Using a resource allocation: Difference between revisions

Jump to navigation Jump to search
Line 39: Line 39:
=Using a compute allocation on a cluster=
=Using a compute allocation on a cluster=


When submitting a jobs to the scheduler on a cluster, users will need to specify a group name as the value of the <code>--account</code> option.  Jobs pertaining to the research described in the RAC application should be submitted with the group name corresponding to the RAC award, ''e.g.'' <code>--account=rrg-somename-ab</code>.  Jobs pertaining to other research should be submitted with the default group name, ''e.g.'' <code>--account=def-somename</code>.  See [[Running_jobs#Accounts_and_projects|Running jobs: Accounts and projects]] for more details.
<tabs>
<tab name="GP clusters">
When submitting a jobs to the scheduler on a general-purpose cluster, users will need to specify a group name as the value of the <code>--account</code> option.  Jobs pertaining to the research described in the RAC application should be submitted with the group name corresponding to the RAC award, ''e.g.'' <code>--account=rrg-somename-ab</code>.  Jobs pertaining to other research should be submitted with the default group name, ''e.g.'' <code>--account=def-somename</code>.  See [[Running_jobs#Accounts_and_projects|Running jobs: Accounts and projects]] for more details.
</tab>
<tab name="Niagara">
When a user submits a job to the scheduler on Niagara, the job will be assigned to the current RRG or RPP of the user's PI.  If the user has access to more than RRG or RPP, they must specify a group name as the value of the <code>--account</code> option.
</tab>
</tabs>


=Using allocated storage on a cluster=
=Using allocated storage on a cluster=
Bureaucrats, cc_docs_admin, cc_staff
2,879

edits

Navigation menu