Svitla Smart Talk: Performance tests and other lies
- explore anti-patterns in performance testing and provide battle-tested practical advice on how to avoid being misled by test results;
- address questions such as: Should we fear "coordinated omission"? Why is statistics often considered the pinnacle of deception, accompanied by a quick course on interpreting test results? Why are "latency" and "throughput" not interchangeable? Why are test datasets as crucial as test scenarios? What insights can microbenchmarks offer?