IEEE INFOCOM 2023
Datacenter and Switches
Dynamic Demand-Aware Link Scheduling for Reconfigurable Datacenters
Kathrin Hanauer, Monika Henzinger, Lara Ost and Stefan Schmid (University of Vienna, Austria)
This paper proposes a dynamic algorithms approach to improve the performance of reconfigurable datacenter networks, by supporting faster reactions to changes in the traffic demand. This approach leverages the temporal locality of traffic patterns in order to update the interconnecting matchings incrementally, rather than recomputing them from scratch. In particular, we present six (batch-)dynamic algorithms and compare them to static ones. We conduct an extensive empirical evaluation on 176 synthetic and 39 real-world traces, and find that dynamic algorithms can both significantly improve the running time and reduce the number of changes to the configuration, especially in networks with high temporal locality, while retaining matching quality.
Speaker Kathrin Hanauer (University of Vienna)
Kathrin Hanauer is an assistant professor at the University of Vienna, Austria. She obtained her PhD in 2018 from the University of Passau, Germany. Her research interests include the design, analysis, and experimental evaluation of algorithms and their engineering, especially for graph algorithms and dynamic algorithms.
Scalable Real-Time Bandwidth Fairness in Switches
Robert MacDavid, Xiaoqi Chen and Jennifer Rexford (Princeton University, USA)
We propose Approximate Hierarchical Allocation of Bandwidth (AHAB), a per-user bandwidth limit enforcer that runs fully in the data plane of commodity switches. AHAB tracks each user's approximate traffic rate and compares it against a bandwidth limit, which is iteratively updated via a real-time feedback loop to achieve max-min fairness across users. Using a novel sketch data structure, AHAB avoids storing per-user state, and therefore scales to thousands of slices and millions of users. Furthermore, AHAB supports network slicing, where each slice has a guaranteed share of the bandwidth that can be scavenged by other slices when under-utilized. Evaluation shows AHAB can achieve fair bandwidth allocation within 3.1ms, 13x faster than prior data-plane hierarchical schedulers.
Speaker Xiaoqi Chen (Princeton University)
Xiaoqi Chen (https://cs.princeton.edu/~xiaoqic) is a final year Ph.D. student in the Department of Computer Science, Princeton University, advised by Prof. Jennifer Rexford. His research focuses on designing efficient algorithms for high-speed traffic processing in the network data plane, to improve the performance, reliability, and security of future networks.
Protean: Adaptive Management of Shared-Memory in Datacenter Switches
Hamidreza Almasi, Rohan Vardekar and Balajee Vamanan (University of Illinois at Chicago, USA)
periods of time. We implemented Protean in today's programmable switches and demonstrate their high performance with negligible overhead. Our at-scale ns-3 simulations show that Protean
reduces the tail latency by a factor of 5 over DT on average across varying loads with realistic workloads.
Speaker Hamidreza Almasi (University of Illinois at Chicago)
Hamid is a final year Ph.D. candidate in Computer Science at the University of Illinois Chicago advised by Prof. Balajee Vamanan. He received his B.Sc. degree from University of Tehran and his M.Sc. from Sharif University of Technology. His research interests lie in the areas of datacenter networks, system efficiency for distributed machine learning, and programmable networks.
Designing Optimal Compact Oblivious Routing for Datacenter Networks in Polynomial Time
Kanatip Chitavisutthivong (Vidyasirimedhi Institute of Science and Technology, Thailand); Chakchai So-In (Khon Kaen University, Thailand); Sucha Supittayapornpong (Vidyasirimedhi Institute of Science and Technology, Thailand)
Speaker Sucha Supittayapornpong (Vidyasirimedhi Institute of Science and Technology)
Sucha Supittayapornpong is a faculty member in the School of Information Science and Technology at Vidyasirimedhi Institute of Science and Technology, Thailand. He received his Ph.D. in Electrical Engineering from the University of Southern California. His research interests include datacenter networking, performance optimization, and operations research.
Memory/Cache Management 1
ISAC: In-Switch Approximate Cache for IoT Object Detection and Recognition
Wenquan Xu and Zijian Zhang (Tsinghua University, China); Haoyu Song (Futurewei Technologies, USA); Shuxin Liu, Yong Feng and Bin Liu (Tsinghua University, China)
Speaker Wenquan Xu (Tsinghua University)
A Phd student from Tsinghua University, whose research areas are data center networks, programmable network, and in-network computing.
No-regret Caching for Partial-observation Regime
Zifan Jia (Institute of Information Engineering, University of Chinese Academy of Sciences, China); Qingsong Liu (Tsinghua University, China); Xiaoyan Gu (Institute of Information Engineering, Chinese Academy of Sciences, China); Jiang Zhou (Chinese Academy of Sciences, China); Feifei Dai (University of Chinese Academy of Sciences, China); Bo Li and Weiping Wang (Institute of Information Engineering, Chinese Academy of Sciences, China)
Speaker Qingsong Liu (Tsinghua University, China)
Qingsing Liu received the B.Eng. degree in electronic engineering from Tsinghua University, China. Now he is currently pursuing the Ph.D. degree with the Institute for Interdisciplinary Information Sciences (IIIS) of Tsinghua University. His research interests include online learning, and networked and computer systems modeling and optimization. He has published several papers in IEEE Globecom, IEEE ICASSP, IEEE WiOpt, IEEE INFOCOM, ACM/IFIP Performance, and NeurIPS
CoLUE: Collaborative TCAM Update in SDN Switches
Ruyi Yao and Cong Luo (Fudan University, China); Hao Mei (Fudan University); Chuhao Chen (Fudan University, China); Wenjun Li (Harvard University, USA); Ying Wan (China Mobile (Suzhou) Software Technology Co., Ltd, China); Sen Liu (Fudan University, China); Bin Liu (Tsinghua University, China); Yang Xu (Fudan University, China)
Speaker Ruyi Yao (Fudan University)
Ruyi Yao received her B.Sc. in 2020 from Nanjing University of Posts and Telecommunications. She is currently pursuing the Ph.D. degree from School of Computer science, Fudan University, Shanghai, China. Her research interests include software defined networking, programmable data plane, and Network Measurement and Management.
Scalable RDMA Transport with Efficient Connection Sharing
Jian Tang and Xiaoliang Wang (Nanjing University, China); Huichen Dai (Huawei, China); Huichen Dai (Tsinghua University, China)
Speaker Jian Tang (Nanjing University)
Jian Tang is a master's student at Nanjing University, China. He is interested in identifying fundamental system design and performance optimization issues in large-scale cloud and distributed network systems and searching for generally applicable, efficient, and easily implementable solutions.
FlowBench: A Flexible Flow Table Benchmark for Comprehensive Algorithm Evaluation
Zhikang Chen (Tsinghua University, China); Ying Wan (China Mobile (Suzhou) Software Technology Co., Ltd, China); Ting Zhang (Tsinghua University, China); Haoyu Song (Futurewei Technologies, USA); Bin Liu (Tsinghua University, China)
Speaker Zhikang Chen (Tsinghua University)
A master student studying Computer Science and Technology in Tsinghua University.
On Data Processing through the Lenses of S3 Object Lambda
Pablo Gimeno-Sarroca and Marc Sánchez Artigas (Universitat Rovira i Virgili, Spain)
Speaker Pablo Gimeno-Sarroca (Universitat Rovira i Virgili)
Pablo Gimeno-Sarroca is a second year PhD student at Universitat Rovira i Virgili (Spain). He received his B.S. degree in Computer Engineering from Universitat Rovira i Virgili in 2020 and his M.S. degree in Mathematical and Computational Engineering from Universitat Oberta de Catalunya and Universitat Rovira i Virgili in 2021. His current research interests mainly focus on serverless computing, stream data processing and machine learning.
DUNE: Improving Accuracy for Sketch-INT Network Measurement Systems
Zhongxiang Wei, Ye Tian, Wei Chen, Liyuan Gu and Xinming Zhang (University of Science and Technology of China, China)
Speaker Wei Chen(University of Science and Technology of China)
Wei Chen is a Ph.D student in the department of Computer Science and Technology, University of Science and Technology of China. He is supervised by Prof. Ye Tian. He received the bachelor’s degree in University of Science and Technology of China in 2020. His research interests include network measurement and management.
Search in the Expanse: Towards Active and Global IPv6 Hitlists
Bingnan Hou and Zhiping Cai (National University of Defense Technology, China); Kui Wu (University of Victoria, Canada); Tao Yang and Tongqing Zhou (National University of Defense Technology, China)
Speaker Bingnan Hou (National University of Defense Technology)
Bingnan Hou received the bachelor’s and master’s degrees in Network Engineering from Nanjing University of Science and Technology, China, in 2010 and 2015, respectively, and the Ph.D degree in Computer Science and Technology from National University of Defense Technology, China, in 2022. His research interests include network measurement and network security.