Introduction to lsuCloud

lsuCloud project is motivated by the essential requirement of simultaneously achieving good performance and high utilization for cost efficiency in cloud computing environments. Good performance (e.g., fast response time) is critical for the business of e-commerce web applications like Amazon. High utilization through virtualization and hardware resource sharing is essential for cloud venders for high return on investment. However, both practitioners and researchers have experienced large response time fluctuations or unpredictable performance in cloud, especially when the utilization becomes high. To solve this problem, our research has been focusing on two aspects: first, investigate various system-level factors that cause the performance unpredictability of web applications running at high resource utilization; second, design, implement, and evaluate practical solutions to mitigate the negative impact of those factors and achieve the performance predictability at high resource utilization.

People

• Faculty

  • Dr. Qingyang Wang

• Research Members

  • Hui Chen, PhD
  • Huasong Shan, PhD
  • Shungeng Zhang, PhD

2018

• Qingyang Wang, Hui Chen, Shungeng Zhang, Liting Hu, and Balaji Palanisamy, “Integrating Concurrency Control in n-Tier Application Scaling Management in the Cloud”, to appear in IEEE Transactions on Parallel and Distributed Systems (IEEE TPDS)

• Shungeng Zhang, Qingyang Wang, and Yasuhiko Kanemasa, “Improving Asynchronous Invocation Performance in Client-server Systems”, in Proc. of the 38th International Conference on Distributed Computing Systems (ICDCS'18), Vienna, Austria, July 2018. (Application track, acceptance rate < 20%)

• Shengsong Yang, Li Pan, Qingyang Wang, and Shijun Liu, “To Sell or Not To Sell: Trading Your Reserved Instances in Amazon EC2 Marketplace”, in Proc. of the 38th International Conference on Distributed Computing Systems (ICDCS'18), Vienna, Austria, July 2018. (Application track, acceptance rate < 20%)

• Brian Peterson, Yalda Fazlalizadeh, Gerald Baumgartner, Qingyang Wang, “A Vector-Scheduling Approach for Running Many-Task Applications in the Cloud”, in Proc. of the 11th International Conference on Cloud Computing (Cloud'18), Seattle, WA, June 2018. (Best Paper Award)

2017

• Huasong Shan, Qingyang Wang, and Calton Pu, “Tail Attacks on Web Applications”, in Proceedings of the 24th ACM Conference on Computer and Communications Security (CCS'17), Dallas, Texas, October 30-November 3, 2017. (Acceptance rate: 151/836=18%)

• Huasong Shan, Qingyang Wang, and Qiben Yan, “Very Short Intermittent DDoS Attacks in an Unsaturated System”, in Proceedings of 13th EAI International Conference on Security and Privacy in Communication Networks (SecureComm'17), Niagara Falls, Canada, October 22-24, 2017. (Acceptance rate: 31/105=29.5%)

• Qingyang Wang, Chien-An Lai, Yasuhiko Kanemasa, Shungeng Zhang, and Calton Pu, “A Study of Long-Tail Latency in n-Tier Systems: RPC vs. Asynchronous Invocations”, in Proc. of the 37th International Conference on Distributed Computing Systems (ICDCS'17), Atlanta, GA, June 2017. (Acceptance rate: 90/531=16.9%)

• Hui Chen, Qingyang Wang, Balaji Palanisamy, and Pengcheng Xiong, “DCM: Dynamic Concurrency Management for Scaling n-Tier Applications in Cloud”, in Proc. of the 37th International Conference on Distributed Computing Systems (ICDCS'17), Atlanta, GA, June 2017. (accepted as a short paper)

• Chien-An Lai, Joshua Kimball, Tao Zhu, Qingyang Wang, and Calton Pu, “milliScope: a Fine-Grained Monitoring Framework for Performance Debugging of n-Tier Web Services", in Proc. of the 37th International Conference on Distributed Computing Systems (ICDCS'17), Atlanta, GA, June 2017. (Acceptance rate: 90/531=16.9%)

• Tao Zhu, Jack Li, Josh Kimball, Junhee Park, Chien-An Lai, Calton Pu and Qingyang Wang, "Limitations of Load Balancing Mechanisms for N-Tier Systems in the Presence of Millibottlenecks", in Proc. of the 37th International Conference on Distributed Computing Systems (ICDCS'17), Atlanta, GA, June 2017. (Application track)

• Chui-Hui Chiu, Dipak Kumar Singh, Qingyang Wang, and Seung-Jong Park, "Coflourish: An SDN-Assisted Coflow Scheduling Framework for Clouds", in Proc. of the 10th International Conference On Cloud Computing (Cloud'17), Honolulu, Hawaii, June 2017. (Acceptance rate: 18%)

• Chui-Hui Chiu, Dipak Kumar Singh, Qingyang Wang, Kisung Lee, and Seung-Jong Park, "Minimal Coflow Routing and Scheduling in OpenFlow-based Cloud Storage Area Networks", in Proc. of the 10th International Conference On Cloud Computing (Cloud'17), Honolulu, Hawaii, June 2017.

• Li Pan, Qingyang Wang, Liang Li, Shijun Liu, and Dahui Chen, "An Experimental Study of the Impact of vCPU Provisioning on the Performance of a 2-Tier Application Running in Cloud", in Proc. of the 10th International Conference On Cloud Computing (Cloud'17), Honolulu, Hawaii, June 2017. (Application track)

• Jinlai Xu and Balaji Palanisamy, Heiko Ludwig, and Qingyang Wang, "Zenith: Utility-aware Resource Allocation for Edge Computing", in Proc. of 1st IEEE International Conference on Edge Computing (IEEE EDGE 2017), Honolulu, Hawaii, June 2017.

2016

• Junhee Park, Qingyang Wang Jack Li, Chien-An Lai, Tao Zhu, Calton Pu, “Performance Interference of Memory Thrashing in Virtualized Cloud Environments: A Study of consolidated n-Tier Applications” In Proc. of the 9th International Conference On Cloud Computing (Cloud'16), San Francisco, USA, July 2016. (Acceptance rate: 15%) (Runner-Up for Best Paper Award)

2015

• Qi Fan, Qingyang Wang, “Performance Comparison of Web Servers with Different Architectures: A Case Study using High Concurrency Workload”, In Proc. of the 3rd IEEE Workshop on Hot Topics in Web Systems and Technologies (HotWeb'15), Washington, D.C., USA, November 2015.

• Brian Peterson, Gerald Baumgartner, Qingyang Wang, “A Hybrid Cloud Framework for Scientific Computing”, In Proc. of the 8th International Conference On Cloud Computing (Cloud'15), New York City, USA, July 2015. (Acceptance rate: 15%)

2014

• Qingyang Wang, Yasuhiko Kanemasa, Jack Li,Chien-An Lai, Chien-An Cho, Yuji Nomura, Calton Pu, “Lightning in the Cloud: A Study of Very Short Bottlenecks on n-Tier Web Application Performance”, In Proc. of USENIX Conference on Timely Results in Operating Systems (TRIOS'14), co-located with OSDI’14, Colorado, USA, October 2014. [presentation]

• Jack Li, Qingyang Wang, Chien-An Lai, Junhee Park, Daisaku Yokoyama, Calton Pu, “The Impact of Software Resource Allocation on Consolidated n-Tier Applications”, In Proc. of the 7th International Conference On Cloud Computing (Cloud'14), Alaska, USA, June 2014.(Acceptance rate: 20%)

• Chien-An Lai, Qingyang Wang, Josh Kimball,Jack Li, Junhee Park, Calton Pu, “IO Performance Interference among Consolidated n-Tier Applications: Sharing is Better than Isolation for Disks”, In Proc. of the 7th International Conference On Cloud Computing (Cloud'14), Alaska, USA June 2014.(Acceptance rate: 20%)

This research has been partially funded by National Science Foundation by CISE’s CNS (1566443), Louisiana Board of Regents under grant LEQSF(2015-18)-RD-A-11, and grants, or contracts from Fujitsu Labs.