NetLock: Fast, Centralized Lock Management Using Programmable Switches
Zhuolong Yu, Yiwen Zhang, Vladimir Braverman, Mosharaf Chowdhury, Xin Jin
Abstract
Lock managers are widely used by distributed systems. Traditional centralized lock managers can easily support policies between multiple users using global knowledge, but they suffer from low performance. In contrast, emerging decentralized approaches are faster but cannot provide flexible policy support. Furthermore, performance in both cases is limited by the server capability.
We present NetLock, a new centralized lock manager that codesigns servers and network switches to achieve high performance without sacrificing flexibility in policy support. The key idea of NetLock is to exploit the capability of emerging programmable switches to directly process lock requests in the switch data plane. Due to the limited switch memory, we design a memory management mechanism to seamlessly integrate the switch and server memory. To realize the locking functionality in the switch, we design a custom data plane module that efficiently pools multiple register arrays together to maximize memory utilization We have implemented a NetLock prototype with a Barefoot Tofino switch and a cluster of commodity servers. Evaluation results show that NetLock improves the throughput by 14.0ś18.4×, and reduces the average and 99% latency by 4.7ś20.3× and 10.4ś18.7× over DSLR, a state-of-the-art RDMA-based solution, while providing flexible policy support.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext ed254ce2-1c8d-4637-9b18-cc725ed908cbCited by top-tier papers32
- CocoSketch: high-performance sketch-based measurement over arbitrary partial key queryYinda Zhang, Zaoxing Liu, Ruixin Wang, Tong Yang et al.SIGCOMM 2021 · 146 citations
- Programmable packet scheduling with a single queueZhuolong Yu, Chuheng Hu, Jingfeng Wu, Xiao Sun et al.SIGCOMM 2021 · 100 citations
- Sherman: A Write-Optimized Distributed B+Tree Index on Disaggregated MemoryQing Wang, Youyou Lu, Jiwu ShuSIGMOD 2022 · 99 citations
- Electrode: Accelerating Distributed Protocols with eBPFYang Zhou, Zezhou Wang, Sowmya Dharanipragada, Minlan YuNSDI 2023 · 78 citations
- Concordia: Distributed Shared Memory with In-Network Cache CoherenceQing Wang, Youyou Lu, Erci Xu, Junru Li et al.FAST 2021 · 74 citations
Builds on2
- Harmonia: Near-Linear Scalability for Replicated Storage with In-Network Conflict DetectionHang Zhu, Zhihao Bai, Jialin Li, Ellis Michael et al.VLDB 2020 · 58 citations
- Scaling Distributed Machine Learning with In-Network AggregationAmedeo Sapio, Marco Canini, Chen-Yu Ho, Jacob Nelson et al.NSDI 2021
Related papers
- ShiftLock: Mitigate One-sided RDMA Lock Contention via HandoverJian Gao, Qing Wang, Jiwu ShuFAST 2025 · 10 citations
- Fast and Scalable In-network Lock Management Using Lock FissionHanze Zhang, Ke Cheng, Rong Chen, Haibo ChenOSDI 2024 · 9 citations
- Citron: Distributed Range Lock Management with One-sided RDMAJian Gao, Youyou Lu, Minhui Xie, Qing Wang et al.FAST 2023 · 13 citations
- Scalable RDMA-accelerated Distributed Locks with Shared Stream AbstractionMiao Cai, Junru Shen, Xiaojian Liao, Rong Gu et al.EuroSys 2026
- FARLock: Asymmetric RDMA Locking Made FairYuehao Hu, Jiatang Zhou, Tianzheng Wang, Keval VoraOSDI 2026
