Application-Driven Bandwidth Guarantees in Datacenters

被引:71
|
作者
Lee, Jeongkeun [1 ]
Turner, Yoshio [1 ]
Lee, Myungjin [2 ]
Popa, Lucian [3 ]
Banerjee, Sujata [1 ]
Kang, Joon-Myung [1 ]
Sharma, Puneet [1 ]
机构
[1] HP Labs, Palo Alto, CA 94304 USA
[2] Univ Edinburgh, Edinburgh EH8 9YL, Midlothian, Scotland
[3] Databricks, San Francisco, CA USA
关键词
Datacenter; Bandwidth; Availability; Cloud; Virtual Network; Application;
D O I
10.1145/2740070.2626326
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Providing bandwidth guarantees to specific applications is becoming increasingly important as applications compete for shared cloud network resources. We present Cloud Mirror, a solution that provides bandwidth guarantees to cloud applications based on a new network abstraction and workload placement algorithm. An effective network abstraction would enable applications to easily and accurately specify their requirements, while simultaneously enabling the infrastructure to provision resources efficiently for deployed applications. Prior research has approached the bandwidth guarantee specification by using abstractions that resemble physical network topologies. We present a contrasting approach of deriving a network abstraction based on application communication structure, called Tenant Application Graph or TAG. Cloud Mirror also incorporates a new workload placement algorithm that efficiently meets bandwidth requirements specified by TAGs while factoring in high availability considerations. Extensive simulations using real application traces and datacenter topologies show that Cloud Mirror can handle 40% more bandwidth demand than the state of the art (e.g., the Oktopus system), while improving high availability from 20% to 70%.
引用
收藏
页码:467 / 478
页数:12
相关论文
共 50 条
  • [31] MATCHING JOBS WITH RESOURCES: AN APPLICATION-DRIVEN APPROACH
    Clematis, A.
    Corana, A.
    D'Agostino, D.
    Galizia, A.
    Quarati, A.
    SCALABLE COMPUTING-PRACTICE AND EXPERIENCE, 2010, 11 (02): : 109 - 120
  • [32] Application-driven validation of posteriors in inverse problems
    Adler, Tim J.
    Noelke, Jan-Hinrich
    Reinke, Annika
    Tizabi, Minu Dietlinde
    Gruber, Sebastian
    Trofimova, Dasha
    Ardizzone, Lynton
    Jaeger, Paul F.
    Buettner, Florian
    Koethe, Ullrich
    Maier-Hein, Lena
    MEDICAL IMAGE ANALYSIS, 2025, 101
  • [33] KASTEL - An Application-Driven Center of Excellence for IT Security
    Mueller-Quade, Joern
    IT-INFORMATION TECHNOLOGY, 2011, 53 (05): : 250 - 255
  • [34] APPLICATION-DRIVEN, TOP-DOWN MARKET
    Depalma, Angelo
    Lab Manager, 2012, 7 (02): : 62 - 63
  • [35] Application-driven power management for mobile communication
    Kravets, R
    Krishnan, P
    WIRELESS NETWORKS, 2000, 6 (04) : 263 - 277
  • [36] A framework for application-driven classification of data streams
    Zhang, Peng
    Gao, Byron J.
    Liu, Ping
    Shi, Yong
    Guo, Li
    NEUROCOMPUTING, 2012, 92 : 170 - 182
  • [37] Ecohydrology in The Netherlands: Principles of an application-driven interdiscipline
    Grootjans, AB
    VanWirdum, G
    Kemmers, R
    VanDiggelen, R
    ACTA BOTANICA NEERLANDICA, 1996, 45 (04): : 491 - 516
  • [38] Tools for application-driven linear dimension reduction
    Srivastava, A
    Liu, XW
    NEUROCOMPUTING, 2005, 67 : 136 - 160
  • [39] Application-driven synthesis of core-based systems
    Kirovski, D
    Lee, C
    Potkonjak, M
    MangioneSmith, W
    1997 IEEE/ACM INTERNATIONAL CONFERENCE ON COMPUTER-AIDED DESIGN - DIGEST OF TECHNICAL PAPERS, 1997, : 104 - 107
  • [40] EIC Editorial: Application-Driven Management of Service Systems
    Zhang, Liang-Jie
    IEEE TRANSACTIONS ON SERVICES COMPUTING, 2011, 4 (01) : 1 - 2