On Mon, Jan 24, 2011 at 10:46 AM, Markus Kienast <mark@xxxxxxxxxxxxx> wrote: > How does ceph differentiate itself from xtreemfs? Ceph and XtreemFS have pretty different goals. >From what I've read, Xtreemfs is designed as a WAN distributed FS with interesting file replication strategies designed to minimize latency across the internet. Ceph is a cluster filesystem designed to be used across a high-speed low-latency network that provides pseudo-random but deterministic block-based replication of data, with strong consistency guarantees, and extreme scalability. (Unlike xtreemfs, Ceph can shard responsibility for metadata across many nodes, and since it calculates data placement rather than assigning it, less metadata needs to be stored and cached.) If you have more specific questions (preferably with indications of how xtreemfs behaves; I'm not terribly familiar with it) we can answer those in more detail. :) -- 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
