Re: [OMPI devel] [OMPI svn-full] svn:open-mpi r23936

2010-10-25 Thread George Bosilca
On Oct 25, 2010, at 20:22 , Jeff Squyres wrote: > I dug into this a bit. > > The problem is in the SM BTL init where it's waiting for all of the peers to > set seg_inited in shared memory (so that it knows everyone has hit that > point). We loop on calling opal_progress while waiting. > >

[hwloc-devel] Create success (hwloc r1.0.3a1r2638)

2010-10-25 Thread MPI Team
Creating nightly hwloc snapshot SVN tarball was a success. Snapshot: hwloc 1.0.3a1r2638 Start time: Mon Oct 25 21:03:09 EDT 2010 End time: Mon Oct 25 21:05:05 EDT 2010 Your friendly daemon, Cyrador

[hwloc-devel] Create success (hwloc r1.1a1r2636)

2010-10-25 Thread MPI Team
Creating nightly hwloc snapshot SVN tarball was a success. Snapshot: hwloc 1.1a1r2636 Start time: Mon Oct 25 21:01:03 EDT 2010 End time: Mon Oct 25 21:03:09 EDT 2010 Your friendly daemon, Cyrador

Re: [OMPI devel] [OMPI svn-full] svn:open-mpi r23936

2010-10-25 Thread Jeff Squyres
I dug into this a bit. The problem is in the SM BTL init where it's waiting for all of the peers to set seg_inited in shared memory (so that it knows everyone has hit that point). We loop on calling opal_progress while waiting. The problem is that opal_progress() is not returning (!). It

Re: [OMPI devel] [OMPI svn-full] svn:open-mpi r23936

2010-10-25 Thread George Bosilca
So now we're in good shape, at least for compiling. IB and TCP seem to work, but SM deadlock. george. On Oct 25, 2010, at 14:33 , Jeff Squyres wrote: > I was literally just about to commit that (i.e., when I ran "svn up" before > committing 23937 and 23938, it merged your change exactly on

Re: [OMPI devel] [OMPI svn-full] svn:open-mpi r23936

2010-10-25 Thread Jeff Squyres
I was literally just about to commit that (i.e., when I ran "svn up" before committing 23937 and 23938, it merged your change exactly on top of mine). :-) With the changes from 936, 937, and 938, I am able to "make distcheck" successfully (and therefore also VPATH build properly). On Oct

Re: [OMPI devel] [OMPI svn] svn:open-mpi r23931

2010-10-25 Thread Jeff Squyres
It's a VPATH build issue -- I have a fix that I am testing right now before I commit... (am testing with "make distcheck" which takes at least 30 mins...) On Oct 25, 2010, at 1:53 PM, Aurélien Bouteiller wrote: > Ralph, > > In file included from >

Re: [OMPI devel] [OMPI svn] svn:open-mpi r23931

2010-10-25 Thread Aurélien Bouteiller
Ralph, In file included from ../../../../../trunk/opal/mca/event/libevent207/libevent207_module.c:44: ../../../../../trunk/opal/mca/event/libevent207/libevent/event.h:165:33: error: event2/event-config.h: No such file or directory Looks like you forgot some files. Aurelien Le 25 oct.