Kill! Kill! Die! Die! Load Testing With A Vengeance
summary
Claims a practical, repeatable load strategy: node-based clients using a shred HTTP wrapper and spire.io messaging, distributed Dolphin pods across Tokyo, Dublin, Brazil and AWS regions, and an AMI kernel-tuned tester to avoid ephemeral tester limits. Shows a real system under test, graphs concurrency vs latency, reports surprising run-to-run variance (about twice the throughput between runs), explains noisy-neighbor/cloud bandwidth bottlenecks, and ties tests into CI and cost-per-user scaling decisions.
AI-written summary · about
chapters (7)
- 0:00Load testing evolution
- 2:10Load testing importance
- 7:53Real user behavior modeling
- 15:13Scalable load testing tools
- 21:33Distributed testing with Dolphin
- 27:30Visualizing results
- 29:40Open source plans & closing
related talks
48mHow to not Crash in Prod, Load Testing Crash Course
47mLoad Testing You Always Wanted
45mBeat the rush! Designing effective load tests for your web application
26mIntroduction to Load Testing
30mBeat the rush! Designing effective load tests for your web application
46mLoad Testing Without Being Off the Mark
57mLast- und Performancetests in der Cloud?!
43mA Murder of Crows: Actors, Instrumentation, and Load-testing as Part of the TDD Cycle