Michal Orzechowski, Bartosz Balis, Krzysztof Janecki
{"title":"实现云原生科学工作流程管理","authors":"Michal Orzechowski, Bartosz Balis, Krzysztof Janecki","doi":"arxiv-2408.15445","DOIUrl":null,"url":null,"abstract":"Cloud-native is an approach to building and running scalable applications in\nmodern cloud infrastructures, with the Kubernetes container orchestration\nplatform being often considered as a fundamental cloud-native building block.\nIn this paper, we evaluate alternative execution models for scientific\nworkflows in Kubernetes. We compare the simplest job-based model, its variant\nwith task clustering, and finally we propose a cloud-native model based on\nmicroservices comprising auto-scalable worker-pools. We implement the proposed\nmodels in the HyperFlow workflow management system, and evaluate them using a\nlarge Montage workflow on a Kubernetes cluster. The results indicate that the\nproposed cloud-native worker-pools execution model achieves best performance in\nterms of average cluster utilization, resulting in a nearly 20\\% improvement of\nthe workflow makespan compared to the best-performing job-based model. However,\nbetter performance comes at the cost of significantly higher complexity of the\nimplementation and maintenance. We believe that our experiments provide a\nvaluable insight into the performance, advantages and disadvantages of\nalternative cloud-native execution models for scientific workflows.","PeriodicalId":501422,"journal":{"name":"arXiv - CS - Distributed, Parallel, and Cluster Computing","volume":"10 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Towards cloud-native scientific workflow management\",\"authors\":\"Michal Orzechowski, Bartosz Balis, Krzysztof Janecki\",\"doi\":\"arxiv-2408.15445\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Cloud-native is an approach to building and running scalable applications in\\nmodern cloud infrastructures, with the Kubernetes container orchestration\\nplatform being often considered as a fundamental cloud-native building block.\\nIn this paper, we evaluate alternative execution models for scientific\\nworkflows in Kubernetes. We compare the simplest job-based model, its variant\\nwith task clustering, and finally we propose a cloud-native model based on\\nmicroservices comprising auto-scalable worker-pools. We implement the proposed\\nmodels in the HyperFlow workflow management system, and evaluate them using a\\nlarge Montage workflow on a Kubernetes cluster. The results indicate that the\\nproposed cloud-native worker-pools execution model achieves best performance in\\nterms of average cluster utilization, resulting in a nearly 20\\\\% improvement of\\nthe workflow makespan compared to the best-performing job-based model. However,\\nbetter performance comes at the cost of significantly higher complexity of the\\nimplementation and maintenance. We believe that our experiments provide a\\nvaluable insight into the performance, advantages and disadvantages of\\nalternative cloud-native execution models for scientific workflows.\",\"PeriodicalId\":501422,\"journal\":{\"name\":\"arXiv - CS - Distributed, Parallel, and Cluster Computing\",\"volume\":\"10 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Distributed, Parallel, and Cluster Computing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2408.15445\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Distributed, Parallel, and Cluster Computing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2408.15445","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Towards cloud-native scientific workflow management
Cloud-native is an approach to building and running scalable applications in
modern cloud infrastructures, with the Kubernetes container orchestration
platform being often considered as a fundamental cloud-native building block.
In this paper, we evaluate alternative execution models for scientific
workflows in Kubernetes. We compare the simplest job-based model, its variant
with task clustering, and finally we propose a cloud-native model based on
microservices comprising auto-scalable worker-pools. We implement the proposed
models in the HyperFlow workflow management system, and evaluate them using a
large Montage workflow on a Kubernetes cluster. The results indicate that the
proposed cloud-native worker-pools execution model achieves best performance in
terms of average cluster utilization, resulting in a nearly 20\% improvement of
the workflow makespan compared to the best-performing job-based model. However,
better performance comes at the cost of significantly higher complexity of the
implementation and maintenance. We believe that our experiments provide a
valuable insight into the performance, advantages and disadvantages of
alternative cloud-native execution models for scientific workflows.