Re: PGs stuck unclean "active+remapped" after an osd marked out

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Hi,

Gregory Farnum a wrote :

> If I remember/guess correctly, if you mark an OSD out it won't
> necessarily change the weight of the bucket above it (ie, the host),
> whereas if you change the weight of the OSD then the host bucket's
> weight changes.

I can just say that, indeed, I have noticed exactly what you describe
in the ouput of of "ceph osd tree".

> That makes for different mappings, and since you only
> have a couple of OSDs per host (normally: hurray!)

er, er... no, I have 10 OSDs in the first "osd node" and 11 OSDs in the
second "osd node" (see my fisrt message).

> and not many hosts (normally: sadness)

Yes, only I have only 2 "osd nodes" (and 3 monitors).

> then marking one OSD out makes things harder for the CRUSH algorithm.

Ah, Ok. So my cluster is too little for Ceph. ;)
Thanks for your answer Greg, I will follow the pull-request with attention.

-- 
François Lafont
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com





[Index of Archives]     [Information on CEPH]     [Linux Filesystem Development]     [Ceph Development]     [Ceph Large]     [Linux USB Development]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]     [xfs]


  Powered by Linux