Just in time delivery: Leveraging operating systems knowledge for better datacenter congestion control
Name
chimera-hotcloud19.pdf
Description
Accepted version
Size
141.02 KB
Format
Adobe PDF
Checksum (MD5)
59689ecaacc813f03924ecfb4cff1b06
Author(s)
Ousterhout, Amy Elizabeth
Belay, Adam M
Zhang, I
Date Issued
July 2019
Journal
11th USENIX Workshop on Hot Topics in Cloud Computing, HotCloud 2019, co-located with USENIX ATC 2019
Publisher
USENIX Association
Citation
Ousterhout, Amy et al. "Just in time delivery: Leveraging operating systems knowledge for better datacenter congestion control." 11th USENIX Workshop on Hot Topics in Cloud Computing, HotCloud 2019, co-located with USENIX ATC 2019, July 2019, Renton, Washington, USENIX Association, July 2019. © 2019 USENIX Association
Version
Author's final manuscript
Abstract
Network links and server CPUs are heavily contended resources in modern datacenters. To keep tail latencies low, datacenter operators drastically overprovision both types of resources today, and there has been significant research into effectively managing network traffic [4, 19, 21, 29] and CPU load [22, 27, 32]. However, this work typically looks at the two resources in isolation. In this paper, we make the observation that, in the datacenter, the allocation of network and CPU resources should be co-designed for the most efficiency and the best response times. For example, while congestion control protocols can prioritize traffic from certain flows, this provides no benefit if the traffic arrives at an overloaded server that will only queue the request. This paper explores the potential benefits of such a co-designed resource allocator and considers the recent work in both CPU scheduling and congestion control that is best suited to such a system. We propose a Chimera, a new datacenter OS that integrates a receiver-based congestion control protocol with OS insight into application queues, using the recent Shenango operating system [32].
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://www.usenix.org/conference/hotcloud19/presentation/ousterhout
