CAREER: Enable Robust Virtualized Hosting Infrastructures via Coordinated Learning, Recovery, and Diagnosis

Large-scale virtualized hosting infrastructures have become the fundamental platforms for many real world systems such as cloud computing infrastructures, enterprise data centers, educational computing platforms, and data-intensive computing systems. However, due to their inherent complexity and sharing nature, hosting infrastructures are prone to various performance anomalies caused by software bugs or hardware failures.

The overarching objective of this proposal is to systematically explore innovative runtime reliability management techniques for large-scale virtualized hosting infrastructures. Our research focuses on handling performance anomalies in distributed systems that are often very difficult to reproduce offline. The PI plans to combine the power of online learning, knowledge-driven first-response recovery, and in-situ diagnosis to handle unexpected system anomalies more efficiently and effectively. She aims at transforming the runtime system anomaly management from a trial-and-error guessing game into an efficient knowledge-driven self-healing process.

Techniques developed in this project will generate significant impact on improving the reliability and diagnosability of many real world hosting infrastructure systems. The PI plans to develop new course modules and programming courseware based on the research prototype developed in this project. The prototype developed in this project will be applied to the Virtual Computing Lab at NCSU, an educational computing platform for K-12, community colleges and universities. She will also disseminate her results and collected data broadly through publication and technology transfer. Developed software artifacts and experimental datasets will also be released for public use.