Difference between revisions of "Oldwiki.scinet.utoronto.ca:System Alerts"

From oldwiki.scinet.utoronto.ca
Jump to navigation Jump to search
Line 1: Line 1:
 
== System Status: <span style="color:#00dd00">'''UP'''</span> ==  
 
== System Status: <span style="color:#00dd00">'''UP'''</span> ==  
 +
 +
System Temporary Change:
 +
 +
Due to some changes we are making to the GPC GigE nodes, if you run multinode ethernet MPI jobs (IB multinode jobs are fine), you will need to explicitly request the ethernet interface in your mpirun:
 +
 +
For Openmpi  -> mpirun  --mca btl self,sm,tcp
 +
 +
For IntelMPI  ->  mpirun -env I_MPI_FABRICS shm:tcp
 +
 +
There is no need to do this if you run on IB, or if you run single node mpi jobs on the ethernet (GigE) nodes.  Please check [[GPC_MPI_Versions]] for more details.
 +
 +
Thu Jan 19 11:12:55 EST 2012
 +
 +
---------------------------
  
 
All systems are back up.  Please resubmit your jobs.
 
All systems are back up.  Please resubmit your jobs.

Revision as of 12:15, 19 January 2012

System Status: UP

System Temporary Change:

Due to some changes we are making to the GPC GigE nodes, if you run multinode ethernet MPI jobs (IB multinode jobs are fine), you will need to explicitly request the ethernet interface in your mpirun:

For Openmpi -> mpirun --mca btl self,sm,tcp

For IntelMPI -> mpirun -env I_MPI_FABRICS shm:tcp

There is no need to do this if you run on IB, or if you run single node mpi jobs on the ethernet (GigE) nodes. Please check GPC_MPI_Versions for more details.

Thu Jan 19 11:12:55 EST 2012


All systems are back up. Please resubmit your jobs.

Thu Jan 19 10:50:49 EST 2012



Chiller failure, all systems automatically shut down. We'll keep you informed in this space.

Thu 19 Jan 2012 07:54:17 EST


(Previous messages)