[Gluster-devel] Glusterd 'Management Volume' proposal

[James]

On Mon, Nov 24, 2014 at 9:29 AM, Jeff Darcy <jdarcy at redhat.com> wrote:
> I think the ideal might be to embed a consensus
> protocol implementation (Paxos, Raft, or Viewstamped Replication)
> directly into glusterd, so it's guaranteed to start up and die exactly
> when those daemons do and be subject to the same permission or resource
> limits.  I'm not sure it's even more work than managing either an
> external daemon or a management volume (with its own daemons).


I was hoping someone would say this... I've been fooling around a lot
with raft lately (since I found Paxos too hard as a first exercise)
and I'd love to see either of these algorithms be part of Gluster
core...

As an aside, apart from Google's paper about chubby, are there any
good resources about how to understand Raft/Paxos on a Global scale,
in particular if latencies/links can be high/unreliable?

Cheers,
James