Facebook open-sources new suite of Linux kernel components and tools

This post introduces a suite of open-source Linux kernel components and tools developed at Facebook to address critical fleet management issues in large-scale cloud computing. Key contributions include: BPF for safe and flexible kernel code execution (used in Katran load balancer), Btrfs as a next-generation filesystem for fault tolerance and administration (improving I/O control with cgroup2), Netconsd for lightweight UDP-based netconsole logging, Cgroup2 for advanced workload grouping and resource control (driving multi-tenancy and isolation), PSI for quantifying resource shortages (memory, CPU, I/O) to enable proactive responses, and Oomd as a userspace OOM killer with greater context awareness. These components are in production across Facebook's infrastructure and are now available to the open-source community.
More from the Scalability and Large-Scale Systems Engineering trail
- Open-Sourcing Rebalancer: A Generic, High-Performance Library for Solving Assignment Problems
- ZGateway: Learnings from Putting a Proxy in Front of ZippyDB
- MTIA 300: Meta’s First Training Chip with Built-in NICs and Communication-Offloading Engines
- From User Sequences to Scaling Laws: A Multi-Stage Architecture for Meta’s Ads Ranking
- GEM Training: How Meta Doubled the Efficiency of Its LLM-Scale Ads Foundation Model