Hi, no I have not seen any log entries related to scrubs. I see slow requests for various operations including readdir, unlink. Sometimes rdlock, sometimes wrlock.
On 12 May 2017 at 16:10, Peter Maloney <peter.malo...@brockmann-consult.de> wrote: > On 05/12/17 16:54, James Eckersall wrote: > > 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 it look anything like my issue here? > https://www.spinics.net/lists/ceph-devel/msg36184.html > > > Does anyone have any ideas on how to diagnose what is causing this? > > > > Thanks > > > > James > >
_______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
