[ceph-users] Reducing Max_mds

Rhian Resnick rresnick at fau.edu
Tue Oct 30 03:28:34 PDT 2018


John,


Thanks!


Rhian Resnick

Associate Director Research Computing

Enterprise Systems

Office of Information Technology


Florida Atlantic University

777 Glades Road, CM22, Rm 173B

Boca Raton, FL 33431

Phone 561.297.2647

Fax 561.297.0222

 [image] <https://hpc.fau.edu/wp-content/uploads/2015/01/image.jpg>


________________________________
From: John Spray <jspray at redhat.com>
Sent: Tuesday, October 30, 2018 5:26 AM
To: Rhian Resnick
Cc: ceph-users at lists.ceph.com
Subject: Re: [ceph-users] Reducing Max_mds

On Tue, Oct 30, 2018 at 6:36 AM Rhian Resnick <rresnick at fau.edu> wrote:
>
> Evening,
>
>
> I am looking to decrease our max mds servers as we had a server failure and need to remove a node.
>
>
> When we attempt to decrease the number of mds servers from 5 to 4 (or any other number) they never transition to standby. They just stay active.
>
>
> ceph fs set cephfs max_mds X

After you decrease max_mds, use "ceph mds deactivate <rank>" to bring
the actual number of active daemons in line with your new intended
maximum.

>From Ceph 13.x that happens automatically, but since you're on 12.x it
needs doing by hand.

John

>
> Nothing looks useful in the mds or mon logs and I was wondering what you recommend looking at?
>
>
> We are on 12.2.9 running Centos.
>
>
> _______________________________________________
> ceph-users mailing list
> ceph-users at lists.ceph.com
> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.ceph.com/pipermail/ceph-users-ceph.com/attachments/20181030/c572c48c/attachment.html>


More information about the ceph-users mailing list