Build Systems that Drive Business
June 11–12, 2018: Training
June 12–14, 2018: Tutorials & Conference
San Jose, CA

Think local: Reducing coordination and improving performance when designing around distributed state

John Mumm (Wallaroo Labs)
11:25am–12:05pm Wednesday, June 13, 2018
Distributed Data
Location: 230 B Level: Beginner
Secondary topics: Distributed State
Average rating: *****
(5.00, 1 rating)

Prerequisite knowledge

  • A basic understanding of distributed systems

What you'll learn

  • Learn strategies for avoiding coordination and relying on local knowledge wherever possible and tips for using in-memory state instead of the typical approach of using external data stores

Description

We build distributed systems to maintain high availability and improve performance. However, as soon as distributed state is thrown into the mix, you have to start thinking about the performance costs of accessing that state and keeping it current. Many of the worst problems concern the need for coordination across nodes and across systems within a node.

Drawing on the lessons he’s learned working on Wallaroo, a high-performance, open source framework for building stateful distributed applications, John Mumm shares strategies for avoiding coordination and relying on local knowledge wherever possible along with pros and cons and tips for using in-memory state instead of the typical approach of using external data stores.

Photo of John Mumm

John Mumm

Wallaroo Labs

John Mumm is a Netherlands-based software architect at Wallaroo Labs, where he works on an open source high-performance framework for building stateful distributed applications. John holds a PhD in philosophy.