mds slow requests

[James Eckersall <james.eckersall@xxxxxxxxx>]

Hi,

We have an 11 node ceph cluster 8 OSD nodes with 5 disks each and 3 MDS servers.

Since upgrading from Jewel to Kraken last week, we are seeing the active MDS constantly reporting a number of slow requests > 30 seconds.

The load on the Ceph servers is not excessive.  None of the OSD disks appear to be slow or excessively busy.

Does anyone have any ideas on how to diagnose what is causing this?

Thanks

James

_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com