[ceph-users] GFS2 as RBD on ceph?

[Flint WALRUS]

Hi, in fact it highly depend on your ceph underlying installation (both HW
and Ceph version).

Would you be willing to share more information on your needs and design?
How many IOPS are you looking at? Which processors and disks are you using?
What ceph version? Which OS?
Are you targeting mostly read operations or write operations ? A mixin?

Honestly, serving three webservers (even distributing thousands of small
assets) will perfectly fit on CephFS and the resulting performances would
far better than GFS2 with less ops cost and a better health-management and
data-protection.

Don’t forget that even block volumes are objects store,that’s your storage
hardware, os configuration and ceph version that will drive your
performances.
___
ceph-users mailing list
ceph-users@lists.ceph.com
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com

[ceph-users] GFS2 as RBD on ceph?

[Kevin Olbrich]

Hi!

*Is it safe to run GFS2 on ceph as RBD and mount it to approx. 3 to 5 vm's?*
Idea is to consolidate 3 webservers which are located behind proxys. The
old infrastructure is not HA or capable of load balancing.
I would like to set up a webserver, clone the image and mount the GFS2 disk
as shared storage. This would also allow FTP load balancing.

Redundancy would be taken care of by ceph while the VMs share up-to-date
data on all nodes.

*I don't think CephFS is an option, as most files are very small and
thousands of files will be opened simultaneously.*

Anyone using such an approach?

Kind regards,
Kevin
___
ceph-users mailing list
ceph-users@lists.ceph.com
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com