Please provide us with crushmap
* sudo ceph osd getcrushmap -o crushmap.`date +%Y%m%d%H`
On Fri, Feb 10, 2017 at 5:46 AM, Craig Read <craig@xxxxxxxxxxxxxxxx> wrote:
> Sorry, 2 nodes, 6 daemons (forgot I added 2 daemons to see if it made a difference)
>
> On CentOS7
>
> Ceph -v:
>
> 10.2.5
>
> Ceph -s:
>
> Health HEALTH_WARN
> 64 pgs stuck unclean
> Too few PGs per OSD (21 < min 30)
> Monmap e1: 1 mons at {<hostname>=<ip>:6789/0}
> Election epoch 3, quorum 0 <hostname>
> Osdmap e89: 6 osds: 6 up, 6 in; 64 remapped pgs
> Flags sortbitwise,require_jewel_osds
> Pgmap v263: 64pgs, 1 pools, 0 bytes data, 0 objects
> 209 MB used, 121GB / 121GB avail
> 32 active+remapped
> 32 active
>
> Ceph osd tree:
>
> -1 0.11899 root default
> -2 0.05949 Host 1:
> 0 0.00490 Osd.0 up 1.00000 1.00000
> 3 0.01070 Osd.3 up 1.00000 1.00000
> 4 0.04390 Osd.4 up.100000 1.00000
>
> -3 0.05949 Host 2:
> 1 0.00490 Osd.1 up 1.00000 1.00000
> 2 0.01070 Osd.2 up 1.00000 1.00000
> 5 0.04390 Osd.5 up1.00000 1.00000
>
>
> Appreciate your help
>
> Craig
>
> -----Original Message-----
> From: Shinobu Kinjo [mailto:skinjo@xxxxxxxxxx]
> Sent: Thursday, February 9, 2017 2:34 PM
> To: Craig Read <craig@xxxxxxxxxxxxxxxx>
> Cc: ceph-users@xxxxxxxxxxxxxx
> Subject: Re: OSDs stuck unclean
>
> 4 OSD nodes or daemons?
>
> please:
>
> * ceph -v
> * ceph -s
> * ceph osd tree
>
>
> On Fri, Feb 10, 2017 at 5:26 AM, Craig Read <craig@xxxxxxxxxxxxxxxx> wrote:
>> We have 4 OSDs in test environment that are all stuck unclean
>>
>>
>>
>> I’ve tried rebuilding the whole environment with the same result.
>>
>>
>>
>> OSDs are running on XFS disk, partition 1 is OSD, partition 2 is journal
>>
>>
>>
>> Also seeing degraded despite having 4 OSDs and a default osd pool of 2
>>
>>
>> _______________________________________________
>> ceph-users mailing list
>> ceph-users@xxxxxxxxxxxxxx
>> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
>>
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
