CPU Profiling: What, How, and When
Follow CPU samples from collection to symbol resolution and visualization, and learn when profiling can help diagnose a bottleneck.
Blogs
LevelDB MVCC
Read how LevelDB uses sequence numbers and snapshots to support concurrent access and consistent reads.
Prometheus--TSDB
Explore the design of the Prometheus time-series database, connecting its storage structure to observability workloads.
Borg: Large-scale Cluster Management at Google with Borg
Paper Reading · Part 12 of 12Study how Borg combines admission control, scheduling, and resource sharing to operate large clusters efficiently.
Percolator: Large-scale Incremental Processing Using Distributed Transactions and Notifications
Paper Reading · Part 11 of 12It has been a while since I last studied, and I wanted to learn something interesting. This time, I’ll be covering Percolator, a distributed transaction system. I won’t translate the paper …