Toward Resource-Efficient and High-Performance Program Deployment in Programmable Networks

被引:1
|
作者
Liu, Hongyan [1 ]
Chen, Xiang [1 ]
Huang, Qun [2 ]
Sun, Guoqiang [1 ]
Wang, Peiqiao [3 ]
Zhang, Dong [3 ]
Wu, Chunming [1 ]
Liu, Xuan [4 ]
Yang, Qiang [5 ]
机构
[1] Zhejiang Univ, Coll Comp Sci & Technol, Hangzhou 310007, Peoples R China
[2] Peking Univ, Sch Elect Engn & Comp Sci, Beijing 100871, Peoples R China
[3] Fuzhou Univ, Coll Comp Sci & Big Data, Fuzhou 350116, Peoples R China
[4] Yangzhou Univ, Coll Informat Engn, Coll Artificial Intelligence, Yangzhou 225002, Peoples R China
[5] Zhejiang Univ, Coll Elect Engn, Hangzhou 310007, Peoples R China
关键词
Data plane programs; program deployment; resource efficiency; packet processing performance; programmable networks; ALGORITHMS; SKETCH;
D O I
10.1109/TNET.2024.3413388
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Programmable switches allow administrators to customize packet processing behaviors in data plane programs. However, existing solutions for program deployment fail to achieve resource efficiency and high packet processing performance. In this paper, we propose, a system that provides resource-efficient and high-performance deployment for data plane programs. For resource efficiency, merges input data plane programs by reducing program redundancy. Then it abstracts the substrate network into an one big switch (OBS), and deploys the merged program on the OBS while minimizing resource usage. For high performance, searches for the performance-optimal mapping between the OBS and the substrate network with respect to network-wide constraints. It also maintains program logic among different switches via inter-device packet scheduling. We have implemented on a Barefoot Tofino switch. The evaluation indicates that achieves resource-efficient and high-performance deployment for real data plane programs.
引用
收藏
页码:4270 / 4285
页数:16
相关论文
共 50 条
  • [41] Binarized Neural Networks for Resource-Efficient Hashing with Minimizing Quantization Loss
    Zheng, Feng
    Deng, Cheng
    Huang, Heng
    PROCEEDINGS OF THE TWENTY-EIGHTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2019, : 1032 - 1040
  • [42] TRTRL: A localized resource-efficient learning algorithm for recurrent neural networks
    Budik, Danny
    Elhanany, Itamar
    IEEE MWSCAS'06: PROCEEDINGS OF THE 2006 49TH MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS,, 2006, : 371 - +
  • [43] Towards Resource-Efficient Application-Controlled Software Defined Networks
    Blendin, Jeremias
    Hausheer, David
    2014 IEEE 22ND INTERNATIONAL CONFERENCE ON NETWORK PROTOCOLS (ICNP), 2014, : 483 - 485
  • [44] Resource-Efficient Deep Neural Networks for Automotive Radar Interference Mitigation
    Rock, Johanna
    Roth, Wolfgang
    Toth, Mate
    Meissner, Paul
    Pernkopf, Franz
    IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2021, 15 (04) : 927 - 940
  • [45] Time-Domain Coding for Resource-Efficient Deep Neural Networks
    Avalos-Legaz, Sergio
    Ituero, Pablo
    2019 XXXIV CONFERENCE ON DESIGN OF CIRCUITS AND INTEGRATED SYSTEMS (DCIS), 2019,
  • [46] Robust and Resource-Efficient Identification of Two Hidden Layer Neural Networks
    Fornasier, Massimo
    Klock, Timo
    Rauchensteiner, Michael
    CONSTRUCTIVE APPROXIMATION, 2022, 55 (01) : 475 - 536
  • [47] A resource-efficient QoS routing protocol for mobile ad hoc networks
    De, S
    Qiao, CM
    Das, SK
    WIRELESS COMMUNICATIONS & MOBILE COMPUTING, 2003, 3 (04): : 465 - 486
  • [48] Decentralized and resource-efficient self-calibration of visual sensor networks
    Simonjan, Jennifer
    Rinner, Bernhard
    AD HOC NETWORKS, 2019, 88 : 112 - 128
  • [49] Resource-efficient and robust group communication in mobile ad hoc networks
    Choi, DH
    Kim, KI
    Kim, SH
    APCC 2003: 9TH ASIA-PACIFIC CONFERENCE ON COMMUNICATION, VOLS 1-3, PROCEEDINGS, 2003, : 433 - 438
  • [50] Gating Mechanism in Deep Neural Networks for Resource-Efficient Continual Learning
    Jin, Hyundong
    Yun, Kimin
    Kim, Eunwoo
    IEEE ACCESS, 2022, 10 : 18776 - 18786