Xkernel: Principled Performance Tunability of Operating System Kernels
Zhongjie Chen, Wentao Zhang, Yulong Tang, Ran Shu, Fengyuan Ren, Tianyin Xu, Jing Liu
摘要
The Linux kernel is permeated with constant values that are critical to system performance. Many of these constants, referred to as perf-consts , are magic numbers with brittle assumptions on hardware and workloads. Unfortunately, there is no capability of in-situ tuning of perf-const values on deployed kernels. This paper rethinks OS performance tunability. We present Xkernel, a system that offers a safe, efficient, and programmable interface for in-situ tuning of any perf-consts directly on a running kernel. Xkernel transforms any perf-const into a tunable knob on demand using a novel approach called Scoped Indirect Execution (SIE). SIE captures precise binary boundaries where a perf-const enters system state and redirects control to synthesized instructions that update the state as if new values were used. Xkernel goes beyond version atomicity when updating perf-consts to guarantee side-effect safety, a property notably absent in existing kernel update mechanisms. Case studies on various OS subsystems demonstrate significant performance benefits of tuning perf-consts which is made possible by Xkernel.
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。
它引用的顶会 Paper7
- XRP: In-Kernel Storage Functions with eBPFYuhong Zhong, Haoyu Li, Yu Jian Wu, Ioannis Zarkadas 等OSDI 2022 · 被引用 100 次
- LlamaTune: Sample-Efficient DBMS Configuration TuningKonstantinos Kanellis, Cong Ding, Brian Kroth, Andreas Müller 等VLDB 2022 · 被引用 73 次
- Syrup: User-Defined Scheduling Across the StackKostis Kaffes, Jack Tigar Humphries, David Mazières, Christos KozyrakisSOSP 2021 · 被引用 35 次
- IOCost: block IO control for containers in datacentersTejun Heo, Dan Schatzberg, Andrew Newell, Song Liu 等ASPLOS 2022 · 被引用 22 次
- PageFlex: Flexible and Efficient User-space Delegation of Linux Paging Policies with eBPFAnil Yelam, Kan Wu, Zhiyuan Guo, Suli Yang 等USENIX ATC 2025 · 被引用 15 次
相关 Paper
- TuxBot: Semantic-Aware Online OS Tuning with LLMsGeorgios Liargkovas, Mihir Nitin Joshi, Hubertus Franke, Kostis KaffesSOSP 2026
- TypeCraft: A Lightweight Data Type Profiler with High ResolutionZecheng Li, Xu Liu, Namhyung Kim, Blake Jones 等OSDI 2026
- Multi-Intention-Aware Configuration Selection for Performance TuningHaochen He, Zhouyang Jia, Shanshan Li, Yue Yu 等ICSE 2022 · 被引用 11 次
- PeriScope: An Effective Probing and Fuzzing Framework for the Hardware-OS BoundaryDokyung Song, Felicitas Hetzelt, Dipanjan Das, Chad Spensky 等NDSS 2019 · 被引用 114 次
- Fast, Flexible, and Practical Kernel ExtensionsKumar Kartikeya Dwivedi, Rishabh R. Iyer, Sanidhya KashyapSOSP 2024 · 被引用 7 次
