My experience with using TLA+ in distributed systems class

Facebook's Mystery Machine: End-To-end Performance Analysis of Internet Services

Perspectives on the CAP theorem

The Scalable Commutativity Rule

Distributed is not necessarily more scalable than centralized

BookKeeper: High-availability scalable distributed logging

Facebook's software architecture

Tango: Distributed Data Structures Over a Shared Log

ZooKeeper: Wait-free coordination for Internet-scale systems

Hybrid Logical Clocks