Open MPI logo

Open MPI Development Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Development mailing list

Subject: Re: [OMPI devel] New interface code refactor
From: Ralph Castain (rhc_at_[hidden])
Date: 2010-08-31 16:56:42


I should also have noted that:

1. all of the opal_ifxxx functions still have their "no-op" versions when
struct sockaddr_in is not present.

2. we still "lazy discover" interfaces, so the new opal_if framework is
-not- opened unless you call one of the opal_ifxxx functions and get a
non-no-op version

So I believe RS will be protected, so long as it fails the "have struct
sockaddr_in" test. I'm pretty sure that is the protection used currently, so
nothing should have changed in that regard.

HTH
Ralph

On Tue, Aug 31, 2010 at 2:48 PM, Ralph Castain <rhc_at_[hidden]> wrote:

> I believe it is there, but correct me if not. All of the component
> configure.m4s depend on a test for sockaddr_in, which I believe RS will fail
> - yes?
>
>
> On Tue, Aug 31, 2010 at 2:42 PM, Barrett, Brian W <bwbarre_at_[hidden]>wrote:
>
>> Ralph -
>>
>> My Red Storm dev cluster isn't working right now, but I didn't see an
>> option for no if support at all. Did I miss it, or are we going to have to
>> add it later?
>>
>> Thanks,
>>
>> Brian
>>
>> On Aug 31, 2010, at 2:28 PM, Ralph Castain wrote:
>>
>> > Per a discussion on the devel telecon a week or two ago, I have
>> refactored the opal/util/if.c code into a static framework (ala the
>> installdirs implementation) so that the various cases are dealt with in
>> configure.m4 instead of a mass of interwoven #if-#else clauses. Jeff will
>> undoubtedly do some cleanup of the configury magic, but the basic
>> functionality is ready for initial review.
>> >
>> > For those who care, please clone and check the code at
>> http://bitbucket.org/rhc/ompi-if to ensure that the correct opal/mca/if
>> components are being built for your environment, and that the discovered
>> interfaces are correct. Please let me know (up or down) so we can get a feel
>> for how close we are to bringing this back to the trunk.
>> >
>> > Thanks
>> > Ralph
>> >
>> > <ATT00002..txt>
>>
>> --
>> Brian W. Barrett
>> Dept. 1423: Scalable System Software
>> Sandia National Laboratories
>>
>>
>>
>>
>>
>> _______________________________________________
>> devel mailing list
>> devel_at_[hidden]
>> http://www.open-mpi.org/mailman/listinfo.cgi/devel
>>
>
>