A slide deck by Alexander Shraer providing a shorter version of the Dynamic Reconfiguration of Primary/Backup Clusters in Apache ZooKeeper paper.
There are still some scenarios where the proposal algorithm will not work, but I cannot tell how often these will occur:
- Quorum of new ensemble must be in sync
- Another reconfig in progress
- Version condition check fails
One of the most interesting slides in the deck is the one explaining the failure free flow:
Original title and link: Dynamic Reconfiguration of Apache ZooKeeper ( ©myNoSQL)