I build networked systems. My current research focuses on mitigating unfair network flows and preventing incast traffic bursts in a datacenter, from the receiver's point of view. Previously, I architected transport protocols for hybrid packet/circuit networks, built machine learning systems for processing streaming video data at the edge, and developed new software architectures for big data analytics that put performance clarity first. I have a longstanding collaboration with Meta's Host Networking Team.
Summer & Fall 2023 @ Meta Host Networking Team: I evaluated congestion control techniques for Meta's AI training clusters and wrote a research paper about our work on mitigating incast microbursts.
Summer & Fall 2022 @ Meta Host Networking Team: I developed delay-based congestion control algorithms and techniques for mitigating incast microbursts in datacenter networks.
Fall 2021: I was a full instructor (with Professor Peter Steenkiste) for CMU's 15-441/641 Networking and the Internet course. I gave seven lectures, created the homework assignments, managed the three projects, and supervised the four teaching assistants.
Summer & Fall 2021 @ Meta Host Networking Team: I contributed to the development of techniques for preventing incast microbursts in datacenter networks.
From 2016-2019, I managed a student team in the Intel Science and Technology Center for Visual Cloud Systems, where we built systems for machine learning on edge devices under the guidance of Professor Dave Andersen and Michael Kaminsky. From 2014-2016, I built big data analytics systems with Kay Ousterhout and Professors Sylvia Ratnasamy and Scott Shenker in the NetSys Lab. I earned a B.S. in Electrical Engineering and Computer Science from UC Berkeley in 2015 and an M.S. in Computer Science from CMU in 2021.
I am from San Diego, CA.
Publications Google Scholar
Time-division TCP for reconfigurable data center networks SIGCOMM 2022
Shawn Shuoshuo Chen, Weiyang Wang, Christopher Canel, Srinivasan Seshan, Alex C. Snoeren, Peter Steenkiste
Watching the watchmen: Least privilege for managed network services HotNets 2021
Guyue Liu, Ao Li, Christopher Canel, Vyas Sekar
Adapting TCP for reconfigurable datacenter networks NSDI 2020
Matthew K. Mukerjee, Christopher Canel, Weiyang Wang, Daehyeok Kim, Srinivasan Seshan, Alex C. Snoeren
Scaling video analytics on constrained edge nodes SysML 2019
Christopher Canel, Thomas Kim, Giulio Zhou, Conglong Li, Hyeontaek Lim, David G. Andersen, Michael Kaminsky,
Subramanya R. Dulloor
Mainstream: Dynamic stem-sharing for multi-tenant video processing USENIX ATC 2018
Angela Jiang, Daniel L.-K. Wong, Christopher Canel, Lilia Tang, Ishan Misra, Michael Kaminsky,
Michael A. Kozuch, Padmanabhan Pillai, David G. Andersen, Gregory R. Ganger
Monotasks: Architecting for performance clarity in data analytics frameworks SOSP 2017
Kay Ousterhout, Christopher Canel, Sylvia Ratnasamy, Scott Shenker
Performance clarity as a first-class design principle HotOS 2017
Kay Ousterhout, Christopher Canel, Max Wolffe, Sylvia Ratnasamy, Scott Shenker