My career has been building platforms and products for distributed systems. Early in my career, much of my focus was on distributed networks of (what are now called) IoT devices: tens of thousands of systems distributed across the globe, backed by a SOA control plane. Today I work building platforms for distributed concurrent systems powering global communications and IoT.
I've collected a number of papers around distributed algorithms, metrics and monitoring, and statistical analysis. You can find my favorite distributed computing white papers on GitHub.
Here are a few samples get you started.
- Raft consensus algorithm, used by Consul and etcd for distributed metadata, service discovery, coordinated locks, and more.
- Online calculation of quantiles over data streams - efficient real time calculation of quantiles for streaming metrics.
- Dapper distributed tracing system - And see Zipkin for Twitters implementation.
- SWIM membership protocol - a peer to protocol for membership.
If you are looking for any particular help or have questions, ping me at @alowe on Twitter.