get_sth_cpubind(): if
>> processor_bind() shows binding, report this and be done. If not, then
>> continue on with the lgroup logic that's already in that function. Yes?
> If processor_bind() correctly reports an error when only an lgroup
> binding is done, that should be all fine and welcome, indeed.
Well, no. It doesn't report an error. It simply says there is no binding. I think we're on the same page, though. The point is
not to check on processor_bind error but to check on "no binding".
I'm attaching a patch.