Open MPI logo

PLPA Users' Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all PLPA Users mailing list

From: Jeff Squyres (jsquyres_at_[hidden])
Date: 2006-02-10 17:28:04


On Feb 10, 2006, at 5:07 PM, Paul H. Hargrove wrote:

> Some, but not all versions of the syscall return the expected size in
> bytes on success or -1 on error. The others return 0 on success or -1
> on error.
>
> So, correct documentation of the current behavior would be to say
> "non-negative" on success, rather than "zero".
>
> We can resolve the difference between docs and code by changing either
> one to match the other.
> I have no strong feeling either way.

I think that it is in the spirit of the PLPA to provide a consistent
interface and hide the differences between the different versions in
Glibc/the kernel, so I'd prefer to return a consistent form. I'm
kinda guessing that this is what I had in mind when I wrote the docs.

So unless anyone objects, I'm going to have the PLPA set/get affinity
calls return 0 upon success (i.e., the syscall returns >=0).

-- 
{+} Jeff Squyres
{+} The Open MPI Project
{+} http://www.open-mpi.org/