Open MPI logo

Open MPI Development Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Development mailing list

Subject: Re: [OMPI devel] collectives / #1944 progress
From: Eugene Loh (Eugene.Loh_at_[hidden])
Date: 2009-07-02 11:07:32


Jeff Squyres wrote:

> Eugene --
>
> Can you CMR over anything that still needs to go to v1.3 for the sm
> fixes?

#1962

> I'll be filing a CMR to activate coll_sync later today.
>
> (I admit I didn't pay close attention to see if everything is already
> over there)
>
> On Jul 2, 2009, at 8:06 AM, Jeff Squyres wrote:
>
>> On Jul 1, 2009, at 10:23 PM, Eugene Loh wrote:
>>
>>> > For the future, we have a two pronged plan:
>>>
>>> I suspect the standard procedure is that we all look quickly at this
>>> e-mail message, file appropriately, and then resume our normal lives.
>>> Yes? Or, is such a plan put somehow into place?
>>
>> I have time to allocate to this starting next week, but I then take
>> a week of vacation the week after.
>>
>>> > 1. Clean up the sm btl:
>>> > 1a. Remove all dead code.
>>>
>>> What do you mean here? (Possibly you mean getting rid of sm pending
>>> sends if we implement 1b properly, but I'm not sure.)
>>
>> You mentioned to Brian and me that there was a lot of "dead code"
>> (#if'ed out or otherwise will-never-be-used). If that's incorrect,
>> then forget this item.
>>
>>> > 1b. Resize free_list_max and fifo_size MCA params to effect good
>>> > enough flow control.
>>> > 1c. Possibly: convert from FIFO's to linked lists (for future
>>> > maintenance purposes, not necessarily to fix problems).
>>>
>>> Another idea is to have two kinds of FIFOs. One is just for returning
>>> fragments. The other is for in-coming message fragments. It would
>>> even
>>> seem as though one would no longer need "free lists", but just use the
>>> ack FIFO to manage fragments. (ALL of this is complicated by the fact
>>> that we have two kinds of fragments, eager and max, but fortunately
>>> those details can be pushed onto the sorry fool who'll be implementing
>>> all this. I wonder who that'll be.)
>>
>> Likely me and/or Brian.
>