Detecting and Resolving PFC Deadlocks with ITSY Entirely in the Data Plane
Xinyu Crystal Wu, T. S. Eugene Ng
摘要
The Priority-based Flow Control (PFC) protocol is adopted to guarantee zero packet loss in many high-performance data centers. PFC, however, can induce deadlocks and in severe cases cause the entire network to be blocked. Existing solutions have focused on deadlock avoidance; unfortunately, they are not foolproof. Therefore, deadlock detection is a necessity. We propose ITSY, a novel system that correctly detects and resolves deadlocks entirely in the data plane. It works with any network topologies and routing algorithms. Unique to ITSY is the use of deadlock initial triggers, which contributes to efficient deadlock detection, mitigation, and recurrence prevention. ITSY provides three deadlock resolution mechanisms with different trade-off options. We implement ITSY for programmable switches in the P4 language. Experiments show that ITSY detects and resolves deadlocks rapidly with minimal overheads.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper3
- Empowering Azure Storage with RDMAWei Bai, Shanim Sainul Abdeen, Ankit Agrawal, Krishan Kumar Attre 等NSDI 2023 · 被引用 117 次
- Flattened Clos: Designing High-performance Deadlock-free Expander Data Center Networks Using Graph ContractionShizhen Zhao, Qizhou Zhang, Peirui Cao, Xiao Zhang 等NSDI 2023 · 被引用 9 次
- Hawkeye: Diagnosing RDMA Network Performance Anomalies with PFC ProvenanceShicheng Wang, Menghao Zhang, Xiao Li, Qiyang Peng 等SIGCOMM 2025 · 被引用 7 次
它引用的顶会 Paper5
- Re-architecting Congestion Management in Lossless EthernetWenxue Cheng, Kun Qian, Wanchun Jiang, Tong Zhang 等NSDI 2020 · 被引用 100 次
- Programmable packet scheduling with a single queueZhuolong Yu, Chuheng Hu, Jingfeng Wu, Xiao Sun 等SIGCOMM 2021 · 被引用 100 次
- Understanding, Detecting and Localizing Partial Failures in Large System SoftwareChang Lou, Peng Huang, Scott SmithNSDI 2020 · 被引用 88 次
- Config2Spec: Mining Network Specifications from Network ConfigurationsRüdiger Birkner, Dana Drachsler-Cohen, Laurent Vanbever, Martin T. VechevNSDI 2020 · 被引用 67 次
- Finding Network Misconfigurations by Automatic Template InferenceSiva Kesava Reddy K., Alan Tang, Ryan Beckett, Karthick Jayaraman 等NSDI 2020 · 被引用 53 次
相关 Paper
- Pitstop: Enabling a Virtual Network Free Network-on-ChipHossein Farrokhbakht, Henry Kao, Kamran Hasan, Paul V. Gratz 等HPCA 2021 · 被引用 29 次
- Towards timeout-less transport in commodity datacenter networksHwijoon Lim, Wei Bai, Yibo Zhu, Youngmok Jung 等EuroSys 2021 · 被引用 28 次
- FLB: Fine-grained Load Balancing for Lossless Datacenter NetworksJinbin Hu, Wenxue Li, Xiangzhou Liu, Junfeng Wang 等USENIX ATC 2025 · 被引用 10 次
- NetRT: Enhancing RDMA with Retransmission Offloading in Data Center NetworksWentao Wang, Jiangping Han, Kaiping Xue, Jian Li 等INFOCOM 2025 · 被引用 3 次
- DRAIN: Deadlock Removal for Arbitrary Irregular NetworksMayank Parasar, Hossein Farrokhbakht, Natalie D. Enright Jerger, Paul V. Gratz 等HPCA 2020 · 被引用 34 次
