Observability for Deep Systems
summary
Microservices create layered, interdependent architectures where responsibility outpaces control, producing "deep systems" that need new observability approaches. Empirical looks at LightStep customers show lots of room for improvement — 70% performance gains are common when bottlenecks are found. The talk argues that deep systems demand prioritized signals, that OpenTelemetry unifies logs metrics and traces, and that traces are critical to find where latency and failures actually originate so teams can reduce MTTR.
AI-written summary · about
chapters (8)
- 0:00Intro
- 0:39Impact of Observability
- 1:05Wide vs Deep Scale
- 2:41Observability in Software
- 4:05What would you hear
- 4:48Stress
- 6:45Use cases
- 7:56Summary
related talks
24mHow Deep Systems Broke Observability
33mEffective observability in microservice architectures
16mThe State of Observability
01mObservability
29mObservability; a gentle introduction
48mObservability or How to Know the State of Your System
50mZen State, and Observability of Your Inner Microservice
09mSetting up Intelligent Observability