I'm reasonably certain I've bumped into a case where a broker in my cluster is serving bad metadata to clients, making them think that a certain partition is leaderless.
This is similar to what's described here (end of the post): https://github.com/Shopify/sarama/issues/665#issuecomment-223128098 Two questions: 1. Has anyone bumped into this case? 2. How can I force that broker to flush that cached metadata? (It keeps serving it for days now.)
