Cluster Snapshot Project

Introduction

This is the home page of the Cluster Snapshot Block Device.  This is a virtual block device that runs under Linux's device mapper subsystem, to allow you to create up to 64 read/write snapshots of a cluster filesystem (e.g., GFS) mounted on a shared block device.   Any or all these snapshots can be mounted by themselves or simultaneously with the original volume.

What is this for?  Why, backup of course.  A snapshot block device allows you to back up a snapshot of your filesystem, while you continue to use your filesystem.  A cluster snapshot block device lets you do that with a cluster filesystem, as well as a normal filesystem.

The Cluster Snapshot Block Device consists of a simple kernel device-mapper target that communicates over a network with a not-very-simple cluster snapshot server running as a normal user process.  The server provides synchronization between and distributes access information to cluster nodes that share the original volume and/or snapshots.

Mailing lists

linux-cluster is the mailing list for cluster-related questions and discussion.
Subscribe to this from https://www.redhat.com/mailman/listinfo/linux-cluster.
The list archives are at https://www.redhat.com/archives/linux-cluster/.
The mailing list address is linux-cluster@redhat.com.

Whenever the development source code repository is updated, email is sent to the cluster-cvs mailing list. This list is run using ezmlm.
To subscribe, send an email to cluster-cvs-subscribe@sources.redhat.com or cluster-cvs-digest-subscribe@sources.redhat.com.
You can read the list archives at http://sources.redhat.com/ml/cluster-cvs/

Project Team

That would be me!

Daniel Phillips <phillips@redhat.com>

Status

The cluster snapshot is now feature-complete and lightly tested.  Some subtle aspects of failover still remain to be implemented.  The userspace server is coded in a very non-parallel way, and as a result is prone to bottlenecks on certain loads.  The interface protocol is still subject to change.  The whole thing does appear to work, and has been lightly tested, but not stressed.

A set of unit tests and regression tests is in preparation.

Source code

Here is the latest tarball, to be built against kernel 2.4.8.1.  This code is suitable for unit testing and experimenting, not live use.  Tracing output is on by default.  Follow the directions in the README. 

Note Note Note!  This is still pre-alpha.   Do not use it on a filesystem you care about.

To get the latest source from CVS:
 
    cvs -d :pserver:cvs@sources.redhat.com:/cvs/cluster login cvs
    cvs -d :pserver:cvs@sources.redhat.com:/cvs/cluster checkout cluster/csnap

Just hit enter at the login password prompt.

Documentation

Cluster snapshot design
Linux Kongress Paper
Frequently Asked Questions

IRC

Channel #linux-cluster on freenode

Links

Cluster Project Page