I think the point is that as a group, we consciously, deliberately,
and painfully decided not to support multi-cluster. And as a result,
we ripped out a lot of supporting code. Starting down this path again
will likely result in a) re-opening all the discussions, b) re-adding
a lot of
Because:
1. last time we went through this, it all started with a single pebble
in the pond - and I don't want to get engulfed again; and
2. if you bothered to read the email, then you would see that I
pointed out this change doesn't even do what they are trying to do.
The change needs
Ralph,
There is NO need to have this discussion again, it was painful enough
last time. From my perspective I do not understand why are you making
so much noise on this one. How a 4 lines change in some ALPS specific
files (Cray system very specific to ORNL) can generate more than 3 A4
There was a very long drawn-out discussion about this early in 2007.
Rather than rehash all that, I'll try to summarize it here. It may get
confusing - it helped a whole lot to be in a room with a whiteboard.
There were also presentations on the subject - I believe the slides
may still be
Hello All,
As it became apparent this morning, it was well past the time
to actually restrict commit access to the 1.3 branch. As of this
afternoon, all changes to the 1.3 branch must occur via the
CMR process we are all familiar with from the 1.2 branch. See:
What Ken put in is what is needed for the limited multi-cluster capabilities
we need, just one additional string. I don't think there is a need for any
discussion of such a small change.
Rich
On 9/22/08 1:32 PM, "Ralph Castain" wrote:
> We really should discuss that as a group
Hmmm...well, there -used- to be a tool that was distributed with the
1.2 series for doing just that, but I don't see it in the 1.2.7
release. Not sure when or how that got dropped - probably fell through
a crack.
Unfortunately, minus that tool, there is no clean way to shut this
down.
We really should discuss that as a group first - there is quite a bit
of code required to actually support multi-clusters that has been
removed.
Our operational model that was agreed to quite a while ago is that
mpirun can -only- extend over a single "cell". You can connect/accept
This check in was in error - I had not realized that the checkout was from
the 1.3 branch, so we will fix this, and put these into the trunk (1.4). We
are going to bring in some limited multi-cluster support - limited is the
operative word.
Rich
On 9/22/08 12:50 PM, "Jeff Squyres"
Whoa! We made a decision NOT to support multi-cluster apps in OMPI
over a year ago!
Please remove this from 1.3 - we should discuss if/when this would
even be allowed in the trunk.
Thanks
Ralph
On Sep 22, 2008, at 10:35 AM, mat...@osl.iu.edu wrote:
Author: matney
Date: 2008-09-22
Greetings,
I have a manager/worker application. The
manager is called "t2a" and the workers "w2d"
I launch the manager and each worker with
its own mpiexec with n=1. They connect using
various calls including MPI_Open_port,
MPI_Comm_accept, MPI_Comm_connect and
MPI_Intercomm_merge.
It works
We always output the entire map, so you'll see the parent procs as
well as the child
On Sep 16, 2008, at 12:52 PM, Greg Watson wrote:
Hi Ralph,
No I'm happy to get a map at the beginning and at every spawn. Do
you send the whole map again, or only an update?
Regards,
Greg
On Sep 11,
12 matches
Mail list logo