Aeron Cluster - The Aeron Files
theaeronfiles.com · 1,348 words · saved by 1 readers
Documentation for Aeron based on the underlying files
Aeron Cluster Traditional Service ¶ We all recognise a 'traditional' service that looks something like this: Clients send in messages. The service processes them, builds up some internal state and sends response messages. Any modifications to the state are also written to a database, so if the service crashes, the state isn't lost. This is fine for moderate loads, but the database is a source of contention, so it becomes a bottleneck as the load increases. This kind of architecture will never be able to process 100,000's of messages per second with consistent, 99.999% latency measured in
related reading
- 6.5840 Lab 3: Raftpdos.csail.mit.edu
- Students' Guide to Raft :: Jon Gjengsetthesquareplanet.com
- A Distributed Systems Reading Listferd.ca
- Chain Replication for Supporting High Throughput and Availabilitycs.cornell.edu
- An Understandable Consensus Algorithmpdos.csail.mit.edu
- Scaling Replicated State Machines with Compartmentalizationmwhittaker.github.io
- Implementing Raft: Part 3 - Persistence and Optimizations - Eli Bendersky's websiteeli.thegreenplace.net
- Let’s take a crack at understanding distributed consensuspreethikasireddy.com
- A Byzantine failure in the real world | The Cloudflare Blogblog.cloudflare.com
- Durable Execution Solutionstemporal.io
- DBMS Musings: It’s Time to Move on from Two Phase Commitdbmsmusings.blogspot.com
- Lightweight Asynchronous Snapshots for Distributed Dataflowsarxiv.org