[sheepdog] [PATCH 0/4] do not read the node list from end recovery code in farm

Liu Yuan namei.unix at gmail.com
Fri Jun 1 17:44:05 CEST 2012


On 06/01/2012 11:21 PM, Christoph Hellwig wrote:

> With the current code base I can easily trigger a bug in farm during
> a test case that creates a cluster with four nodes, then shuts the
> cluster down, restarts two of the sheep, starts a new sheep and then
> restarts the other two original sheep.


I haven't read the code yet, but when the new sheep joins in middle way,
the master didn't refuses it to join? I am wondering why there is
recovery process. By design, there should not. only All the 4 origin
nodes joins back, the cluster status will be set okay.

Thanks,
Yuan



More information about the sheepdog mailing list