ACM SIGCOMM Computer Communication Review ( IF 2.8 ) Pub Date : 2023-04-20 , DOI: https://dl.acm.org/doi/10.1145/3594255.3594256 Sebastiano Miano, Xiaoqi Chen, Ran Ben Basat, Gianni Antichi
The extended Berkeley Packet Filter (eBPF) is an infrastructure that allows to dynamically load and run micro-programs directly in the Linux kernel without recompiling it.
In this work, we study how to develop high-performance network measurements in eBPF. We take sketches as case-study, given their ability to support a wide-range of tasks while providing low-memory footprint and accuracy guarantees. We implemented NitroSketch, the state-of-the-art sketch for user-space networking and show that best practices in user-space networking cannot be directly applied to eBPF, because of its different performance characteristics. By applying our lesson learned we improve its performance by 40% compared to a naive implementation.
中文翻译:
eBPF 中的快速内核流量草图
扩展的 Berkeley 数据包过滤器 (eBPF) 是一种基础架构,它允许直接在 Linux 内核中动态加载和运行微程序,而无需重新编译。
在这项工作中,我们研究了如何在 eBPF 中开发高性能网络测量。我们将草图作为案例研究,因为它们能够支持广泛的任务,同时提供低内存占用和准确性保证。我们实现了 NitroSketch,这是用于用户空间网络的最先进的草图,并表明用户空间网络中的最佳实践不能直接应用于 eBPF,因为它具有不同的性能特征。通过吸取我们的经验教训,与简单的实施相比,我们将其性能提高了 40%。