为容器化边缘服务提供实时支持

IF 3.9 3区计算机科学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

ACM Transactions on Internet Technology Pub Date : 2023-09-04 DOI:10.1145/3617123

Wenzhao Zhang, Yi Gao, Wei Dong

{"title":"为容器化边缘服务提供实时支持","authors":"Wenzhao Zhang, Yi Gao, Wei Dong","doi":"10.1145/3617123","DOIUrl":null,"url":null,"abstract":"Containers have emerged as a popular technology for edge computing platforms. Although there are varieties of container orchestration frameworks, e.g., Kubernetes to provide high-reliable services for cloud infrastructure, providing real-time support at the containerized edge systems (CESs) remains a challenge. In this paper, we propose EdgeMan, a holistic edge service management framework for CESs, which consists of (1) a model-assisted event-driven lightweight online scheduling algorithm to provide request-level execution plans; (2) a bottleneck-metric-aware progressive resource allocation mechanism to improve resource efficiency. We then build a testbed that installed three containerized services with different latency sensitivities for concrete evaluation. Besides, we adopt real-world data traces from Alibaba and Twitter for large-scale emulations. Extensive experiments demonstrate that the deadline miss ratio of time-sensitive services run with EdgeMan is reduced by 85.9% on average compared with that of existing methods in both industry and academia.","PeriodicalId":50911,"journal":{"name":"ACM Transactions on Internet Technology","volume":"1 1","pages":""},"PeriodicalIF":3.9000,"publicationDate":"2023-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Providing Realtime Support for Containerized Edge Services\",\"authors\":\"Wenzhao Zhang, Yi Gao, Wei Dong\",\"doi\":\"10.1145/3617123\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Containers have emerged as a popular technology for edge computing platforms. Although there are varieties of container orchestration frameworks, e.g., Kubernetes to provide high-reliable services for cloud infrastructure, providing real-time support at the containerized edge systems (CESs) remains a challenge. In this paper, we propose EdgeMan, a holistic edge service management framework for CESs, which consists of (1) a model-assisted event-driven lightweight online scheduling algorithm to provide request-level execution plans; (2) a bottleneck-metric-aware progressive resource allocation mechanism to improve resource efficiency. We then build a testbed that installed three containerized services with different latency sensitivities for concrete evaluation. Besides, we adopt real-world data traces from Alibaba and Twitter for large-scale emulations. Extensive experiments demonstrate that the deadline miss ratio of time-sensitive services run with EdgeMan is reduced by 85.9% on average compared with that of existing methods in both industry and academia.\",\"PeriodicalId\":50911,\"journal\":{\"name\":\"ACM Transactions on Internet Technology\",\"volume\":\"1 1\",\"pages\":\"\"},\"PeriodicalIF\":3.9000,\"publicationDate\":\"2023-09-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ACM Transactions on Internet Technology\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1145/3617123\",\"RegionNum\":3,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACM Transactions on Internet Technology","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1145/3617123","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}

引用次数: 0

摘要

容器已经成为边缘计算平台的流行技术。尽管有各种容器编排框架，例如Kubernetes，为云基础设施提供高可靠性服务，但在容器化边缘系统（CES）提供实时支持仍然是一个挑战。在本文中，我们提出了EdgeMan，一个用于CES的整体边缘服务管理框架，它由（1）一个模型辅助的事件驱动的轻量级在线调度算法组成，以提供请求级执行计划；（2）感知瓶颈度量的渐进式资源分配机制，以提高资源效率。然后，我们构建了一个测试平台，安装了三个具有不同延迟敏感性的容器化服务，用于具体评估。此外，我们采用了阿里巴巴和推特的真实世界数据跟踪进行大规模模拟。大量实验表明，与工业界和学术界现有的方法相比，使用EdgeMan运行的时间敏感服务的截止日期未命中率平均降低了85.9%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Providing Realtime Support for Containerized Edge Services

Containers have emerged as a popular technology for edge computing platforms. Although there are varieties of container orchestration frameworks, e.g., Kubernetes to provide high-reliable services for cloud infrastructure, providing real-time support at the containerized edge systems (CESs) remains a challenge. In this paper, we propose EdgeMan, a holistic edge service management framework for CESs, which consists of (1) a model-assisted event-driven lightweight online scheduling algorithm to provide request-level execution plans; (2) a bottleneck-metric-aware progressive resource allocation mechanism to improve resource efficiency. We then build a testbed that installed three containerized services with different latency sensitivities for concrete evaluation. Besides, we adopt real-world data traces from Alibaba and Twitter for large-scale emulations. Extensive experiments demonstrate that the deadline miss ratio of time-sensitive services run with EdgeMan is reduced by 85.9% on average compared with that of existing methods in both industry and academia.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

ACM Transactions on Internet Technology 工程技术-计算机：软件工程

CiteScore

10.30

自引率

1.90%

发文量

137

审稿时长

>12 weeks

期刊介绍： ACM Transactions on Internet Technology (TOIT) brings together many computing disciplines including computer software engineering, computer programming languages, middleware, database management, security, knowledge discovery and data mining, networking and distributed systems, communications, performance and scalability etc. TOIT will cover the results and roles of the individual disciplines and the relationshipsamong them.