This system is operated according to the ITCS Change Management system. All Non-Emergency downtime will require 2 weeks' notice and approval from the Change Management Committee.
If emergency downtime is required, an email will be sent to all users informing them of the situation.
The system "Message-of-the-Day" will be updated with any downtime schedule or other information.
It is possible that during a downtime period, a number of batch jobs may have to be removed. A separate email will be sent to each user with a job in this state.
SGI has gone to a semi-annual upgrade schedule, where major OS distributions are shipped every six months.
LSF is a workload management system. It manages batch scheduling to more effectively manage system resources. LSF configuration LSF uses a group of configurable queues that runs each job based on a number of resource requirements of the job and availability of system resources.
A limit of 30 cpu minutes has been placed on all processes start interactively during a session. When an interactive task reaches this limit it will be killed by the system. Jobs run via LSF are not affected by this limit and are controlled by the LSF queue definition.
Useful LSF filesOn Zeus in the directory: /usr/local/lsf/ there are several adobe acrobat (.pdf) files that can be downloaded and printed for your use.lsf_qrefcard_6.0.pdfA quick reference card for normal LSF commands.lsf_using_6.0.pdfThe user guide for LSF.running_jobs.pdfA tutorial on running jobs with LSF.
LSF Job queue configuration
|Queue Name||Max Jobs||Run Limits||User Groups||Queue Description|
|system||N/A||N/A||System||System administration jobs|
|short||N/A||< 30m||ALL||Short jobs|
|8c_72||2||30m-72h||ECU||5-8 cpus and up to 72 hours|
|4c_120||3||30m-120h||ECU||1-4 cpus and up to 120 hours|
|e_4c_120||1||30m-120h||NON-ECU||1-4 cpus and up to 120 hours|
|1c_240||4||30m-240h||ECU||1 cpu and up to 240 hours|
|e_1c_240||1||30m-240h||NON-ECU||1 cpu and up to 240 hours|
|1c_720||2||30m-720h||ECU||1 cpu and up to 720 hours|