DESCRIPTION

Eject all nodes after failover

The failover helper needs to return all nodes, not just
the last one to be able to properly eject all nodes.

Change-Id: Ibca2d62a6f5f2383b1aa58701f2bba71bd487715


COMMENTS

author: Reid Stokes
date: 2012-02-02 16:07:21.735000000

Patch Set 1: I would prefer that you didn't submit this

Suppose in cluster of 3 nodes. We are failing over node 1.
As a part of failover we stop node1. Next for some reason if failover fails, the   test will fail and exit out. 
For the next test run, the cluster is left in inconsistent state, with 2 nodes up and 1 node down. 
All the following tests in the run list will fail as well, bcoz one node is stopped...

I dont see how this solves the above issue of inconsistent state of the cluster.

-------------------------------------
author: Reid Stokes
date: 2012-02-02 16:08:06.277000000

Patch Set 1: Looks good to me, approved

Oh.. This was meant for the other commit.

-------------------------------------
