Lustre Quota Troubleshooting: Difference between revisions
| Line 1: | Line 1: | ||
== Adding to This Guide == | == Adding to This Guide == | ||
Revision as of 08:46, 30 January 2025
Adding to This Guide
If you have improvements, corrections, or more information to share on this topic please contribute to this page.
Status Verification
To verify the status of space accounting and quota, run the following on every Lustre node that serves an MDT or OST and has the target mounted
lctl get_param osd-*.*.quota_slave_*.enabled
A MDT will display two different output stanza per target: dt for data/block and md for metadata/inode.
osd-ldiskfs.testfs-MDT0000.quota_slave_dt.enabled=none osd-ldiskfs.testfs-MDT0000.quota_slave_md.enabled=none osd-ldiskfs.testfs-MDT0001.quota_slave_dt.enabled=none osd-ldiskfs.testfs-MDT0001.quota_slave_md.enabled=none
An OST will display only one output stanza per target: dt for data/block.
osd-ldiskfs.testfs-OST0000.quota_slave_dt.enabled=none osd-ldiskfs.testfs-OST0001.quota_slave_dt.enabled=none
Closely inspect the values for quota enabled: and space acct:. The values can be none or any combination of the letters u, g and p, representing user, group and project. The default value for quota enabled: is none and the default value for space acct: is ugp
Quota Modification
User, group and project quota can be modified on a per target basis. Typically, it is desirable to have all target's quota configuration set the same.