LOG REPLICATION IN RAFT VS KAFKA

Abstract

The implementation of a fault-tolerant system requires some type of consensus algorithm for correct operation. From Paxos to Viewstamped Replication and Raft multiple algorithms have been developed to handle this problem. This paper presents and compares the Raft algorithm and Apache Kafka, a distributed messaging system which, although at a higher level, implements many concepts present in Raft (strong leadership, append-only log, log compaction, etc.). This shows that mechanisms conceived to handle one class of problems (consensus algorithms) are very useful to handle a larger category in the context of distributed systems.

Keywords

• comparison, Raft, Kafka, consensus algorithm, replicated log.