On Fri, Dec 18, 2015 at 7:27 AM, Bryan Wright <bkw1a@xxxxxxxxxxxx> wrote: > Gregory Farnum <gfarnum@...> writes: > >> >> Nonetheless, it's probably your down or incomplete PGs causing the >> issue. You can check that by seeing if seed 0.5d427a9a (out of that >> blocked request you mentioned) belongs to one of the dead ones. >> -Greg > > Hi Greg, > > How would I find out which pg this seed belongs to? Also, here's part of > the "ceph pg nnn query" output for one of incomplete pgs: > > > "probing_osds": [ > "107", > "201", > "302", > "406", > "504" > ], > "down_osds_we_would_probe": [ > 102 > ], > "peering_blocked_by": [] > > osd 102 is the dead osd. I think there's a doc about this and I tend to get confused, but I believe you reverse the hash? So 0.5d427a9a is in pool 0, and would be part of its PG a9. 0.a9. Or maybe it's 0.9a, or maybe I just don't remember at all. I'm sure somebody recalls... _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |