On Tue, Sep 5, 2017 at 10:28 AM, Marc Roos <M.Roos@xxxxxxxxxxxxxxxxx> wrote:
> What would be the best way to get an overview of all client connetions.
> Something similar to the output of rbd lock list
>
>
> cluster:
> 1 clients failing to respond to capability release
> 1 MDSs report slow requests
>
>
> ceph daemon mds.a dump_ops_in_flight
> {
> "ops": [
> {
> "description": "client_request(client.2342664:12 create
> #0x100001b9177/..discinfo.hJpqTF 2017-09-05 09:56:43.419636
> caller_uid=500, caller_gid=500{500,1,2,3,4,6,10,})",
> "initiated_at": "2017-09-05 09:56:43.419708",
> "age": 5342.233837,
> "duration": 5342.233857,
> "type_data": {
> "flag_point": "failed to wrlock, waiting",
> "reqid": "client.2342664:12",
> "op_type": "client_request",
> "client_info": {
> "client": "client.2342664",
> "tid": 12
> },
> "events": [
> {
> "time": "2017-09-05 09:56:43.419708",
> "event": "initiated"
> },
> {
> "time": "2017-09-05 09:56:43.419913",
> "event": "failed to wrlock, waiting"
> }
> ]
> }
> }
> ],
> "num_ops": 1
> }
>
> http://docs.ceph.com/docs/master/cephfs/troubleshooting/
As of luminous, it's "ceph tell mds.0 client ls".
In earlier releases there is "ceph tell mds.0 session ls", and "ceph
daemon mds.<id> session ls" (some of these output non-pretty-printed
JSON that you'd probably need to pipe into a script).
John
>
>
> _______________________________________________
> 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
