Known issues/en: Difference between revisions

Jump to navigation Jump to search
Updating to match new version of source page
(Updating to match new version of source page)
(Updating to match new version of source page)
Line 8: Line 8:


== Scheduler issues ==
== Scheduler issues ==
* Some users are experiencing excessively long wait times for jobs to run. Staff are analyzing the causes and plan to introduce scheduler changes in the next few weeks that should alleviate the problem. (16:48, 27 September 2017 (UTC))
* The CC Slurm configuration encourages whole-node jobs. When appropriate, users should request whole-node rather than per-core resources. See [[Job_scheduling_policies#Whole_nodes_versus_cores;|Job Scheduling - Whole Node Scheduling]].
* The CC Slurm configuration encourages whole-node jobs. When appropriate, users should request whole-node rather than per-core resources. See [[Job_scheduling_policies#Whole_nodes_versus_cores;|Job Scheduling - Whole Node Scheduling]].
* Slurm epilog does not fully clean up processes from ended jobs, especially if the job did not exit normally.   
* Slurm epilog does not fully clean up processes from ended jobs, especially if the job did not exit normally.   
Line 17: Line 18:
Users will sometimes see a quota error on their project folders. This may happen when files are owned by a group other than the project group. You can change the group which owns files using the command
Users will sometimes see a quota error on their project folders. This may happen when files are owned by a group other than the project group. You can change the group which owns files using the command
{{Command|chgrp -R <group> <folder>}}
{{Command|chgrp -R <group> <folder>}}
If the project directories are configured as intended, new files and directories created in them will automatically assume the project group ownership.  One of the ways in which an unexpected group ownership can occur is transferring files to the project directories using a program option to preserve group ownership.  So, if you have a recurring problem with ownership, check the options being used by your file transfer program.


To see what the value of <group> should be, run the following command:
To see what the value of <group> should be, run the following command:
Line 37: Line 40:
** Workaround: use the /project or /scratch filesystems instead.
** Workaround: use the /project or /scratch filesystems instead.
** Might be resolved by an update or reconfiguration.
** Might be resolved by an update or reconfiguration.
* diskusage_report (and alias 'quota') do not report on Graham /home
** Workaround: 'du -sh ~' shows usage; quota limit is 50G.
* Compute nodes cannot access Internet
* Compute nodes cannot access Internet
** Solution: Request exceptions to be made at  [mailto:support@computecanada.ca CC support] describing what you need to access and why.
** Solution: Request exceptions to be made at  [mailto:support@computecanada.ca CC support] describing what you need to access and why.
38,760

edits

Navigation menu