Distributed systems and performance

The foundations chapter. Everything else in the book is an application of what is here: the latency ladder that makes every architecture decision a placement decision, the two formulas (Little's Law and the queueing multiplier) that turn capacity questions from intuition into arithmetic, the consensus protocols that run underneath etcd and Spanner and Kafka's KRaft, and the consistency vocabulary that candidates most often use imprecisely.

The depth signal in this area is not reciting Raft. It is knowing when you do not need consensus at all. Cassandra, Dynamo and S3 reach enormous scale by keeping consensus off the data path and using it only for metadata, leadership and configuration.

What this chapter covers

• [done] The latency numbers and derived facts
• [done] Back-of-envelope capacity math
• [done] The consistency ladder
• [done] Consistent hashing and its alternatives
• [done] Raft
• [done] Time: Lamport, vector clocks, TrueTime, HLC
• [done] Little's Law and queueing
• [done] The Universal Scalability Law
• [done] Benchmarking discipline, and what microbenchmarks lie about
• [done] Paxos: the two phases and the Phase 2a constraint
• [done] CRDTs: the catalog, and the invariant they cannot save
• [done] Write skew and snapshot isolation
• [done] The tail at scale
• [done] Idempotency and exactly-once

Source: §5.1, §40.