Re: [OMPI devel] bml_r2_btl.c

2008-03-17 Thread George Bosilca
A placeholder for possible extensions ? Well, in fact as we only have one BML, there was no need for the modular architecture, but as we put it in place in the beginning ... we just followed the guidelines. george. On Mar 17, 2008, at 9:36 PM, Jeff Squyres wrote: Is there a purpose for b

[OMPI devel] bml_r2_btl.c

2008-03-17 Thread Jeff Squyres
Is there a purpose for bml_r2_btl.c? It looks like an empty source file to me...? -- Jeff Squyres Cisco Systems

[OMPI devel] RFC: libevent update

2008-03-17 Thread Jeff Squyres
WHAT: Bring new version of libevent to the trunk. WHY: Newer version, slightly better performance (lower overheads / lighter weight), properly integrate the use of epoll and other scalable fd monitoring mechanisms. WHERE: 98% of the changes are in opal/event; there's a few changes to conf

Re: [OMPI devel] orte\mca\smr

2008-03-17 Thread Ralph H Castain
Hello As Jeff stated, the smr has been removed from the system. We did this because experience showed that monitoring process/node status was highly system dependent and directly correlated with the launch system. Thus, it made no sense to separate those two functions. For example, we have succes