{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T19:26:34Z","timestamp":1777058794275,"version":"3.51.4"},"reference-count":33,"publisher":"F1000 Research Ltd","license":[{"start":{"date-parts":[[2024,3,21]],"date-time":"2024-03-21T00:00:00Z","timestamp":1710979200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100006227","name":"Lawrence Livermore National Laboratory LLNL-LDRD Program","doi-asserted-by":"publisher","award":["22-ERD-041"],"award-info":[{"award-number":["22-ERD-041"]}],"id":[{"id":"10.13039\/100006227","id-type":"DOI","asserted-by":"publisher"}]},{"name":"U.S. Department of Energy by Lawrence Livermore National Laboratory","award":["DE-AC52-07NA27344, LLNL-JRNL-855145-DRAFT"],"award-info":[{"award-number":["DE-AC52-07NA27344, LLNL-JRNL-855145-DRAFT"]}]}],"content-domain":{"domain":["f1000research.com"],"crossmark-restriction":false},"short-container-title":["F1000Res"],"abstract":"<ns3:p>Converged computing is an emerging area of computing that brings together the best of both worlds for high performance computing (HPC) and cloud-native communities. The economic influence of cloud computing and the need for workflow portability, flexibility, and manageability are driving this emergence. Navigating the uncharted territory and building an effective space for both HPC and cloud require collaborative technological development and research. In this work, we focus on developing components for the converged workload manager, the central component of batch workflows running in any environment. From the cloud we base our work on Kubernetes, the de facto standard batch workload orchestrator. From HPC the orchestrator counterpart is Flux Framework, a fully hierarchical resource management and graph-based scheduler with a modular architecture that supports sophisticated scheduling and job management. Bringing these managers together consists of implementing Flux inside of Kubernetes, enabling hierarchical resource management and scheduling that scales without burdening the Kubernetes scheduler. This paper introduces the Flux Operator \u2013 an on-demand HPC workload manager deployed in Kubernetes. Our work describes design decisions, mapping components between environments, and experimental features. We perform experiments that compare application performance when deployed by the Flux Operator and the MPI Operator and present the results. Finally, we review remaining challenges and describe our vision of the future for improved technological innovation and collaboration through converged computing.<\/ns3:p>","DOI":"10.12688\/f1000research.147989.1","type":"journal-article","created":{"date-parts":[[2024,3,21]],"date-time":"2024-03-21T10:55:37Z","timestamp":1711018537000},"page":"203","update-policy":"https:\/\/doi.org\/10.12688\/f1000research.crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["The Flux Operator"],"prefix":"10.12688","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4387-3819","authenticated-orcid":false,"given":"Vanessa","family":"Sochat","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aldo","family":"Culquicondor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5260-9019","authenticated-orcid":false,"given":"Antonio","family":"Ojea","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6500-3227","authenticated-orcid":false,"given":"Daniel","family":"Milroy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"2560","published-online":{"date-parts":[[2024,3,21]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"6256","DOI":"10.3390\/su14106256","article-title":"A systematic survey on energy-efficient techniques in sustainable cloud computing.","volume":"14","author":"S Bharany","year":"2022","journal-title":"Sustainability."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1-7","DOI":"10.48161\/qaj.v1n2a36","article-title":"Iot and cloud computing issues, challenges and opportunities: A review.","volume":"1","author":"M Sadeeq","year":"2021","journal-title":"Qubahan Academic Journal."},{"key":"ref3","first-page":"684-693","article-title":"Quakeflow: a scalable machine-learning-based earthquake monitoring workflow with cloud computing.","volume":"232","author":"W Zhu","year":"2023","journal-title":"Geophys. J. Int."},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1145\/3430936","article-title":"The decline of computers as a general purpose technology.","author":"N Thompson","year":"March 2021"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"255-288","DOI":"10.1201\/9781003190011-12","article-title":"High-performance computing and its requirements in deep learning.","author":"B Jena","year":"2022","journal-title":"High-Performance Medical Image Processing."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1071-1079","DOI":"10.1080\/17460441.2021.1932812","article-title":"The machine learning life cycle and the cloud: implications for drug discovery.","volume":"16","author":"O Spjuth","year":"2021","journal-title":"Expert Opin. Drug Discov."},{"key":"ref8","first-page":"336-338","article-title":"End-to-end machine learning using kubeflow.","author":"J George","year":"2022","journal-title":"5th Joint International Conference on Data Science & Management of Data (9th ACM IKDD CODS and 27th COMAD)."},{"key":"ref9","article-title":"Machine learning operations (mlops): Overview, definition, and architecture.","author":"D Kreuzberger","year":"2023","journal-title":"IEEE Access."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"3587-3608","DOI":"10.1007\/s11831-022-09708-9","article-title":"A comprehensive survey on security challenges in different network layers in cloud computing.","volume":"29","author":"M Jangjou","year":"2022","journal-title":"Arch. Comput. Methods Eng."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"202-213","DOI":"10.1016\/j.future.2020.04.006","article-title":"Flux: Overcoming scheduling challenges for exascale workflows.","volume":"110","author":"D Ahn","year":"2020","journal-title":"Futur. Gener. Comput. Syst."},{"key":"ref17","first-page":"5-6","article-title":"Go at google.","author":"R Pike","year":"2012","journal-title":"Proceedings of the 3rd annual conference on Systems, programming, and applications: software for humanity."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"10-16","DOI":"10.1109\/CANOPIEHPC54579.2021.00006","article-title":"It\u2019s a Scheduling Affair: GROMACS in the Cloud with the KubeFlux Scheduler.","author":"C Misale","year":"2021","journal-title":"2021 3rd International Workshop on Containers and New Orchestration Paradigms for Isolated Environments in HPC (CANOPIE-HPC)."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.8312253","article-title":"flux-framework\/flux-operator.","author":"V Sochat","year":"September 2023"},{"key":"ref21","article-title":"R&D 100 award winners announced in Process\/Prototyping and Software\/Services categories.","author":"P Heney","year":"2021"},{"key":"ref23","article-title":"(2023)]CNCF_Cloud_Native_Computing_Foundation2023-pi CNCF [Cloud Native Computing Foundation]. Enabling HPC & ML workloads with the latest kubernetes job features- micha\u0142 wo\u017aniak & vanessa sochat.","year":"May 2023"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"669-680","DOI":"10.1016\/j.im.2018.11.002","article-title":"The faster the better? innovation speed and user interest in open source software.","volume":"56","author":"J Dong","year":"July 2019","journal-title":"Inf. Manag."},{"key":"ref25","article-title":"Internet, innovation, and open source.","author":"I Tuomi","year":"January 2001"},{"key":"ref26","article-title":"Enabling openmpi workloads on bare-metal infrastructure using kubernetes.","author":"M Biliaiev","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"108171","DOI":"10.1016\/j.cpc.2021.108171","article-title":"LAMMPS - a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales.","volume":"271","author":"A Thompson","year":"2022","journal-title":"Comput. Phys. Commun."},{"key":"ref28","first-page":"9396-9409","article-title":"ReaxFF: A reactive force field for hydrocarbons.","volume":"105","author":"A Duin","year":"October 2001","journal-title":"J. Phys. Chem. A."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.10248093","article-title":"converged-computing\/operator-experiments: F1000Research Submission Release.","author":"V Sochat","year":"December 2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.8312253","article-title":"flux-framework\/flux-operator.","author":"V Sochat","year":"September 2023"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"1-11","DOI":"10.1109\/SC.2010.18. 10.1109\/SC.2010.18","article-title":"Design, Modeling, and Evaluation of a Scalable Multi-Level Checkpointing System.","author":"A Moody","year":"2010","journal-title":"Proceedings of the 2010 ACM\/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, SC\u201910, USA, IEEE Computer Society."},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3341325.3341995","author":"B Thurgood","year":"2019","journal-title":"Proceedings of the 3rd International Conference on Future Networks and Distributed Systems, ICFNDS\u201919, New York, NY, USA."},{"key":"ref33","first-page":"1-1","article-title":"The need for speed: From electric supercars to cloud bursting for design.","author":"D Drako","year":"2022","journal-title":"Proceedings of the 2022 International Symposium on Physical Design."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"33","DOI":"10.12688\/f1000research.29032.2","article-title":"Sustainable data analysis with snakemake.","volume":"10","author":"F M\u00f6lder","year":"January 2021","journal-title":"F1000Res."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"316-319","DOI":"10.1038\/nbt.3820","article-title":"Nextflow enables reproducible computational workflows.","volume":"35","author":"P Di Tommaso","year":"April 2017","journal-title":"Nat. Biotechnol."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"1723-1737","DOI":"10.1109\/TETC.2020.3019202","article-title":"StreamFlow: Cross-Breeding cloud with HPC.","volume":"9","author":"I Colonnelli","year":"October 2021","journal-title":"IEEE Trans. Emerg. Top. Comput."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"626-627","DOI":"10.1038\/s41559-023-02008-w","article-title":"Better incentives are needed to reward academic software development.","volume":"7","author":"C Merow","year":"May 2023","journal-title":"Nat. Ecol. Evol."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"e230163","DOI":"10.1148\/radiol.230163","article-title":"ChatGPT and other large language models are double-edged swords.","volume":"307","author":"Y Shen","year":"April 2023","journal-title":"Radiology."},{"key":"ref39","doi-asserted-by":"publisher","first-page":"1986-2007","DOI":"10.1002\/spe.2885","article-title":"Impact of etcd deployment on kubernetes, istio, and application performance.","volume":"50","author":"L Larsson","year":"October 2020","journal-title":"Softw. Pract. Experience."},{"key":"ref40","first-page":"1-16","article-title":"A massively parallel infrastructure for adaptive multiscale simulations: modeling RAS initiation pathway for cancer.","author":"F Di Natale","year":"November 2019","journal-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, number Article 57 in SC\u201919, New York, NY, USA. Association for Computing Machinery."},{"key":"ref41","doi-asserted-by":"publisher","first-page":"1-16","DOI":"10.1145\/3458817.3476210","article-title":"Generalizable Coordination of Large Multiscale Workflows: Challenges and Learnings at Scale.","author":"H Bhatia","year":"2021","journal-title":"SC21: International Conference for High Performance Computing, Networking, Storage and Analysis."}],"container-title":["F1000Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/f1000research.com\/articles\/13-203\/v1\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/f1000research.com\/articles\/13-203\/v1\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/f1000research.com\/articles\/13-203\/v1\/iparadigms","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,11]],"date-time":"2024-06-11T21:10:27Z","timestamp":1718140227000},"score":1,"resource":{"primary":{"URL":"https:\/\/f1000research.com\/articles\/13-203\/v1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,21]]},"references-count":33,"URL":"https:\/\/doi.org\/10.12688\/f1000research.147989.1","relation":{"has-review":[{"id-type":"doi","id":"10.5256\/f1000research.162246.r284364","asserted-by":"subject"},{"id-type":"doi","id":"10.5256\/f1000research.162246.r267225","asserted-by":"subject"},{"id-type":"doi","id":"10.5256\/f1000research.162246.r284364","asserted-by":"object"},{"id-type":"doi","id":"10.5256\/f1000research.162246.r267225","asserted-by":"object"}]},"ISSN":["2046-1402"],"issn-type":[{"value":"2046-1402","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,21]]},"assertion":[{"value":"Indexed","URL":"https:\/\/f1000research.com\/articles\/13-203\/v1#article-reports","order":0,"name":"referee-status","label":"Referee status","group":{"name":"current-referee-status","label":"Current Referee Status"}},{"value":"10.5256\/f1000research.162246.r267225, Rafael Ferreira da Silva, National Center for Computational Sciences, Oak Ridge National Laboratory, Oak Ridge, Tennessee, 07 Jun 2024, version 1, indexed","URL":"https:\/\/f1000research.com\/articles\/13-203\/v1#referee-response-267225","order":0,"name":"referee-response-267225","label":"Referee Report","group":{"name":"article-reports","label":"Article Reports"}},{"value":"10.5256\/f1000research.162246.r284364, David Hancock, Pervasive Technology Institute, Indiana University, Bloomington, 11 Jun 2024, version 1, indexed","URL":"https:\/\/f1000research.com\/articles\/13-203\/v1#referee-response-284364","order":1,"name":"referee-response-284364","label":"Referee Report","group":{"name":"article-reports","label":"Article Reports"}},{"value":"This work was performed under the auspices of the U.S. Department of Energy by Lawrence Livermore National Laboratory under Contract DE-AC52-07NA27344, LLNL-JRNL-855145-DRAFT. This project was supported by the LLNL-LDRD Program under Project No. 22-ERD-041. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.","order":2,"name":"grant-information","label":"Grant Information"},{"value":"This is an open access article distributed under the terms of the Creative Commons Attribution Licence, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.","order":0,"name":"copyright-info","label":"Copyright"}]}}