On 11/09/2012 05:11 AM, Gandalf Corvotempesta wrote:
Based on your experience, will the following configuration be ok for a production cluster? - R515 12 disks + 2 internal disks I'll start with 2x or 4x 2TB SATA disks in each R515. One OSD for each disk, 3 servers. Each R515 will have one internal SSD to be used as journal (single, huge, filesystem) shared by all OSDs and one SATA 10k RPM (probably WD Raptor) to be used as operating system and mons storage.
I'd suggest partitioning the SSD and using those raw block devices as journals to avoid the overhead of an fs.
On each R515 i'll put OSDs and one mon node. Actually, i'll use only RBD and RGW, so no need for MDS. When CephFS will be stable, i'll put MDS on each node. Any suggestion/advice ?
You'll be better off with more nodes so that when 1 dies, 1/3 of your data doesn't need to be re-replicated. Josh -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
