Millibottlenecks and Their Impact on Cloud Application Performance
Prof. Qingyang Wang
School of Electrical Engineering and Computer Science,
Louisiana State University
In this talk, I will show that millibottlenecks are an important contributing factor to the long-tail latency problem of latency sensitive online services. The first part of the talk is to introduce the potential causes (both system level and application level) of millibottlenecks and their impact of web-facing applications due to the complex inter-dependencies in the system. In the second part of my talk, I will show how millibottlenecks can be exploited by attackers to launch novel DDoS attacks, with the goal of causing significant performance damage to the target system while keeping stealthy, avoiding detection by state-of-the-art DDoS defense tools.
Dr. Qingyang Wang is an Associate Professor in the Department of EECS at Louisiana State University-Baton Rouge. His research is in distributed systems and cloud computing with a current focus on performance, scalability, and security analysis of large-scale web applications (e.g., Amazon.com) and IoT stream processing. He has led research projects at LSU on cloud performance measurements, scalable web application design, and automated system management in clouds. He has collaborated extensively with scientists and researchers from industry companies, including IBM, HP, Amazon, Fujitsu (Japan), Wipro (India), and Huawei (China). He graduated from the College of Computing, Georgia Institute of Technology with a Ph.D. degree in 2014, and has previously received his M.E. and B.E. degrees in computer science and engineering from Chinese Academy of Sciences and Wuhan University in 2007 and 2004, respectively. His work has been published in top system and security venues including Middleware, ICDCS, CCS, USENIX Security, TPDS, etc. He has won or nominated for the Best Paper award and Best Student paper award multiple times in IEEE Cloud Computing conference.