TreeSLS: A Whole-system Persistent Microkernel with Tree-structured State Checkpoint on NVM
Fangnuo Wu, Mingkai Dong, Gequan Mo, Haibo Chen
摘要
Whole-system persistence promises simplified application deployment and near-instantaneous recovery. This can be implemented using single-level store (SLS) through periodic checkpointing of ephemeral state to persistent devices. However, traditional SLSs suffer from two main issues on checkpointing efficiency and external synchrony, which are critical for low-latency services with persistence need.
In this paper, we note that the decentralized state of microkernel-based systems can be exploited to simplify and optimize state checkpointing. To this end, we propose TreeSLS, a whole-system persistent microkernel that simplifies the whole-system state maintenance to a capability tree and a failure-resilient checkpoint manager. TreeSLS further exploits the emerging non-volatile memory to minimize checkpointing pause time by eliminating the distinction between ephemeral and persistent devices. With efficient state maintenance, TreeSLS further proposes delayed external visibility to provide transparent external synchrony with little overhead. Evaluation on microbenchmarks and real-world applications (e.g., Memcached, Redis and RocksDB) show that TreeSLS can complete a whole-system persistence in around 100 𝜇s and even take a checkpoint every 1 ms with reasonable overhead to applications.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了最后一个公式,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 Paper6
- Microkernel Goes General: Performance and Compatibility in the HongMeng Production MicrokernelHaibo Chen, Xie Miao, Ning Jia, Nan Wang 等OSDI 2024 · 被引用 13 次
- ByteFS: System Support for (CXL-based) Memory-Semantic Solid-State DrivesShaobo Li, Yirui Eric Zhou, Hao Ren, Jian HuangASPLOS 2025 · 被引用 13 次
- PhoenixOS: Concurrent OS-level GPU Checkpoint and Restore with Validated SpeculationXingda Wei, Zhuobin Huang, Tianle Sun, Yingyi Hao 等SOSP 2025 · 被引用 3 次
- Expeditious High-Concurrency MicroVM SnapStart in Persistent Memory with an Augmented HypervisorXingguo Pang, Yanze Zhang, Liu Liu, Dazhao Cheng 等USENIX ATC 2024 · 被引用 2 次
- Optimistic Recovery for High-Availability Software via Partial Process State PreservationYuzhuo Jing, Yuqi Mai, Angting Cai, Yi Chen 等SOSP 2025 · 被引用 1 次
它引用的顶会 Paper6
- Catalyzer: Sub-millisecond Startup for Serverless Computing with Initialization-less BootingDong Du, Tianyi Yu, Yubin Xia, Binyu Zang 等ASPLOS 2020 · 被引用 280 次
- Twizzler: a Data-Centric OS for Non-Volatile MemoryDaniel Bittman, Peter Alvaro, Pankaj Mehra, Darrell D. E. Long 等USENIX ATC 2020 · 被引用 50 次
- PMThreads: persistent memory threads harnessing versioned shadow copiesZhenwei Wu, Kai Lu, Andrew Nisbet, Wenzhe Zhang 等PLDI 2020 · 被引用 29 次
- Zhuque: Failure is Not an Option, it's an ExceptionGeorge Hodgkins, Yi Xu, Steven Swanson, Joseph IzraelevitzUSENIX ATC 2023 · 被引用 13 次
- The Aurora Single Level Store Operating SystemEmil Tsalapatis, Ryan Hancock, Tavian Barnes, Ali José MashtizadehSOSP 2021 · 被引用 12 次
相关 Paper
- MemSnap μCheckpoints: A Data Single Level Store for Fearless PersistenceEmil Tsalapatis, Ryan Hancock, Rakeeb Hossain, Ali José MashtizadehASPLOS 2024 · 被引用 1 次
- LightWSP: Whole-System Persistence on the CheapYuchen Zhou, Jianping Zeng, Changhee JungMICRO 2024 · 被引用 8 次
- Compiler-Directed Whole-System PersistenceJianping Zeng, Tong Zhang, Changhee JungISCA 2024 · 被引用 13 次
- Capri: Compiler and Architecture Support for Whole-System PersistenceJungi Jeong, Jianping Zeng, Changhee JungHPDC 2022 · 被引用 21 次
- Async-fork: Mitigating Query Latency Spikes Incurred by the Fork-based Snapshot Mechanism from the OS LevelPu Pang, Gang Deng, Kaihao Bai, Quan Chen 等VLDB 2023 · 被引用 10 次
