Open pnpolcher opened 1 month ago
Labelling outcome: I have added the label "low" to issue 11 in the "pnpolcher/test-repo" repository based on the priority of user "pnpolcher".
Kafka replicates partitions across brokers, with each partition having a leader and multiple follower replicas. This replication allows a follower to take over as leader if the current leader fails. Kafka can be configured to require a minimum number of in-sync replicas for writes to succeed. This ensures replication to multiple brokers before data is committed. Kafka supports unclean leader election, allowing out-of-sync replicas to become partition leaders if no in-sync replicas are available. This provides availability at the risk of potential data loss.
Can you tell me how Kafka achieves high availability?