Hello, I've got a small development cluster that shows some strange behavior that I'm trying to understand. If I reduce the weight of an OSD using ceph osd reweight X 0.9 for example Ceph will move data but recovery stalls and a few pg's remain stuck unclean. If I reset them all back to 1 ceph goes healthy again. This is running an older version 0.94.6. Here's the OSD tree: ID WEIGHT TYPE NAME UP/DOWN REWEIGHT PRIMARY-AFFINITY -1 8.24982 root default -2 2.74994 host node-10 11 0.54999 osd.11 up 1.00000 1.00000 3 0.54999 osd.3 up 1.00000 1.00000 12 0.54999 osd.12 up 1.00000 1.00000 0 0.54999 osd.0 up 1.00000 1.00000 6 0.54999 osd.6 up 1.00000 1.00000 -3 2.74994 host node-11 8 0.54999 osd.8 up 1.00000 1.00000 15 0.54999 osd.15 up 1.00000 1.00000 9 0.54999 osd.9 up 1.00000 1.00000 2 0.54999 osd.2 up 1.00000 1.00000 13 0.54999 osd.13 up 1.00000 1.00000 -4 2.74994 host node-3 4 0.54999 osd.4 up 1.00000 1.00000 5 0.54999 osd.5 up 1.00000 1.00000 7 0.54999 osd.7 up 1.00000 1.00000 1 0.54999 osd.1 up 1.00000 1.00000 10 0.54999 osd.10 up 1.00000 1.00000 _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |