Why Is My App Slow - Defining Reliability in Platform Engineering

Explore how Google's Serverless SRE team tackles platform-level latency issues in this 47-minute conference talk from YOW! Australia 2023. Dive into detecting regressions, measuring their impact, and tracking performance over time. Learn about the limitations of SLOs and discover a statistical approach for a customer-centric view of platform performance. Gain insights on total latency distribution, request delivery latency, reliability in practice, and the 2-Sigma Technique. Understand concepts like stationarity, overload score, and impact analysis. Examine the mechanics, FAQ, backtesting, limitations, and other applications of this approach. Conclude with valuable lessons for platform engineers and SREs working on serverless architectures.

Intro
Serverless platform is amazing
"My app is slow"
The platform is slow
Total end-to-end latency distribution
Request delivery latency
Goal
Reliability in practice
Applying to the model
Stationarity
2-Sigma Technique
Mechanics
Overload score
Impact analysis
FAQ
Backtesting
Limitations
Other applications
Conclusions
Outro