Fine-Grained Replicated State Machines for a Cluster Storage System (NSDI 2020)

muratbuffalo.blogspot.com

28 points·mad44··6 comments

Weird that they didn't cite Ken Birman's RNFS paper from 1987 on a highly available, fine grained replicated state machine storage cluster.

Poor Birman seems to be habitually lost to the sands of time.

Can you provide more detail? I can't find the paper you are referring to.

RNFS - A Highly Available Network File Service. K. Birman with S. Armstrong et. al. Workshop on Workstation Operation Systems, Boston, Massachusetts, November 1987.

It's about building a clustered NFS server on "virtual synchrony", which is another replicated state machine scheme like paxos and raft. The paper really focuses on some of the issues in making the system very fine grained versus previous virtual synchrony implementations, in addition to the issues in general to making a clustered, highly available, multi master NFS server.

Have you tried googling for a copy of that paper?

That might be part of the reason.

The universities have access to it.

This is usually true but I couldn't find any record of an actual published version in proceedings anywhere.

On the other hand, a related paper on the same system by a subset of authors is available: http://dl.acm.org.sci-hub.tw/doi/book/10.5555/866299

Reply on news.ycombinator.com