A 1994 paper describing how to bring a distributed system to a known state.
Some two-phase commit optimizations for cloud storage.
A Paxos variant that speeds up linearizable reads in geo-distributed clusters.
Faster replication through the magic of partial order.
A multicore replication algorithm.
I attended my first High Performance Transaction Systems conference, here are my messy inaccurate notes.
A PhD thesis and two papers about reactive and predictive autoscaling.
A super-low latency protocol with causal consistency and total order, for cutting-edge data centers.
A 2-week toy project to learn a famous algorithm and try out a distributed systems test framework.
A clever algorithm for reducing conflicts in a distributed task scheduler.