Parallel jobs - SIGKILL issues

Rajesh_kr82 · Post by **Rajesh_kr82** » Thu Sep 07, 2006 1:26 pm

I was wondering if anyone knows about this error I get while running scheduled parallel jobs, the error is not descriptive it says
"node_node1: Player 2 terminated unexpectedly." the next error is
main_program: Unexpected termination by Unix signal 9(SIGKILL)

I am running the same parallel job with multiple instances. At one time only on instance runs. Each instance is supplied with different input files. Amout of data is not very big. Job get killed like once in 20 runs. Also i am using only one node.

I am not sure what exactly is the casue. I have seen other posts on this but didnt get any satisfactory answer. Please me know if some one was able to successfully over come this problem.

Rajesh

Krazykoolrohit · Post by **Krazykoolrohit** » Thu Sep 07, 2006 2:00 pm

Your jobs are being killed in the server. So maybe you can ask your unix admin about it.

My guess is probably you are exceeding the number of jobs which are allowed to run on the server. thats one one of it gets killed.