Learning Distributed Systems

Thanks to the paper trail and CaitieM.

Basics

• Distributed systems for fun and profit
• History of the Impossibles - CAP and FLP
• FLP and CAP aren't the same thing
• Readings in Database Systems - Peter Bailis, Joseph M. Hellerstein, Michael Stonebrake
• The Log: What every software engineer should know about real-time data's unifying abstraction - Jay Kreps

Courses

• CS6213 Special Topics in Distributed Computing
• CS 425 Distributed Systems

Papers

• Readings in Distributed Systems - Christopher Meiklejohn The Part-Time Parliament Viewstamped Replication: A New Primary Copy Method to Support Highly-Available Distributed Systems Fast Paxos Paxos Made Moderately Complex Distributed Snapshots: Determining Global States of Distributed Systems Forward and Backward Simulations Part I: Untimed Systems An Axiomatic Proof Technique for Parallel Programs I Proving Liveness Properties of Concurrent Programs

Exercises

• Toydb
• pea2pea

TLA+

• Leslie Lamport's The TLA+ Video Course
• raft.tla
• Dr. TLA+ Series - Raft
• Dr. TLA+ series - learn an algorithm and protocol, study a specification

Raft

• An Erlang implementation of RAFT from WhatsApp

Data Structures

• Distributed Hash Tables

Books

• Distributed systems for fun and profit

• Designing Data Intensive Applications - Martin Kleppmann

• Replication: Theory and Practice

• Introduction to Reliable and Secure Distributed Programming

Papers

• A Note on Distributed Systems

• MapReduce: Simplified Data Processing on Large Clusters

• Dynamo

• An overview of clock synchronization

• Impossibility of Distributed Consensus with One Faulty Process

• Harvest, Yield and Scalable Tolerant Systems

• Unreliable Failure Detectors for Reliable Distributed Systems

• Survey on Scalable Failure Detectors

• Life beyond distribuyed transactions

• Two phase commit

• Three phase commit

• Paxos

• Chubby

• Zookeeper

• A Quorum-based Commit Protocol

• Bully algorithm

• How to Build a Highly Available System Using Consensus

• Distributed Snapshots: Determining Global States of a Distributed System

• Atomic broadcast

• Gossip

• Chain Replication for Supporting High Throughput and Availability

Real Systems

• GFS

• Spanner

• F1

• Chubby

• BigTable

• MillWheel

• Omega

• Dapper

• Paxos Made Live

• The Tail At Scale

• Dryad

• Cassandra

• Ceph

• RAMCloud

• HyperDex

• PNUTS

• Azure Data Lake Store

Blog Posts & Talks

• Everything Will Flow - Zach Tellman

Courses

• PingCAP Talent Plan

• MIT 6.824

• Aphyr's class

• The System Design Primer

Others

• CAP Twelve Years Later: How the "Rules" Have Changed

• Fallacies of distributed computing

• You Can’t Sacrifice Partition Tolerance: In which there are limits to the CAP conjecture

• Fallacies of distributed computing

• Two Generals' Problem

• Byzantine fault

• Vector clock

• Quorum

• baseds: Exploring the basics of distributed systems