基于依赖的微服务编排的tera调度程序

2022 International Conference on Advanced Aspects of Software Engineering (ICAASE) Pub Date : 2022-09-17 DOI:10.1109/ICAASE56196.2022.9931568

Souheir Merkouche, Tarik Haroun, Chafia Bouanaka, Manel Smaali

{"title":"基于依赖的微服务编排的tera调度程序","authors":"Souheir Merkouche, Tarik Haroun, Chafia Bouanaka, Manel Smaali","doi":"10.1109/ICAASE56196.2022.9931568","DOIUrl":null,"url":null,"abstract":"Due to the increase use of Microservices and the adoption of containers as the best choice for their deployment. Orchestration tools are continuously updating their auto-scaling and scheduling strategies in order to offer better options and capabilities to users. Despite the proposed solutions, there are still many unaddressed issues and optimization is still needed from different perspectives. Therefore, we present TERA-scheduler, with a new scheduling strategy, that we implement using Kubernetes, to reduce both the scheduling duration and the traffic between pods, by considering dependencies between Microservices. Experimentation results show that TERA-Scheduler fasten the response time by 39% compared to Kubernetes (K8s for short) default scheduler which make it a better choice especially for latency-aware systems.","PeriodicalId":206411,"journal":{"name":"2022 International Conference on Advanced Aspects of Software Engineering (ICAASE)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"TERA-Scheduler for a Dependency-based Orchestration of Microservices\",\"authors\":\"Souheir Merkouche, Tarik Haroun, Chafia Bouanaka, Manel Smaali\",\"doi\":\"10.1109/ICAASE56196.2022.9931568\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Due to the increase use of Microservices and the adoption of containers as the best choice for their deployment. Orchestration tools are continuously updating their auto-scaling and scheduling strategies in order to offer better options and capabilities to users. Despite the proposed solutions, there are still many unaddressed issues and optimization is still needed from different perspectives. Therefore, we present TERA-scheduler, with a new scheduling strategy, that we implement using Kubernetes, to reduce both the scheduling duration and the traffic between pods, by considering dependencies between Microservices. Experimentation results show that TERA-Scheduler fasten the response time by 39% compared to Kubernetes (K8s for short) default scheduler which make it a better choice especially for latency-aware systems.\",\"PeriodicalId\":206411,\"journal\":{\"name\":\"2022 International Conference on Advanced Aspects of Software Engineering (ICAASE)\",\"volume\":\"13 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-09-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 International Conference on Advanced Aspects of Software Engineering (ICAASE)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICAASE56196.2022.9931568\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 International Conference on Advanced Aspects of Software Engineering (ICAASE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICAASE56196.2022.9931568","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

由于微服务的使用越来越多，并且采用容器作为其部署的最佳选择。编排工具正在不断更新它们的自动伸缩和调度策略，以便为用户提供更好的选择和功能。尽管提出了解决方案，但仍有许多未解决的问题，需要从不同的角度进行优化。因此，我们提出了TERA-scheduler，并使用Kubernetes实现了一种新的调度策略，通过考虑微服务之间的依赖关系，减少了调度持续时间和pod之间的流量。实验结果表明，与Kubernetes(简称k8)默认调度器相比，TERA-Scheduler的响应时间缩短了39%，这使得它成为一个更好的选择，特别是对于延迟感知系统。

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

TERA-Scheduler for a Dependency-based Orchestration of Microservices

Due to the increase use of Microservices and the adoption of containers as the best choice for their deployment. Orchestration tools are continuously updating their auto-scaling and scheduling strategies in order to offer better options and capabilities to users. Despite the proposed solutions, there are still many unaddressed issues and optimization is still needed from different perspectives. Therefore, we present TERA-scheduler, with a new scheduling strategy, that we implement using Kubernetes, to reduce both the scheduling duration and the traffic between pods, by considering dependencies between Microservices. Experimentation results show that TERA-Scheduler fasten the response time by 39% compared to Kubernetes (K8s for short) default scheduler which make it a better choice especially for latency-aware systems.

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

2022 International Conference on Advanced Aspects of Software Engineering (ICAASE)

自引率

0.00%

发文量