Hi,
AFAIK should an "ceph osd down osd.29" marked osd.29 as down.
But what is to do if this don't happens?

I got following:
root@ceph-02:~# ceph osd down osd.29
marked down osd.29.

root@ceph-02:~# ceph osd tree
2014-06-23 08:51:00.588042 7f15747f5700  0 -- :/1018258 >>
172.20.2.11:6789/0 pipe(0x7f157002a370 sd=3 :0 s=1 pgs=0 cs=0 l=1
c=0x7f157002a5d0).fault
# id    weight  type name       up/down reweight
-1      203.8   root default
-3      203.8           rack unknownrack
-2      29.12                   host ceph-01
52      3.64                            osd.52  up      1
53      3.64                            osd.53  up      1
54      3.64                            osd.54  up      1
55      3.64                            osd.55  up      1
56      3.64                            osd.56  up      1
57      3.64                            osd.57  up      1
58      3.64                            osd.58  up      1
59      3.64                            osd.59  up      1
-4      43.68                   host ceph-02
8       3.64                            osd.8   up      1
10      3.64                            osd.10  up      1
9       3.64                            osd.9   up      0.8936
11      3.64                            osd.11  up      0.9022
12      3.64                            osd.12  up      0.8664
13      3.64                            osd.13  up      0.9084
14      3.64                            osd.14  up      0.8097
15      3.64                            osd.15  up      0.893
29      0                               osd.29  up      0
...

osd.29 is marked as up and can't be unmountet, because it's in use. If I
kill the osd-process, they will automaticly restarted just in time.

My ceph-version is
ceph --version
ceph version 0.72.2 (a913ded2ff138aefb8cb84d347d72164099cfd60)

The OSD-node is an "Linux ceph-02 3.11.0-15-generic #25~precise1-Ubuntu"

Any hints?

The ugly way is simple remove the unused OSD - but I want to know how
should this normaly work.

Udo
_______________________________________________
ceph-users mailing list
[email protected]
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com

Reply via email to