tags:

views:

32

answers:

0
Q: 

how to limit number of concurrently running PBS jobs

I have a 64-node cluster, running PBS Pro. If I submit many hundreds of jobs, I can get 64 running at once. This is great, except when all 64 jobs happen to be nearly I/O bound, and are reading/writing to the same disk. In such cases, I'd like to be able to still submit all the jobs, but have a max of (say) 10 jobs running at a given time. Is there an incantation to qsub that will allow me to do such, without having administrative access to the cluster's PBS server?

related questions

how to automatically run a bash script when my qsub jobs are finished on a server?
Running a job on multiple nodes of a GridEngine cluster
Is Recursive Grep Really Better?; How to Improve PBS-based Bash Script?; and other Questions...
parameter for shell scripts that is started with qsub
"embarrassingly parallel" programming using python and PBS on a cluster
R programming - submitting jobs on a multiple node linux cluster using PBS
Getting the exit code from a process submitted with qsub on Sun Grid Engine
How to specify the equivalent of ppn (on PBS) in SGE queuing system ?
Is there a DRMAA Java library that works with Torque/PBS?
Does anyone have experience with clusters running on ClusterVisionOS?
script unable to find directories/files when running from qsub cluster script
PBS programming
Test MPI on a cluster
shared memory, MPI and queuing systems
Cluster "Virtual Machine" with PBS
Build wince5 with platform builder wince 6.
Submitting multiple jobs TORQUE/PBS
PBS (torque) fails to consider quad core processors as 4 processors
PBS: Requesting only a single core per node without requesting the entire node
Why doesn't my awk one-liner work when I call it from Perl?
Encoding Keyboard Command Onto Bash Script