On Feb 2, 2010, at 10:59 PM, Andreea Costea wrote:
> Let's say I have an MPI application that runs on several hosts. I
> want to suspend the application. I do that by sending to the mpirun
> process the signal TSTP. Is there any way to measure how long does
> it take to the application to completely suspend? Doing this "time
> kill -TSTP PID" will measure just the time for sending the signal, I
> suppose, right?
Right. There is no good way to measure this. You could set up
daemons on all the nodes to watch the processes in the job, but even
then there could be clock skew between the hosts. You could at best
get an approximate number.