I run a job with openmpi on a virtual machine, my OS
is redhat fedora core 8. When I use ompi-checkpoint to
checkpoint my job, it only checkpoint when my job end.
I don't know why. And I can't restart my job with this
snapshot, it notifies that process fail with signal
11. Signal code: Address not map.
When I run a job on two virtual machine (they are in a
team), it don't run. And when I use Ctrl+C to
terminate my job. I am notified that process fail with
signal 11. Signal code: Address not map.
Please help me