Core Concepts
JIAGU introduces innovative techniques to harmonize efficiency with practicability in serverless computing, improving resource utilization while maintaining QoS.
Abstract
Jiagu focuses on optimizing resource utilization in serverless computing by introducing novel techniques like pre-decision scheduling and dual-staged scaling. It addresses challenges such as overcommitment, autoscaling, and cold start overheads. The paper evaluates Jiagu's performance using real-world applications and traces from Huawei Cloud, showing significant improvements in deployment density and reduced scheduling costs.
Stats
54.8% improvement in deployment density over commercial clouds (with Kubernetes)
81.0%–93.7% lower scheduling costs
57.4%–69.3% reduction in cold start latency compared to existing QoS-aware schedulers
Quotes
"Current serverless platforms struggle to optimize resource utilization due to their dynamic and fine-grained nature."
"JIAGU harmonizes efficiency with practicability through two novel techniques: pre-decision scheduling and dual-staged scaling."
"Our evaluation shows a significant improvement in deployment density over commercial clouds while maintaining QoS."