Smart Spot Instances for the Supercloud

被引:5
|
作者
Jia, Qin [1 ]
Shen, Zhiming [1 ]
Song, Weijia [1 ]
van Renesse, Robbert [1 ]
Weatherspoon, Hakim [1 ]
机构
[1] Cornell Univ, Ithaca, NY 14853 USA
基金
美国国家科学基金会;
关键词
D O I
10.1145/2904111.2904114
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
In this paper, we explore the use of live VM migration to take advantage of spot markets such as provided by Amazon and Google. These markets provide an exciting low cost alternative to regular VM instances, but the threats of price spikes and premature termination severely limit their usability. Migration can address these threats: spot market instances facing price hikes or termination can migrate to other instance types, including regular ones. Reliability can be further improved by replication. In this paper we investigate various design options and present some preliminary results of experiments with dynamic programming techniques, both using simulation and using a realistic deployment. We find that in unstable markets we can achieve significant savings at low overhead and while maintaining good reliability.
引用
收藏
页数:6
相关论文
共 50 条
  • [1] Spot-on for timed instances: striking a balance between spot and on-demand instances
    Knauth, Thomas
    Fetzer, Christof
    [J]. SECOND INTERNATIONAL CONFERENCE ON CLOUD AND GREEN COMPUTING / SECOND INTERNATIONAL CONFERENCE ON SOCIAL COMPUTING AND ITS APPLICATIONS (CGC/SCA 2012), 2012, : 105 - 112
  • [2] Plug into the Supercloud
    Williams, Dan
    Jamjoom, Hani
    Weatherspoon, Hakim
    [J]. IEEE INTERNET COMPUTING, 2013, 17 (02) : 28 - 34
  • [3] Economics of a Supercloud
    Kash, Ian
    Jia, Qin
    Shen, Zhiming
    Song, Weijia
    van Renesse, Robbert
    Weatherspoon, Hakim
    [J]. 3RD WORKSHOP ON CROSSCLOUD INFRASTRUCTURES & PLATFORMS (CROSSCLOUD 2016), 2016,
  • [4] Present or Future: Optimal Pricing for Spot Instances
    Wang, Peijian
    Qi, Yong
    Hui, Dou
    Rao, Lei
    Liu, Xue
    [J]. 2013 IEEE 33RD INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING SYSTEMS (ICDCS), 2013, : 410 - 419
  • [5] Dynamic Price Prediction for Amazon Spot Instances
    Singh, Vivek Kumar
    Dutta, Kaushik
    [J]. 2015 48TH HAWAII INTERNATIONAL CONFERENCE ON SYSTEM SCIENCES (HICSS), 2015, : 1513 - 1520
  • [6] Spotgres - Parallel Data Analytics on Spot Instances
    Binnig, Carsten
    Salama, Abdallah
    Zamanian, Erfan
    El-Hindi, Muhammad
    Feil, Sebastian
    Ziegler, Tobias
    [J]. 2015 13TH IEEE INTERNATIONAL CONFERENCE ON DATA ENGINEERING WORKSHOPS (ICDEW), 2015, : 14 - 21
  • [7] PISTIS: Composing AWS Spot Instances with Guarantees
    Wong, Walter
    Corneot, Lorenzo
    Zavodovskit, Aleksandr
    Kangasharju, Jussi
    [J]. IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2022), 2022, : 5469 - 5474
  • [8] Price forecasting for spot instances in Cloud computing
    Cai, Zhicheng
    Li, Xiaoping
    Ruiz, Ruben
    Li, Qianmu
    [J]. FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2018, 79 : 38 - 53
  • [9] Methods for improving the availability of spot instances: A survey
    Lin, Liduo
    Pan, Li
    Liu, Shijun
    [J]. COMPUTERS IN INDUSTRY, 2022, 141
  • [10] Scheduling ML Training on Unreliable Spot Instances
    Yang, Sheng
    Khuller, Samir
    Choudhary, Sunav
    Mitra, Subrata
    Mahadik, Kanak
    [J]. COMPANION PROCEEDINGS OF THE 14TH IEEE/ACM INTERNATIONAL CONFERENCE ON UTILITY AND CLOUD COMPUTING (UCC'21 COMPANION), 2021,