Re: [OMPI devel] [OMPI users] still segmentation fault with openmpi-2.0.2rc3 on Linux

2017-01-11 Thread Gilles Gouaillardet
Ralph, spawn_master spawns 4 spawn_slave (i attached note master is fine with mpirun -np 1 --slot-list 0:0-5,1:0-5 --host motomachi ./spawn_master but v2.0.x and v2.x are not. Cheers, Gilles On 1/12/2017 1:42 PM, r...@open-mpi.org wrote: Looking at this note again: how many procs

Re: [OMPI devel] [OMPI users] still segmentation fault with openmpi-2.0.2rc3 on Linux

2017-01-11 Thread r...@open-mpi.org
Looking at this note again: how many procs is spawn_master generating? > On Jan 11, 2017, at 7:39 PM, r...@open-mpi.org wrote: > > Sigh - yet another corner case. Lovely. Will take a poke at it later this > week. Thx for tracking it down > >> On Jan 11, 2017, at 5:27 PM, Gilles Gouaillardet

Re: [OMPI devel] Fwd: Re: [OMPI users] still segmentation fault with openmpi-2.0.2rc3 on Linux

2017-01-11 Thread r...@open-mpi.org
Sigh - yet another corner case. Lovely. Will take a poke at it later this week. Thx for tracking it down > On Jan 11, 2017, at 5:27 PM, Gilles Gouaillardet wrote: > > Ralph, > > > > so it seems the root cause is a kind of incompatibility between the --host > and the

[hwloc-devel] Create success (hwloc git v1.11-201701120204-fa32e98)

2017-01-11 Thread mpiteam
Creating nightly hwloc snapshot git tarball was a success. Snapshot: hwloc v1.11-201701120204-fa32e98 Start time: Thu Jan 12 02:04:12 UTC 2017 End time: Thu Jan 12 02:06:02 UTC 2017 Your friendly daemon, Cyrador ___ hwloc-devel mailing list

[OMPI devel] Fwd: Re: [OMPI users] still segmentation fault with openmpi-2.0.2rc3 on Linux

2017-01-11 Thread Gilles Gouaillardet
Ralph, so it seems the root cause is a kind of incompatibility between the --host and the --slot-list options on a single node with two six cores sockets, this works : mpirun -np 1 ./spawn_master mpirun -np 1 --slot-list 0:0-5,1:0-5 ./spawn_master mpirun -np 1 --host motomachi

[hwloc-devel] Create success (hwloc git v1.11-201701112104-fa32e98)

2017-01-11 Thread mpiteam
Creating nightly hwloc snapshot git tarball was a success. Snapshot: hwloc v1.11-201701112104-fa32e98 Start time: Wed Jan 11 21:04:13 UTC 2017 End time: Wed Jan 11 21:07:06 UTC 2017 Your friendly daemon, Cyrador ___ hwloc-devel mailing list

Re: [OMPI devel] rdmacm and udcm for 2.0.1 and RoCE

2017-01-11 Thread Dave Turner
The btl_openib_receive_queues parameters that Howard provided fixed our problem with getting 2.0.1 working with RoCE so thanks for all the help. However, we are seeing segfaults with this when configured with --enable-btl-openib-failover. I've included the configuration below that the

Re: [OMPI devel] OMPI devel] hwloc missing NUMANode object

2017-01-11 Thread r...@open-mpi.org
Should be fixed here: https://github.com/open-mpi/ompi/pull/2711 > On Jan 5, 2017, at 6:42 AM, r...@open-mpi.org wrote: > > I can add a check to see if we have NUMA, and if not we can fall back to > socket (if present) or just “none” > >> On Jan 5,

[hwloc-devel] Create success (hwloc git v1.11-201701111655-fa32e98)

2017-01-11 Thread mpiteam
Creating nightly hwloc snapshot git tarball was a success. Snapshot: hwloc v1.11-20170655-fa32e98 Start time: Wed Jan 11 16:55:44 UTC 2017 End time: Wed Jan 11 16:57:42 UTC 2017 Your friendly daemon, Cyrador ___ hwloc-devel mailing list