I have noted recently many people running what I consider compute jobs on the system known as hal.cbio.mskcc.org. Which even though we limit the processes when many are running it impacts the interactive response of others. I've emailed folks I find doing this but I don't really have time for that so I ask your assistance in reviewing your usage on the head node and see if you should be instead running jobs on the nodes via the scheduler. We like to be flexible but please try to consider the below in deciding where to run that "one off" job.
Per the wiki:
//
While the head node is available to run short, non-memory-intensive tasks (e.g. editor sessions, archival, compilation, etc.), longer-running jobs or jobs that require more resources should be run on the nodes through the batch queue system (either in batch or interactive mode)---see below.
PLEASE DO NOT RUN MEMORY OR CPU INTENSIVE JOBS ON THE HEAD NODE. Use interactive logins to the compute nodes (see below) for this purpose.
Shell processes on the head node are currently restricted to 10 hours of runtime and 4GB of RAM.
//
Please consider learning either interactive qsub for your needs or discuss with us your reasons for such jobs. Some details on doing this are located here:
I have noted recently many people running what I consider compute jobs on the system known as
hal.cbio.mskcc.org. Which even though we limit the processes when many are running it impacts the interactive response of others. I've emailed folks I find doing this but I don't really have time for that so I ask your assistance in reviewing your usage on the head node and see if you should be instead running jobs on the nodes via the scheduler. We like to be flexible but please try to consider the below in deciding where to run that "one off" job.Per the wiki:
//
While the head node is available to run short, non-memory-intensive tasks (e.g. editor sessions, archival, compilation, etc.), longer-running jobs or jobs that require more resources should be run on the nodes through the batch queue system (either in batch or interactive mode)---see below.
PLEASE DO NOT RUN MEMORY OR CPU INTENSIVE JOBS ON THE HEAD NODE. Use interactive logins to the compute nodes (see below) for this purpose.
Shell processes on the head node are currently restricted to 10 hours of runtime and 4GB of RAM.
//
Please consider learning either interactive qsub for your needs or discuss with us your reasons for such jobs. Some details on doing this are located here:
https://github.com/cBio/cbio-cluster/wiki/MSKCC-cBio-Cluster-User-Guide#interactive-jobs