Re: Steps to stop/restart entire ceph cluster

[TYLin <wooertim@xxxxxxxxx>]

Hi KK,

Thank you for your comment, we did set “ceph osd set noout” before shutdown OSD daemons.

Thanks,

Tim

On Apr 7, 2017, at 6:07 PM, K K <nnex@xxxxxxx> wrote:

Hello, 

my cluster didn't have MDS. I recommended add "ceph osd set noout" before shutdown OSD daemons. 
I've done those operation tomorrow and my cluster working again. 

Пятница, 7 апреля 2017, 13:47 +05:00 от TYLin <wooertim@xxxxxxxxx>:

Hi all,

We’re trying to stop and then restart our ceph cluster. Our steps are as following:

stop cluster:
stop mds -> stop osd -> stop mon

restart cluster:
start mon -> start osd -> start mds

Our cluster will stuck in cephfs degraded and mds is replaying journal. After restart mds again, cluster status becomes HEALTH_OK. What is the correct (or recommend) steps to stop/restart cluster?

Thanks,
Tim
_______________________________________________
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