To try to avoid the disk usage of one or two users or projects adversely affecting other users, we have implemented a policy of checking disk usage on a regular basis and taking the actions detailed below.
View your disk quotas and current usages on systems by running the commands:
quota -v quota -v -s
Administrative disk usage limits
Administrative disk usage limits are imposed on the file systems /short, /home and the mdss file storage area. The concept of a "quota" and "hard" limit is used. The quota limits should be seen as the real limits users should try to stay under, while the hard limit is used by the system as a trigger to take preventative action.A user or project which exceeds the quota limits but not the hard limits has seven days in which to get back under quota to avoid the actions triggered by exceeding hard limits.
Users should ensure they have enough space available before starting jobs. Note that adjustments to quotas, on a temporary or a long-term basis, will be made given reasonable justification.
The consequences of a project or user exceeding these administrative disk usage limits are outlined in the following table:
| File System | Quota Limit Exceeded | Hard Limit Exceeded |
|---|---|---|
| /home | The user will be sent an email to warn them that their disk usage under /home is over the quota limit and they should reduce the disk space used within 7 days if they wish to continue to have jobs run in the queues. |
Use of the queues by the user will be placed on hold until the user
disk usage is reduced. An email to this effect will be sent the user.
Except for the copyq, queued jobs will not start although running jobs will be allowed to continue. The copyq will remain available to allow archiving. Queued jobs will be released when the quota system next detects that the disk usage is back under the quota limit. This should occur within 5 minutes of the user getting back under the disk quota limit. |
| /short | All members of the project will be sent an email to inform them that the project has exceeded the quota limit, and that they must reduce the disk space used under /short within 7 days if they wish to continue to have jobs run in the queues. | Use of the queues by the project will be placed on hold until
the project disk usage is reduced. All members of the project
will be sent an email to this effect. Except for the copyq, queued jobs will not start although running jobs will be allowed to continue. The copyq will remain available to allow archiving. Queued jobs will be released when the quota system next detects that the disk usage is back under the quota limit. This should occur within 5 minutes of the project getting back under the disk quota limit. |
| mdss | All members of the project will be sent an email to inform them that the project has exceeded the MDSS quota limit, and that they must reduce the MDSS space used within 7 days if they wish to continue to have jobs run in the queues. | Access to the queues by the project will be placed on
hold until the file space usage is reduced by the project. All
members of the project will be sent an email to this effect.
Due to the relative "expense" of reassessing file space usage under mdss, reactivation will not automatically occur for up to 3 hours after the removal of files. Contact to request manual reactivation. |
Native filesystem quotas
It is important to understand that these limit are not the native filesystem quotas available on most Unix filesystems - the behaviour and actions described above are quite different. Exceeding administrative limits should not cause job failures nor stop users from managing files etc. However users should be aware that real filesystem "hard quotas" are also imposed but with a limit much higher than the administrative limits discussed above. You can see the imposed filesystem hard quotas by using -s option to the quota command. If a user or project reaches the relevant filesystem hard quota, jobs are likely to fail due to write operations failing.