On 02/14/2013 02:43 PM, Gregory Farnum wrote: > The problem it's complaining about here isn't lost data, but an > insufficient number of mapped OSDs to the PGs. As it says, look up > incomplete in the docs. :) I have, it says "report bug to inktank": http://ceph.com/docs/master/dev/placement-group/?highlight=incomplete # ceph -s health HEALTH_WARN 4 pgs incomplete; 4 pgs stuck inactive; 4 pgs stuck unclean monmap e1: 1 mons at {a=144.92.167.231:6789/0}, election epoch 1, quorum 0 a osdmap e149: 4 osds: 4 up, 4 in pgmap v71913: 576 pgs: 572 active+clean, 4 incomplete; 1405 MB data, 11593 MB used, 3469 GB / 3667 GB avail mdsmap e614: 2/2/2 up {0=a=up:active,1=b=up:active} All 4 osds are up, "reducing pool metadata min_size from 4" is exactly what I don't want, and yes -- I deleted the data from CephFS (my other e-mail) so at this point whatever's stuck has zero useful (to me) information in it. -- Dimitri Maziuk Programmer/sysadmin BioMagResBank, UW-Madison -- http://www.bmrb.wisc.edu
Attachment:
signature.asc
Description: OpenPGP digital signature
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com