DAMON Recipes: Ways to Save Memory Using a Linux Kernel Subsystem in the Real World
summary
DAMON is a kernel access-pattern snapshotter (mainline since v5.15) with a userspace toolchain that monitors virtual/physical ranges and applies actions. Deployments report 3–4% CPU overhead while profiling and driving policies via the daemon/CLI and YAML policies. Lab experiments show protecting hot pages with mlock yields 2.3× speedup in artificial pressure, and CXL migration using HM SDK reports up to 12.9% speedup, 18.8% worst-case slowdown when pages land on CXL.
AI-written summary · about
chapters (8)
- 0:00DAMON introduction
- 1:03DAMON core features
- 5:35DAMON recipes overview
- 6:38Recipe: Access profiling
- 11:15Recipe: Memory reclamation
- 16:49Recipe: CXL tiering with SK Hynix
- 31:29DAMON community
- 35:48Summary
related talks
42mDAMON Recipes: Ways to Save Memory Using a Linux Kernel Subsystem in the Real World
52mDAMON, DAMOS, and DAMO: Kernel Subsystems and User-Space Tools for Data Access...
47mDAMO[N,S]?: Implementing Self-Driven Data Access-Aware Efficient Linux System
46mDAMON Current Status and Future Plans
48mData Access Monitoring Operator (DAMO): User-Space Tool/Python Library for Access-Aware Profiling and Optimization of Your Linux Systems
45mCurrent Status and Future Plans of DAMON
31mHMSDK: Enhancing Software Support for CXL Memory
17mDSA-2LM: A CPU-Free Tiered Memory Architecture with Intel DSA