Hi List I've just begun using ceph and installed a small cluster on ubuntu 16.04 nodes using this the process in this guide: https://www.howtoforge.com/tutorial/how-to-install-a-ceph-cluster-on-ubuntu-16-04/ However, once the installation is complete, I see the newly installed cluster is not healthy, and complaining about pgs stuck in inactive: --- root@lol-045:~# ceph -s cluster 220c92fb-2daa-4860-b511-d65ec88d6060 health HEALTH_ERR 448 pgs are stuck inactive for more than 300 seconds 64 pgs degraded 256 pgs stale 64 pgs stuck degraded 192 pgs stuck inactive 256 pgs stuck stale 256 pgs stuck unclean 64 pgs stuck undersized 64 pgs undersized noout flag(s) set monmap e1: 1 mons at {lol-045=17.16.2.20:6789/0} election epoch 4, quorum 0 lol-045 osdmap e66: 7 osds: 4 up, 4 in; 55 remapped pgs flags noout,sortbitwise,require_jewel_osds pgmap v526: 256 pgs, 1 pools, 0 bytes data, 0 objects 134 MB used, 6120 GB / 6121 GB avail 192 stale+creating 64 stale+active+undersized+degraded --- Why is this, and how can troubleshoot and I fix it? (I've googled extensively but couldn't find a solution to this). My osd tree looks like this: ---- ID WEIGHT TYPE NAME UP/DOWN REWEIGHT PRIMARY-AFFINITY -1 10.46080 root default -2 2.98880 host anx-dp02-046 0 1.49440 osd.0 down 0 1.00000 4 1.49440 osd.4 up 1.00000 1.00000 -3 2.98880 host anx-dp02-047 1 1.49440 osd.1 down 0 1.00000 5 1.49440 osd.5 up 1.00000 1.00000 -4 2.98880 host anx-dp02-048 2 1.49440 osd.2 down 0 1.00000 6 1.49440 osd.6 up 1.00000 1.00000 -5 1.49440 host anx-dp02-049 7 1.49440 osd.7 up 1.00000 1.00000 ---- Many thanks in advance, Traiano _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |