Was Leslie Lamport Right?
Talkat KubeCon + CloudNativeCon Europe 2025 · on Wednesday, 2025-04-02· at 12:00· Level 0 | ICC Capital Hall | Room I·
summary
Shows why Paxos → Raft lineage still matters, proves Byzantine consensus needs 3m+1 nodes and t+1 voting rounds, and demos the 4‑general case where the protocol recovers from one traitor. Covers Lamport clocks, vector clocks, and the bakery algorithm as concrete tools, mentions Porter and blueprints from bare metal to multi‑cloud, and argues these ideas could have prevented a multi‑million‑dollar outage caused by a single timestamp change. 3m+1 formula, t+1 rounds, Lamport vs vector clocks.
AI-written summary · about
chapters (10)
- 0:00Introduction
- 1:06Leslie Lamport’s work still matters
- 4:37Two Generals problem explained
- 7:22Byzantine Generals problem
- 11:15Live demo: Byzantine fault tolerance
- 13:23Consistency models
- 18:21Lamport’s concurrency theory
- 23:41Lamport and vector clocks
- 29:00Lamport’s impact
- 31:07Closing remarks
related talks
40mConsensus Algorithms in Distributed Systems
43mAll Together Now: An Introduction to Distributed Consensus
51mDo Not Reimplement Distributed Consensus Algorithms
01h 13mPaxos vs Raft: Have we reached consensus on distributed consensus?
22mLiberating Distributed Consensus
27mDistributed Systems, Like It or Not
07mA Walk Through Distributed Consensus
43mWhat We Talk About When We Talk About Distributed Systems