About
Runhui Li is a storage expert at Sangfor Technologies. He was a researcher in Huawei Future Network Lab (Hong Kong) and a Postdoc Fellow in Chinese University of Hong Kong. He has been working on big data processing and storage. He has over five-year's experience of hacking source codes of Hadoop. His research results have been published in top conferences like USENIX ATC, USENIX FAST. Currently, he is also working on key-value storage and distributed consensus algorithms.
Runhui received his PhD degree from the Department of Computer Science and Engineering, the Chinese University of Hong Kong, and his BEng degree in Computer Science from School of Computer Science and Technology, University of Science and Technology of China (USTC). He was supervised by Professor Patrick P.C. Lee and Professor John C.S. Lui during his PhD studies.
Download his CV in English or in Chinese. Visit his GitHub page to see his previous projects.
Contacts
Email: lrhdiy@gmail.com
Address: Unit 335-337, Core Bldg, Hong Kong Science Park, Sha Tin, N.T., Hong Kong
Projects and Open Sourced Softwares
Recovery-oriented STAIR Code | GitHub repository EAR: Encoding-Aware Replication | GitHub repository Degraded-First Task Scheduler | GitHub repository CORE: Concurrent Recovery of Regenerating Codes NCFS: Network-Coding File SystemYou can find part of the projects I have worked on in my GitHub page. You can also find some facilitating projects from that page. I typically keep the on-going projects as private repositories, but will make them public once the corresponding research papers are published.
Interests
Big data storage and processing systems (e.g., HDFS, MapReduce, Spark, etc.), In-memory storage (e.g., Memcached, Redis)
PhD Thesis Title: Enabling Efficient and Dependable Clustered File Systems through New Erasure Coding Techniques
Publications
-
Xiaolu Li, Runhui Li, Patrick P. C. Lee, and Yuchong Hu
"OpenEC: Toward Unified and Configurable Erasure Coding Management in Distributed Storage Systems."
USENIX FAST 2019, Boston, MA, USA, Febrary 2019.
Credit: I am corresponding author of this paper, owner of original idea and initial system design.
-
Qun Huang, Xin Jin, Patrick P. C. Lee, Runhui Li, Lu Tang, Yi-Chao Chen and Gong Zhang
"SketchVisor: Robust Network Measurement for Software Packet Processing."
ACM SIGCOMM 2017, Los Angeles, California, July 2017.
-
Runhui Li, Xiaolu Li, Patrick P. C. Lee and Qun Huang
"Repair Pipelining for Erasure-Coded Storage."
The 2017 USENIX Annual Technical Conference (ATC'17), Santa Clara, California, July 2017.
-
Eman Ramadan, Arvind Narayanan, Zhi-Li Zhang, Runhui Li and Gong Zhang
"BIG Cache Abstraction for Cache Networks."
The 37th IEEE International Conference on Distributed Computing Systems (ICDCS'17), Atlanta, Georgia, June 2017.
-
Runhui Li, Yuchong Hu, and Patrick P. C. Lee.
"Enabling Efficient and Reliable Transition from Replication to Erasure Coding for Clustered File Systems."
Accepted for publication in Transactions on Parallel and Distributed Systems (TPDS).
-
Mingqiang Li, Runhui Li, Patrick P. C. Lee
"Relieving Both Storage and Recovery Burdens in Big Data Clusters with R-STAIR Codes."
Poster presentation: USENIX Annual Technical Conference (ATC'15), July 2015.
-
Runhui Li, Jian Lin, and Patrick P. C. Lee.
"Enabling Concurrent Failure Recovery for Regenerating-Coding-Based Storage Systems: From Theory to Practice."
IEEE Transactions on Computers (TC) 64(7), pp. 1898-1911, July 2015.
(An earlier version appeared in MSST 2013)
[main pdf] [supplementary pdf] [software]
-
Runhui Li, Yuchong Hu, and Patrick P. C. Lee.
"Enabling Efficient and Reliable Transition from Replication to Erasure Coding for Clustered File Systems."
Proceedings of the 45th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN'15) (Regular paper), Rio de Janeiro, Brazil, June 2015.
(AR: 50/229 = 21.8%)
-
Runhui Li and Patrick P. C. Lee.
"Making MapReduce Scheduling Effective in Erasure-Coded Storage Clusters."
Proceedings of the 21st IEEE International Workshop on Local and Metropolitan Area Networks (LANMAN'15) (Invited paper), Beijing, China, April 2015.
-
Runhui Li, Patrick P. C. Lee, Yuchong Hu.
"Degraded-First Scheduling for MapReduce in Erasure-Coded Storage Clusters."
Proceedings of the 44th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN'14) (Regular paper), Atlanta, Georgia, June 2014.
-
Silei Xu, Runhui Li, Patrick P. C. Lee, Yunfeng Zhu, Liping Xiang, Yinlong
Xu, John C. S. Lui
"Single Disk Failure Recovery for X-code-based Parallel Storage Systems."
IEEE Transactions on Computers (TC), 63(4), pp. 995-1007, April 2014.
[pdf] [doi]
-
Runhui Li, Jian Lin, Patrick P. C. Lee
"CORE: Augmenting Regenerating-Coding-Based Recovery for Single and Concurrent Failures in Distributed Storage Systems."
Proceedings of the 29th IEEE Conference on Massive Data Storage (MSST 2013) (Short paper), Long Beach, CA, May 2013.
(AR: (14+15)/109 = 26.6%)
[pdf] [pptx] [tech report] [software]
-
Liping Xiang, Yinlong Xu, John Lui, Qian Chang, Yubiao Pan, Runhui Li
"A Hybrid Approach to Failed Disk Recovery Using RAID-6 Codes: Algorithm and Performance Evaluation."
ACM Transactions on Storage (ToS), 7(3):11, October 2011.
[pdf] [doi]