On Fri, Nov 8, 2013 at 9:31 AM, Josh Durgin <josh.dur...@inktank.com> wrote:
> On 11/08/2013 03:50 AM, Wido den Hollander wrote: > >> On 11/07/2013 08:42 PM, Gruher, Joseph R wrote: >> >>> Is there any plan to implement some kind of QoS in Ceph? Say I want to >>> provide service level assurance to my OpenStack VMs and I might have to >>> throttle bandwidth to some to provide adequate bandwidth to others - is >>> anything like that planned for Ceph? Generally with regard to block >>> storage (rbds), not object or filesystem. >>> >>> Or is there already a better way to do this elsewhere in the OpenStack >>> cloud? >>> >>> >> I don't know if OpenStack supports it, but in CloudStack we recently >> implemented the I/O throttling mechanism of Qemu via libvirt. >> >> That might be a solution if OpenStack implements that as well? >> > > Indeed, that was implemented in OpenStack Havana. I think the docs > haven't been updated yet, but one of the related blueprints is: > > https://blueprints.launchpad.net/cinder/+spec/pass-ratelimit-info-to-nova > > Yes, it seemed lack of necessary docs to guide users. I just list commands below to help users to understand: cinder qos-create high_read_low_write consumer="front-end" read_iops_sec=1000 write_iops_sec=10 cinder type-create type1 cinder qos-associate [qos-spec-id] [type-id] cinder create --display-name high-read-low-write-volume --volume-type type1 100 nova volume-attach vm-1 high-read-low-write-volume /dev/vdb > > Thanks, >>> >>> Joe >>> >>> >>> >>> _______________________________________________ >>> ceph-users mailing list >>> ceph-users@lists.ceph.com >>> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com >>> >>> >> >> > _______________________________________________ > ceph-users mailing list > ceph-users@lists.ceph.com > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > -- Best Regards, Wheat
_______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
