Transfer learning-based co-run scheduling for heterogeneous dataceners

Authors

Wei Kuang, Michigan Technological UniversityFollow
Laura E. Brown, Michigan Technological UniversityFollow
Zhenlin Wang, Michigan Technological UniversityFollow

Document Type

Article

Publication Date

2015

Department

Department of Computer Science; Center for Data Sciences; Center for Scalable Architectures and Systems

Abstract

Today’s data centers are designed with multi-core CPUs where multiple virtual machines (VMs) can be co-located into one physical machine or distribute multiple computing tasks onto one physical machine. The result is co-tenancy, resource sharing and competition. Modeling and predicting such co-run interference becomes crucial for job scheduling and Quality of Service assurance. Co-locating interference can be characterized into two components, sensitivity and pressure, where sensitivity characterizes how an application’s own performance is affected by a co-run application, and pressure characterizes how much contentiousness an application exerts/brings onto the memory subsystem. Previous studies show that with simple models, sensitivity and pressure can be accurately characterized for a single machine. We extend the models to consider cross-architecture sensitivity (across different machines).

Publisher's Statement

© 2015 Association for the Advancement of ArtificialIntelligence. Publisher's version of record: https://www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/view/9332

Publication Title

Twenty-Ninth AAAI Conference on Artificial Intelligence

Recommended Citation

Kuang, W., Brown, L. E., & Wang, Z. (2015). Transfer learning-based co-run scheduling for heterogeneous dataceners. Twenty-Ninth AAAI Conference on Artificial Intelligence.
Retrieved from: https://digitalcommons.mtu.edu/michigantech-p/740