Completed
SKQ vs. Kernel Bypass: Uniform 10 ps Workload
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
SKQ - Event Scheduling for Optimizing Tail Latency in a Traditional OS Kernel
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 SKQ: Event Scheduling for Optimizing Tail Latency in a Traditional OS Kernel
- 3 The Latency Problem
- 4 Sources of Latency
- 5 Event-Driven Programming Models
- 6 SKQ Usage
- 7 SKQ Architecture
- 8 Scalability Showdown: SKQ vs. Kqueue
- 9 Performance Improvement: SKQ vs. Kqueue
- 10 Scheduling Policies
- 11 Challenges of Efficient Event Scheduling
- 12 Cache Locality Policies in Memcached
- 13 CPU Affinity vs. Queue Affinity
- 14 Imbalanced Workload: RocksDB
- 15 Load Balancing Policies
- 16 Hybrid Policies
- 17 SKQ vs. Kernel Bypass: Uniform 10 ps Workload
- 18 SKQ vs. Kernel Bypass: Zipf-like Workload
- 19 Policy Selection Guidelines
- 20 Conclusion
