Re: [ceph-users] Major ceph disaster

2019-05-23 Thread Alexandre Marangone
The PGs will stay active+recovery_wait+degraded until you solve the unfound objects issue. You can follow this doc to look at which objects are unfound[1] and if no other recourse mark them lost [1] http://docs.ceph.com/docs/master/rados/troubleshooting/troubleshooting-pg/#unfound-objects . On

Re: [ceph-users] How to just delete PGs stuck incomplete on EC pool

2019-03-02 Thread Alexandre Marangone
If you have no way to recover the drives, you can try to reboot the OSDs with `osd_find_best_info_ignore_history_les = true` (revert it afterwards), you'll lose data. If after this, the PGs are down, you can mark the OSDs blocking the PGs from become active lost. On Sat, Mar 2, 2019 at 6:08 AM

Re: [ceph-users] Ceph on Solaris / Illumos

2015-04-15 Thread Alexandre Marangone
The LX branded zones might be a way to run OSDs on Illumos: https://wiki.smartos.org/display/DOC/LX+Branded+Zones For fun, I tried a month or so ago, managed to have a quorum. OSDs wouldn't start, I didn't look further as far as debugging. I'll give it a go when I have more time. On Wed, Apr 15,