On 11/05/2014 11:03 PM, Lindsay Mathieson wrote: > Morning all .. > > I have a simple 3 node 2 osd cluster setup serving VM Images (proxmox). The > two OSD's are on the two VM hosts. Size is set to 2 for replication on both > OSD's. SSD journals. > > > - if the Ceph Client (VM quest over RBD) is accessing data that is stored on > the local OSD, will it avoid hitting the network and just access the local > drive? From monitoring the network bond that seems to be the case. > No, it will not. The CRUSHMap tells a client to read data from a specific location. You can tune this with localization in the CRUSHMap, but in the basics it will read from the node that CRUSH tells it to read from. > > - if I added an extra OSD to the local node would that same client then use it > to stripe reads, improving the the read transfer rate? > Not persé that local OSD for striping, but data will be migrated and the new disk will be used to gain more performance. > > - Geo Replication - thats done via federated gateways? looks complicated :( > * The remote slave, it would be read only? > That is only for the RADOS Gateway. Ceph itself (RADOS) does not support Geo Replication. > - Disaster strikes, apart from DR backups how easy is it to recover your data > off ceph OSD's? one of the things I liked about gluster was that if I totally > screwed up the gluster masters, I could always just copy the data off the > filesystem. Not so much with ceph. > It's a bit harder with Ceph. Eventually it is doable, but that is something that would take a lot of time. > > - Am I abusing ceph? :) I just have a small 3 node VM server cluster with 20 > windows VM;s, some servers, some VDI. The shared store is a QNAP nas which is > struggling. I'm using ceph for > - Shared Storage > - Replication/Redundancy > - Improved performance > I think that 3 nodes is not sufficient, Ceph really starts performing when you go >10 nodes (excluding monitors). > Its serving all of this, but the complexity concerns me sometimes. > Storage always is a complex thing, Ceph is no exception on that. Wido > Thanks, > > > > _______________________________________________ > ceph-users mailing list > ceph-users@xxxxxxxxxxxxxx > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > -- Wido den Hollander 42on B.V. Ceph trainer and consultant Phone: +31 (0)20 700 9902 Skype: contact42on _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |