Hi,
When forwarding stdin to all ranks in the job (mpirun --stdin all), the
following error message is output:
--
[berlin73:02223] [[56600,0],0] ORTE_ERROR_LOG: A message is attempting
to be sent to a process whose contact information is unknown in
file ../../../../../orte/mca/rml
Hi,
If a job is launched using "srun --resv-ports --cpu_bind:..." and slurm
is configured with:
TaskPlugin=task/affinity
TaskPluginParam=Cpusets
each rank of that job is in a cpuset that contains a single CPU.
Now, if we use carto on top of this, the following happens in
get_ib_dev_distanc
Hi,
In v1.5, when mpirun is called with both the "-bind-to-core" and
"-npersocket" options, and the npersocket value leads to less procs than
sockets allocated on one node, we get a segfault
Testing environment:
openmpi v1.5
2 nodes with 4 8-cores sockets each
mpirun -n 10 -bind-to-core -npersock
Hi list,
I'm hitting a limitation with paffinity/hwloc with cpu numbers >= 64.
In opal/mca/paffinity/hwloc/paffinity_hwloc_module.c, module_set() is
the routine that sets the calling process affinity to the mask given as
parameter. Note that "mask" is a opal_paffinity_base_cpu_set_t (so we
allow
Hi,
When using the carto/file module with a syntactically incorrect carto
file, we get stuck into opal_carto_base_select().
The attached trivial patch fixes the issue.
Regards,
Nadia
--
nadia.derbey
Fix a hang in carto_base_select if carto_module_init fails
diff -r 94299d729b95 opal/mca
like --output-filename is global to the job: even if it
is given on any single line of an application context, with different
values, the last value is the one that is actually taken as an output
file prefix.
Regards,
Nadia
--
nadia.derbey
Hi,
In ompi/mpi/f77/type_create_struct_f.c, routine
mpi_type_create_struct_f() mallocates c_type_old_array, but never frees
it.
Regards,
Nadia
--
nadia.derbey
-btl-openib.txt", "of unknown
> > event",
> > true,orte_process_info.nodename,
> > orte_process_info.pid,
> > - event.event_type, xrc_event ? "true" : "false");
> > +event_type, xrc_event ? "true" : "false");
> > }
> > ibv_ack_async_event(&event);
> > } else {
> > ___
> > svn-full mailing list
> > svn-f...@open-mpi.org
> > http://www.open-mpi.org/mailman/listinfo.cgi/svn-full
> >
>
>
--
nadia.derbey
On Thu, 2010-07-15 at 08:21 -0400, Jeff Squyres wrote:
> On Jul 15, 2010, at 8:22 AM, nadia.derbey wrote:
>
> > So the solution is:
> > 1. leave the intermediate event_type declared as an int.
> > 2. then:
> > . either cast it to ibv_event_type when c
On Thu, 2010-07-15 at 07:21 -0400, Jeff Squyres wrote:
> On Jul 15, 2010, at 2:14 AM, nadia.derbey wrote:
>
> > The only warning I'm getting in the part of the code impacted by the
> > patch is:
> > -
> > ../../../../../ompi/mca/btl/open
gards,
On Wed, 2010-07-14 at 14:10 -0400, Jeff Squyres wrote:
> Do you get additional warnings when compiling with the intel compiler (about
> printf'ing an enum type)? I seem to recall that there's already a truckload
> of those kinds of warnings...
>
>
> On Jul 1
this issue.
Regards,
Nadia
--
nadia.derbey
Wrong event_type value passed in to show_help when getting xrc async events
diff -r e4bab4451664 ompi/mca/btl/openib/btl_openib_async.c
--- a/ompi/mca/btl/openib/btl_openib_async.c Tue May 25 01:30:35 2010 +0200
+++ b/ompi/mca/btl/openib
Hi,
Reference is the v1.5 branch
If an SRQ has the following settings: S,,4,2,1
1) setup_qps() sets the following:
mca_btl_openib_component.qp_infos[qp].u.srq_qp.rd_num=4
mca_btl_openib_component.qp_infos[qp].u.srq_qp.rd_init=rd_num/4=1
2) create_srq() sets the following:
openib_btl->qps[qp].u.
13 matches
Mail list logo