美国亚利桑那州立大学赵明副教授学术讲座
时间:2016-06-15


应计算机学院智能与分布计算实验室邀请,美国亚利桑那州立大学赵明副教授将于2016615日(周三)上午来计算机学院举行学术报告,欢迎广大师生参加。

 

讲座题目:IBIS: Interposed Big-data I/O Scheduler

 

讲座时间:2016615日(周三)上午1000开始

讲座地点:计算机学院会议室(南1433室)

 

主讲人:

Ming Zhao

Associate professor of the Arizona State University (ASU) School of Computing, Informatics, and Decision Systems Engineering (CIDSE)

 

讲座摘要:

Big-data systems are increasingly shared by diverse, data-intensive applications from different domains. However, existing systems lack the support for I/O management, and the performance of big-data applications degrades in unpredictable ways when they contend for I/Os. This talk will introduce IBIS, an Interposed Big-data I/O Scheduler, to address this challenge and provide I/O performance differentiation for competing applications in a shared big-data system.

 

IBIS transparently intercepts, isolates, and schedules an application’s different phases of I/Os via an interposition layer on every datanode of the big-data system. It provides a new proportional-share I/O scheduler, SFQ(D2), to allow applications to share the I/O service of each datanode with good fairness and resource utilization. Moreover, it enables the distributed I/O schedulers to coordinate with one another and achieve proportional sharing of the big-data system’s total I/O service in a scalable manner. The talk will also share the experimental results of IBIS implemented for Hadoop/YARN, a widely used big-data system. The results show that IBIS delivers much stronger performance isolation than native Hadoop/YARN (99% better for WordCount and 15% better for TPC-H queries) with good resource utilization.

 

主讲人简介:

Ming Zhao is an associate professor of the Arizona State University (ASU) School of Computing, Informatics, and Decision Systems Engineering (CIDSE), where he directs the research laboratory for Virtualized Infrastructures, Systems, and Applications (VISA, http://visa.lab.asu.edu). His research is in the areas of experimental computer systems, including distributed/cloud, big-data, and high-performance systems as well as operating systems and storage in general. He is also interested in the interdisciplinary studies that bridge computer systems research with other domains. His work has been funded by the National Science Foundation (NSF), Department of Homeland Security, Department of Defense, Department of Energy, and industry companies, and his research outcomes have been adopted by several production systems in industry. Dr. Zhao has received the NSF Faculty Early Career Development (CAREER) award, the Air Force Summer Faculty Fellowship, the VMware Faculty Award, and the Best Paper Award of the IEEE International Conference on Autonomic Computing. He received his bachelor’s and master’s degrees from Tsinghua University, and his PhD from University of Florida.