LiteFlow
Authors:
Open Access
- 22 August 2022
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 414-427
Abstract
Adaptive neural networks (NN) have been used to optimize OS kernel datapath functions because they can achieve superior performance under changing environments. However, how to deploy these NNs remains a challenge. One approach is to deploy these adaptive NNs in the userspace. However, such userspace deployments suffer from either high cross-space communication overhead or low responsiveness, significantly compromising the function performance. On the other hand, pure kernel-space deployments also incur a large performance degradation because the computation logic of model tuning algorithm is typically complex, interfering with the performance of normal datapath execution. This paper presents LiteFlow, a hybrid solution to build high-performance adaptive NNs for kernel datapath. At its core, LiteFlow decouples the control path of adaptive NNs into: (1) a kernel-space fast path for efficient model inference, and (2) a userspace slow path for effective model tuning. We have implemented LiteFlow with Linux kernel datapath and evaluated it with three popular datapath functions including congestion control, flow scheduling, and load balancing. Compared to prior works, LiteFlow achieves 44.4% better goodput for congestion control, and improves the completion time for long flows by 33.7% and 56.7% for flow scheduling and load balancing, respectively.Keywords
Funding Information
- Key-Area Research and Development Program of Guangdong Province (2021B0101400001)
- NSFC (62062005)
- Hong Kong RGC TRS (T41-603/20-R, GRF-16215119, GRF-16213621)
This publication has 24 references indexed in Scilit:
- Resilient Datacenter Load Balancing in the Wild2017
- The QUIC Transport Protocol2017
- Scheduling Mix-flows in Commodity Datacenters with Karuna2016
- Explicit Path Control in Commodity Data Centers: Design and ApplicationsIEEE/ACM Transactions on Networking, 2015
- pFabric2013
- Large-Scale Machine Learning with Stochastic Gradient Descent2010
- The nature of data center traffic2009
- CUBICACM SIGOPS Operating Systems Review, 2008
- UDT: UDP-based data transfer for high-speed wide area networksComputer Networks, 2007
- Calculus III: Taylor SeriesGeometry & Topology, 2003