KubeKlone: A Digital Twin for Simulating Edge and Cloud Microservices

KubeKlone: A Digital Twin for Simulating Edge and Cloud Microservices
复制标题

KubeKlone:用于模拟边缘和云微服务的数字孪生

DOI:
10.1145/3542637.3542642
复制
发表时间:
2022
期刊:
APNet
影响因子:
--
通讯作者:
Benson, Theophilus A.
Benson, Theophilus A.
中科院分区:
--
文献类型:
--
作者:
Bhardwaj, Ayush;Benson, Theophilus A.

文献摘要

参考文献

被引文献

相似文献

微服务正在通过网络规模的基础设施(如Facebook、b谷歌、Amazon)和电信基础设施(如ATT、爱立信)来改变计算领域。微服务范式的核心是将应用程序解耦为多个服务——这种解耦促进了更好的可伸缩性、容错性和可部署性。不幸的是,这种解耦极大地增加了配置选项的空间和性能问题,使传统的管理方法无效。最近解决这一问题的努力包括用于IT操作的人工智能(AIOps)。然而,训练有效的人工智能模型需要大量的数据,在某些情况下,还需要一个快速探索或分析模型性能的框架。数字双胞胎,或模拟器,已经有效地在其他领域(例如,制造业,工业和汽车)中启用了基于人工智能的管理框架。在本文中,我们提出了KubeKlone的设计,这是第一个用于建模云原生微服务应用的全面开源数字孪生。kubekone的动机是我们需要准确、高效和通用的模型训练。kubekone通过将微服务的模拟与机器学习(ML)模型的训练解耦来满足这些目标,同时确保效率并简化模型设计。特别是,kubekone引入了一个基于队列的模拟器,该模拟器抽象了基础设施细节,并专注于对队列、跨主机和网络组件的资源争用进行建模。为了简化模型设计,kubekone提供了隐藏模拟器细节的接口,并提供了流行ML包的包装器。为了说明kubekone的优势,我们针对谷歌云引擎上的部署验证了它,并实现了几个AIOps资源管理算法(包括PARTIES)。
Microservices are terraforming the computing landscape with web-scale infrastructures (e.g., Facebook, Google, Amazon) and telecom infrastructures (e.g., ATT, Ericsson) adopting them. At it’s core, the microservices paradigm promotes a decoupling of applications into multiple services – a decoupling that promotes better scalability, fault-tolerance, and deployability. Unfortunately, this decoupling significantly increases the space of configuration options and performance problems, rendering traditional approaches to management ineffective. Recent efforts to address this problem embrace Artificial Intelligence for IT Operations (AIOps). However, training effective AI models requires significant amounts of data and, in some instances, a framework for quickly exploring or analyzing model performance. Digital twins, or simulators, have effectively enabled AI-based management frameworks within other domains (e.g., manufacturing, industrial and automotive).In this paper, we propose the design of KubeKlone, the first comprehensive and opensource digital twin for modeling cloud-native microservices applications. KubeKlone is motivated by our need for accurate, efficient, and general model training. KubeKlone satisfies these goals by decoupling the simulation of microservices from the training of machine learning (ML) models while simultaneously ensuring efficiency and simplifying model design. In particular, KubeKlone introduces a queue-based simulator that abstracts infrastructure details and focuses on modeling, with queues, resource contentions across host and network components. To simplify model design, KubeKlone provides interfaces that hide simulator details and provides wrappers around popular ML packages. To illustrate the strengths of KubeKlone, we validate it against a deployment on Google Cloud Engine and implement several AIOps resource management algorithms (including PARTIES).
细节
DOI: --
发表时间: 2018
期刊: A Philosophy of Interior Design
影响因子: --
作者:
S. Abercrombie
通讯作者: S. Abercrombie
uqSim:云微服务的可扩展且经过验证的模拟
DOI: --
发表时间: 2019
期刊: arXiv.org
影响因子: --
作者:
Yanqi Zhang;Yu Gan;Christina Delimitrou
通讯作者: Christina Delimitrou
DOI: 10.1109/focs.2013.17
发表时间: 2013-04
期刊: 2013 IEEE 54th Annual Symposium on Foundations of Computer Science
影响因子: --
作者:
Rasmus Pagh;Gil Segev;Udi Wieder
通讯作者: Rasmus Pagh;Gil Segev;Udi Wieder
基于模型的微服务弹性模式分析
DOI: 10.1109/icsa47634.2020.00019
发表时间: 2020
期刊: 2020 IEEE International Conference on Software Architecture (ICSA)
影响因子: --
作者:
N. Mendonça;C. Aderaldo;J. Cámara;D. Garlan
通讯作者: D. Garlan
TeaStore:用于基准测试、建模和资源管理研究的微服务参考应用程序
DOI: 10.1109/mascots.2018.00030
发表时间: 2018
期刊: 2018 IEEE 26th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS)
影响因子: --
作者:
J. V. Kistowski;Simon Eismann;Norbert Schmitt;André Bauer;Johannes Grohmann;Samuel Kounev
通讯作者: Samuel Kounev