Managing Cloud networking costs for data-intensive applications by provisioning dedicated network links

Managing Cloud networking costs for data-intensive applications by provisioning dedicated network links
复制标题

通过配置专用网络链接来管理数据密集型应用程序的云网络成本

DOI:
10.1145/3437359.3465563
复制
发表时间:
2021
期刊:
arXiv preprint arXiv:2104.06913
影响因子:
--
通讯作者:
Brik, Vladimir
Brik, Vladimir
中科院分区:
--
文献类型:
--
作者:
Sfiligoi, Igor;Hare, Michael;Schultz, David;Würthwein, Frank;Riedel, Benedikt;Hutton, Tom;Barnet, Steve;Brik, Vladimir

文献摘要

参考文献

被引文献

相似文献

许多科学的高吞吐量应用程序可以受益于云资源的弹性性质,特别是在需要缩短完成时间的情况下。成本考量通常是此类工作中的主要问题,网络通常是主要组成部分;对于数据密集型应用,出口网络成本可能超过计算成本。专用网络链路提供了一种降低网络成本的方法,但它们确实增加了复杂性。在本白皮书中,我们描述了支持IceCube生产计算的100 FP32 PFLOPS Cloud Burst,它使用Internet2 Cloud Connect服务来配置来自三大云提供商(即Amazon Web Services、Microsoft Azure和Google Cloud Platform)的多个逻辑专用网络链路,这些链路总共支持约100 Gbps的本地存储出口能力。它提供了有关资源调配过程的技术细节、此类设置的优势和局限性以及所产生的成本分析。
Many scientific high-throughput applications can benefit from the elastic nature of Cloud resources, especially when there is a need to reduce time to completion. Cost considerations are usually a major issue in such endeavors, with networking often a major component; for data-intensive applications, egress networking costs can exceed the compute costs. Dedicated network links provide a way to lower the networking costs, but they do add complexity. In this paper we provide a description of a 100 fp32 PFLOPS Cloud burst in support of IceCube production compute, that used Internet2 Cloud Connect service to provision several logically-dedicated network links from the three major Cloud providers, namely Amazon Web Services, Microsoft Azure and Google Cloud Platform, that in aggregate enabled approximately 100 Gbps egress capability to on-prem storage. It provides technical details about the provisioning process, the benefits and limitations of such a setup and an analysis of the costs incurred.
DOI: 10.1145/3311790.3399612
发表时间: 2020
期刊: Practice and Experience in Advanced Research Computing (PEARC20
影响因子: --
作者:
Sfiligoi, Igor
通讯作者: Sfiligoi, Igor
使用 Chameleon、ExoGENI 和 Internet2 Cloud Connect 试验 AWS Direct Connect
DOI: --
发表时间: 2019
期刊: IEEE International Conference on Network Protocols
影响因子: --
作者:
Paul Ruth;Mert Cevik
通讯作者: Mert Cevik
DOI: 10.1109/ccgrid.2018.00040
发表时间: 2018
期刊: Cloud and Grid Computing
影响因子: --
作者:
Posey, Brandon;Gropp, Christopher;Wilson, Boyd;McGeachie, Boyd;Padhi, Sanjay;Herzog, Alexander;Apon, Amy
通讯作者: Apon, Amy
利用 Google 云平台进行按需紧急高性能计算
DOI: 10.1109/urgenthpc49580.2019.00008
发表时间: 2019
期刊: 2019 IEEE/ACM HPC for Urgent Decision Making (UrgentHPC
影响因子: --
作者:
Posey, Brandon;Deer, Adam;Gorman, Wyatt;July, Vanessa;Kanhere, Neeraj;Speck, Dan;Wilson, Boyd;Apon, Amy
通讯作者: Apon, Amy
DOI: --
发表时间: 2016
期刊: SoutheastCon
影响因子: --
作者:
Joaquín Chung;H. Owen;Russ Clark
通讯作者: Russ Clark