Re: Incorrect output from ceph osd map command

[Vickey Singh <vickey.singh22693@xxxxxxxxx>]

Thanks Greg,

Do you mean ceph osd map command is not displaying accurate information ?

I guess, either of these things are happening with my cluster

- ceph osd map is not printing true information

- Object to PG mapping is not correct ( one object is mapped to multiple PG's )

This is happening for several objects , but the cluster is Healthy.

Need expert suggestion.

On Tue, Feb 23, 2016 at 7:20 PM, Gregory Farnum <gfarnum@xxxxxxxxxx> wrote:

This is not a bug. The map command just says which PG/OSD an object maps to; it does not go out and query the osd to see if there actually is such an object.

-Greg

On Tuesday, February 23, 2016, Vickey Singh <vickey.singh22693@xxxxxxxxx> wrote:

Hello Guys 

I am getting wired output from osd map. The object does not exists on pool but osd map still shows its PG and OSD on which its stored.

So i have rbd device coming from pool 'gold' , this image has an object 'rb.0.10f61.238e1f29.000000002ac5'

The below commands verifies this

[root@ceph-node1 ~]# rados -p gold ls | grep -i rb.0.10f61.238e1f29.000000002ac5

rb.0.10f61.238e1f29.000000002ac5

[root@ceph-node1 ~]#

This object lives on pool gold and OSD 38,0,20 , which is correct

[root@ceph-node1 ~]# ceph osd map gold rb.0.10f61.238e1f29.000000002ac5

osdmap e1357 pool 'gold' (1) object 'rb.0.10f61.238e1f29.000000002ac5' -> pg 1.11692600 (1.0) -> up ([38,0,20], p38) acting ([38,0,20], p38)

[root@ceph-node1 ~]#

Since i don't have object 'rb.0.10f61.238e1f29.000000002ac5' in data and rbd pools , rados ls will not list it. Which is expected.

[root@ceph-node1 ~]# rados -p data ls | grep -i rb.0.10f61.238e1f29.000000002ac5

[root@ceph-node1 ~]# rados -p rbd ls | grep -i rb.0.10f61.238e1f29.000000002ac5

But , how come the object is showing in osd map of pool data and rbd.

[root@ceph-node1 ~]# ceph osd map data rb.0.10f61.238e1f29.000000002ac5

osdmap e1357 pool 'data' (2) object 'rb.0.10f61.238e1f29.000000002ac5' -> pg 2.11692600 (2.0) -> up ([3,51,29], p3) acting ([3,51,29], p3)

[root@ceph-node1 ~]#

[root@ceph-node1 ~]# ceph osd map rbd rb.0.10f61.238e1f29.000000002ac5

osdmap e1357 pool 'rbd' (0) object 'rb.0.10f61.238e1f29.000000002ac5' -> pg 0.11692600 (0.0) -> up ([41,20,3], p41) acting ([41,20,3], p41)

[root@ceph-node1 ~]#

In ceph, object is unique and belongs to only one pool. So why does it shows up in all pool's osd map. 

Is this some kind of BUG in Ceph

Ceph Hammer 0.94.5

CentOS 7.2

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