Presentation: Cluster Consensus: When Aeron Met Raft

Track: Bare Knuckle Performance

Location: Whittle, 3rd flr.

Duration: 4:10pm - 5:00pm

Day of week: Wednesday

Level: Advanced

Share this on:

Abstract

Consensus protocols enable distributed systems to agree a common view of shared state. This common view allows a cluster to continue service while a majority of its members are available. Raft was designed to be understandable. Raft succeeded in this goal and became popular.

Aeron was designed to be an understandable messaging system, it was also designed to be fast, very fast. If the design principles of Aeron were applied to Raft, could we create a high-performance consensus implementation? Come to this talk if you would like to find out what happened when Aeron met Raft.

Question: 

How you you describe the persona and level of the target audience?

Answer: 

Senior developers and architects who need highly resilient systems without compromising performance. Typically these developers will be from a finance, gaming, betting, or high-volume transactional system domains.

Question: 

What do you want “that” persona to walk away from your talk knowing that they might not have known 50 minutes before?

Answer: 

An understanding of how consensus algorithms operate and the techniques that can be applied to make them efficient. Building a system on top of consensus algorithms requires very efficient interfacing to the algorithm and means to comprehend and monitor operation. We'll cover the mechanics of how this can work.

Question: 

What trend in the next 12 months would you recommend an early adopter/early majority SWE to pay particular attention to?

Answer: 

With the event of CPU exploits like Meltdown and Spectre we are seeing more people take performance and efficiency as a first class concern, especially on cloud platforms. From this we'll likely see an increase in adoption of user-space network and storage access libraries. The challenge comes from how we design our software to best utilise these significant changes in infrastructure.

Speaker: Martin Thompson

High Performance & Low Latency Specialist

Martin is a Java Champion with over 2 decades of experience building complex and high-performance computing systems. He is most recently known for his work on Aeron and SBE. Previously at LMAX he was the co-founder and CTO when he created the Disruptor. Prior to LMAX Martin worked for Betfair, three different content companies wrestling with the world largest product catalogues, and was a lead on some of the most significant C++ and Java systems of the 1990s in the automotive and finance domains. He blogs at mechanical-sympathy.blogspot.com, and can be found giving training courses on performance and concurrency when he is not cutting code to make systems better.

Find Martin Thompson at

Last Year's Tracks

Monday, 5 March

Tuesday, 6 March

Wednesday, 7 March