rtla osnoise: what is missing?
summary
An rtla/osnoise tracer runs a per-CPU busy-loop tracer that detects latency spikes by comparing time reads against a threshold, then correlates each spike with kernel tracepoints (IRQ, NMI, softirq, thread) and nested causality to attribute stolen microseconds. It uses lockless kernel counters to count exact contributing events, reports hardware vs hypervisor-origin noise, and currently needs IPI send/entry tracepoints to know who raised IPIs, a guest‑host trace merging path and a user‑workload PID interface to monitor arbitrary tasks.
AI-written summary · about
chapters (5)
- 0:00Introduction to osnoise
- 6:25Current tracer limitations
- 19:10Missing IPI tracing support
- 25:13Hypervisor integration needs
- 27:45Q&A and summary
related talks
21mRTLA Requests and TODOs
50mrtla timerlat: Debugging Real-Time Linux Scheduling Latency
51mRTLA Timerlat - the next step in scheduling latency analysis
49mDebugging Methodologies for Realtime Issues in Linux Systems
47mReal-Time Linux: What Is Next?
26mReal-time Linux: what is next?
59mProposing a new tracer to monitor RT task behavior
40mRT Linux in Safety-Critical Systems: The Potential and the Challenges