PBS allocates cores to batch jobs in units of 12-core nodes. A node cannot be allocated to multiple jobs, so a job is charged for the entire node whether or not it uses all its cores. The PBS -l size option specifies the number of cores to allocate to a job and it must be a multiple of 12.
The service unit charge for each job is:
PBS 'size' * walltime
where walltime is the number of wall clock hours used by the job.
The showusage utility can be used to view your project allocation and overall usage through the last job accounting posting (usually the previous night). For example,
>showusage
Usage on kraken:
Project Totals <userid>
Project Allocation Usage Remaining Usage
_________________________|___________________________|_____________
<YourProj> 2000000 | 123456.78 1876543.22 | 1560.80
The -h option will list more usage details.
More detailed accounting
information can be obtained using the glsjob command:
glsjob -u janeuser- Prints current accounting information for all janeuser's jobs
glsjob -p MY-PROJECT01- Prints current accounting information for all jobs charged to account MY-PROJECT01
glsjob --man- Displays documentation for
glsjob
Job Refund Policy
When a job terminates with no useful output for reasons beyond the user's control, NICS will consider Service Unit refunds for up to two weeks after the charge was incurred, provided the following information is sent to help@teragrid.org:- user ID
- machine name
- Batch Job ID
- reason for the request
Please note that refunds must be requested by the close of business on the 5th of each month for any jobs ending in the previous month.
