NFCache: Fine-grained and Flexible Offloading of Network Functions to Programmable Switches

被引:0
|
作者
Chen, Ruixin [1 ]
Shan, Xinpeng [1 ]
Zhao, Jin [1 ]
机构
[1] Fudan Univ, Sch Comp Sci, Shanghai, Peoples R China
基金
中国国家自然科学基金;
关键词
Programmable Data Plane; Service Function Chains; Network Functions;
D O I
10.1145/3605731.3605747
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
A Service Function Chain (SFC) consists of a sequence of Network Functions (NFs) in order, and plays an important role in network performance and security. In recent years, due to the low throughput and high latency of network functions in the context of Network Function Virtualization (NFV), some NF implementation solutions consider offloading network functions to programmable switches. However, existing offloading efforts either perform coarse-grained offloading or are not flexible enough to adapt to dynamic and unbalanced traffic. In this paper, we propose NFCache, which offloads network functions at the granularity of NF rules and implements a general network function module, allowing different stateful or stateless network functions to share switch resources. When the traffic changes, the control plane of NFCache can flexibly offload the required network function rules that can bring the most significant offloading gain. We also implement NFCache on a commodity programmable switch to evaluate its performance. Experimental results show that compared with the state-of-the-art solutions, NF-Cache increases the average throughput by 72% and decreases the packet latency by 52% under dynamic and unbalanced traffic.
引用
收藏
页码:61 / 70
页数:10
相关论文
共 50 条
  • [41] Multi Fine-Grained Fusion Network for Depression Detection
    Zhou, Li
    Liu, Zhenyu
    Li, Yutong
    Duan, Yuchi
    Yu, Huimin
    Hu, Bin
    [J]. ACM Transactions on Multimedia Computing, Communications and Applications, 2024, 20 (08)
  • [42] CrackFormer: Transformer Network for Fine-Grained Crack Detection
    Liu, Huajun
    Miao, Xiangyu
    Mertz, Christoph
    Xu, Chengzhong
    Kong, Hui
    [J]. 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 3763 - 3772
  • [43] A coarse-to-fine capsule network for fine-grained image categorization
    College of Information and Electrical Engineering, China Agricultural University, Beijing
    100083, China
    不详
    100083, China
    不详
    100083, China
    [J]. Neurocomputing, 1600, (200-219):
  • [44] Fine-Grained Power Control for Combined Input-Crosspoint Queued Switches
    Xia, Yu
    Wang, Ting
    Su, Zhiyang
    Hamdi, Mounir
    [J]. 2014 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM 2014), 2014, : 2599 - 2604
  • [45] Fine-Grained Flow Scheduling in WDM Optical Cut-through Switches
    Zhang, Zhemin
    Dai, Weining
    Cheng, Siying
    Chen, Lisha
    Lin, Congren
    Yang, Yuanyuan
    [J]. 2019 IEEE INTL CONF ON PARALLEL & DISTRIBUTED PROCESSING WITH APPLICATIONS, BIG DATA & CLOUD COMPUTING, SUSTAINABLE COMPUTING & COMMUNICATIONS, SOCIAL COMPUTING & NETWORKING (ISPA/BDCLOUD/SOCIALCOM/SUSTAINCOM 2019), 2019, : 338 - 347
  • [46] pSFC: Fine-grained Composition of Service Function Chains in the Programmable Data Plane
    Zhang, Xiaoquan
    Cui, Lin
    Tso, Fung Po
    [J]. 2022 22ND IEEE/ACM INTERNATIONAL SYMPOSIUM ON CLUSTER, CLOUD AND INTERNET COMPUTING (CCGRID 2022), 2022, : 484 - 493
  • [47] Fine-Grained Sentence Functions for Short-Text Conversation
    Bi, Wei
    Gao, Jun
    Liu, Xiaojiang
    Shi, Shuming
    [J]. 57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019), 2019, : 3984 - 3993
  • [48] SaHaD: A fine-grained in-network latency measurement for datacenter network
    [J]. Zhang, Z. (ziwen@nudt.edu.cn), 1600, Binary Information Press, P.O. Box 162, Bethel, CT 06801-0162, United States (09):
  • [49] MEC-Enabled Fine-Grained Task Offloading for UAV Networks in Urban Environments
    Yu, Sicong
    Zheng, Huiji
    Ma, Caihong
    [J]. SUSTAINABILITY, 2022, 14 (21)
  • [50] DaQAPO: Supporting flexible and fine-grained event log quality assessment
    Martin, Niels
    Van Houdt, Greg
    Janssenswillen, Gert
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2022, 191