Re: [OMPI devel] ORTE headers in OPAL source

2014-10-19 Thread Josh Hursey
The first variable can probably be moved to opal pretty easily. That is used when we need to fully shutdown the BTLs and re-init them on continue. We do not have to do that for tcp (since we leave the sockets open), but do have to do that for IB, for example. The second call is a bit tricky since

Re: [OMPI devel] ORTE headers in OPAL source

2014-10-17 Thread Adrian Reber
Josh, I had a look at the code (e.g., opal/mca/btl/sm/btl_sm.c) and there are two uses of orte code: if (orte_cr_continue_like_restart) and /* On restart we need the old file names to exist (not necessarily * contain content) so the CRS component does not fail when searching * for these

Re: [OMPI devel] ORTE headers in OPAL source

2014-08-11 Thread Adrian Reber
I have seen it. I am still waiting for things to settle down before I start fixing the FT code ( again ;-) Adrian On Mon, Aug 11, 2014 at 01:40:33PM +, Jeff Squyres (jsquyres) wrote: > Ah, I see. > > Ok -- add it to the list of >

Re: [OMPI devel] ORTE headers in OPAL source

2014-08-09 Thread Josh Hursey
Those calls should be protected with the CR FT #define - If I remember correctly. We were using the sstore to track the shared memory file names so we could clean them up on restart. I'm not sure if the sstore framework is necessary in this location, since we should be able to tell opal_crs and

Re: [OMPI devel] ORTE headers in OPAL source

2014-08-09 Thread Jeff Squyres (jsquyres)
I think you're making a joke, right...? I see direct calls to ORTE sstore functionality in all three. On Aug 8, 2014, at 5:42 PM, George Bosilca wrote: > These are harmless. They are only used when FT is enabled which should rarely > be the case. > > George. > > >