Continuous Profiling
summary
A lightweight system continuously collects CPU and heap samples from running processes so you can inspect a profile from just before an OOM kill, and it reuses Prometheus storage and query model (same service discovery, labels, and query style) to make matching profiles to alerts easy. It captures recurring profiles over time, supports differential analysis to spot where memory accumulates, and is already useful in production as conprof on GitHub and as a practical example of continuous profiling.
AI-written summary · about
related talks
01h 13mContinuous Profiling: The Missing Piece in Your Observability Puzzle
40mContinuous Profiling, the missing piece in your observability puzzle!
24mLeveraging Prometheus’ TSDB for conprof (Continuous Profiling)
28mConprof - Profiling in the cloud-native era
56mContinuous Profiling the missing piece in your observability puzzle
24mCommunity Driven Breakout Session: Continuous Profiling
48mProfiling is for Dev, Monitoring is for Ops – no more!
47mContinuous Profiling — what, why and how