From day one Patroni was positioned as a template for PostgreSQL HA, because it is far from being a one-size-fits-all or plug-and-play system. Setting it up in a test lab is a very simple task, while going to production requires solving problems which are not always typical for DBA:
- How to chose/setup/manage Etcd/Consul/Zookeeper cluster?
- How to do backups/PITR with Patroni?
- How to build/reinitialize replicas without hitting the primary?
- How to manage PostgreSQL configuration with Paroni?
- How to monitor the whole system?
- How to provide a single endpoint for applications?
- Where would be a good place for pgbouncer in this setup?
All these (and many more) questions regularly appear among issues in the Patroni repository and in the #Patroni Slack channel.
In the talk I will guide you through the whole process of setting up a production-ready HA cluster managed by Patroni, starting from Etcd and finishing by the single connection endpoint for applications.