FetchBPF: Customizable Prefetching Policies in Linux with eBPF
Xuechun Cao, Shaurya Patel, Soo-Yee Lim, Xueyuan Han, Thomas Pasquier
Abstract
Monolithic operating systems are infamously complex. Linux in particular has a tendency to intermingle policy and mechanisms in a manner that hinders modularity. This is especially problematic when developers aim to finely optimize performance, since it is often the case that a default policy in Linux, while performing well on average, cannot achieve the optimal performance in all circumstances. However, developing and maintaining a bespoke kernel to satisfy the need of a specific application is usually an unrealistic endeavor due to the high software engineering cost. Therefore, we need a mechanism to easily customize kernel policies and its behavior. In this paper, we design a framework called FetchBPF that addresses this problem in the context of memory prefetching. FetchBPF extends the widely used eBPF framework to allow developers to easily express, develop, and deploy prefetching policies without modifying the kernel codebase. We implement various memory prefetching policies from the literature and demonstrate that our deployment model incurs negligible overhead as compared to the equivalent native kernel implementation.
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 08cbfdd1-188f-40cf-925e-bb1d0792d843Cited by top-tier papers7
- PageFlex: Flexible and Efficient User-space Delegation of Linux Paging Policies with eBPFAnil Yelam, Kan Wu, Zhiyuan Guo, Suli Yang et al.USENIX ATC 2025 · 15 citations
- How Soon is Now? Preloading Images for Virtual Disks with ThinkAheadXinqi Chen, Yu Zhang, Erci Xu, Changhong Wang et al.FAST 2026 · 1 citation
- uCache: A Customizable Unikernel-based IO CacheIlya Meignan-Masson, Masanori Misono, Viktor Leis, Pramod BhatotiaFAST 2026 · 1 citation
- Accelerating Model Loading in LLM Inference by Programmable Page CacheYubo Liu, Hongbo Li, Xiaojia Huang, Yongfeng Wang et al.FAST 2026
- Virtualizing eBPF with Late-BindingJing Zhang, Xiaguannan Song, Dong Du, Yubin Xia et al.OSDI 2026
Builds on9
- AIFM: High-Performance, Application-Integrated Far MemoryZhenyuan Ruan, Malte Schwarzkopf, Marcos K. Aguilera, Adam BelayOSDI 2020 · 224 citations
- Effectively Prefetching Remote Memory with LeapHasan Al Maruf, Mosharaf ChowdhuryUSENIX ATC 2020 · 186 citations
- Can far memory improve job throughput?Emmanuel Amaro, Christopher Branner-Augmon, Zhihong Luo, Amy Ousterhout et al.EuroSys 2020 · 163 citations
- Classifying Memory Access Patterns for PrefetchingGrant Ayers, Heiner Litz, Christos Kozyrakis, Parthasarathy RanganathanASPLOS 2020 · 83 citations
- ghOSt: Fast & Flexible User-Space Delegation of Linux SchedulingJack Tigar Humphries, Neel Natu, Ashwin Chaugule, Ofir Weisse et al.SOSP 2021 · 60 citations
Related papers
- cache_ext: Customizing the Page Cache with eBPFTal Zussman, Ioannis Zarkadas, Jeremy Carin, Andrew Cheng et al.SOSP 2025 · 8 citations
- CrossPrefetch: Accelerating I/O Prefetching for Modern StorageShaleen Garg, Jian Zhang, Rekha Pitchumani, Manish Parashar et al.ASPLOS 2024 · 9 citations
- BMC: Accelerating Memcached using Safe In-kernel Caching and Pre-stack ProcessingYoann Ghigoff, Julien Sopena, Kahina Lazri, Antoine Blin et al.NSDI 2021 · 79 citations
- hXDP: Efficient Software Packet Processing on FPGA NICsMarco Spaziani Brunella, Giacomo Belocchi, Marco Bonola, Salvatore Pontarelli et al.OSDI 2020 · 25 citations
- Don't Stall Me Now: Hiding Memory Latency in eBPFFarbod Shahinfar, Marco Molè, Aurojit Panda, Gianni AntichiSIGCOMM 2026
