Re-Architecting Buffer Management in Lossless Ethernet
- 22 July 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Networking
- Vol. 32 (6) , 4749-4764
Abstract
Converged Ethernet employs Priority-based Flow Control (PFC) to provide a lossless network. However, issues caused by PFC, including victim flow, congestion spreading, and deadlock, impede its large-scale deployment in production systems. The fine-grained experimental observations on switch buffer occupancy find that the root cause of these performance problems is a mismatch of sending rates between end-to-end congestion control and hop-by-hop flow control. Resolving this mismatch requires the switch to provide an additional buffer, which is not supported by the classic dynamic threshold (DT) policy in current shared-buffer commercial switches. In this paper, we propose Selective-PFC (SPFC), a practical buffer management scheme that handles such mismatch. Specifically, SPFC incrementally modifies DT by proactively detecting port traffic and adjusting buffer allocation accordingly to trigger PFC PAUSE frames selectively. Extensive case studies demonstrate that SPFC can reduce the number of PFC PAUSEs on non-bursty ports by up to 69.0%, and reduce the average flow completion time by up to 83.5% for large victim flows.Keywords
Funding Information
- National Key Research and Development Program of China (2022YFB3102301)
- NSFC Projects (61932016, 62132011, 62221003, 62202473)
- China National Funds for Distinguished Young Scientists (62425201)
- China Computer Federation (CCF)-Huawei Populus Euphratica Innovation Research Funding
This publication has 37 references indexed in Scilit:
- P-PFC: Reducing Tail Latency with Predictive PFC in Lossless Data Center NetworksIEEE Transactions on Parallel and Distributed Systems, 2020
- Congestion control in high-speed lossless data center networks: A surveyFuture Generation Computer Systems, 2018
- Analyzing and Enhancing Dynamic Threshold Policy of Data Center SwitchesIEEE Transactions on Parallel and Distributed Systems, 2017
- Bullet trains2013
- Speeding up distributed request-response workflowsACM SIGCOMM Computer Communication Review, 2013
- The only constant is changeACM SIGCOMM Computer Communication Review, 2012
- DeTailACM SIGCOMM Computer Communication Review, 2012
- NetLordACM SIGCOMM Computer Communication Review, 2011
- Data center TCP (DCTCP)ACM SIGCOMM Computer Communication Review, 2010
- CloudAnalyst: A CloudSim-Based Visual Modeller for Analysing Cloud Computing Environments and Applications2010