Building a Distributed Computing System for LDMX Bryngemark, Lene Kristian; Cameron, David; Dutta, Valentina ...
EPJ Web of Conferences,
01/2021, Letnik:
251
Conference Proceeding, Journal Article
Recenzirano
Odprti dostop
Particle physics experiments rely extensively on computing and data services, making e-infrastructure an integral part of the research collaboration. Constructing and operating distributed computing ...can however be challenging for a smaller-scale collaboration. The Light Dark Matter eXperiment (LDMX) is a planned small-scale accelerator-based experiment to search for dark matter in the sub-GeV mass region. Finalizing the design of the detector relies on Monte-Carlo simulation of expected physics processes. A distributed computing pilot project was proposed to better utilize available resources at the collaborating institutes, and to improve scalability and reproducibility. This paper outlines the chosen lightweight distributed solution, presenting requirements, the component integration steps, and the experiences using a pilot system for tests with large-scale simulations. The system leverages existing technologies wherever possible, minimizing the need for software development, and deploys only non-intrusive components at the participating sites. The pilot proved that integrating existing components can dramatically reduce the effort needed to build and operate a distributed e-infrastructure, making it attainable even for smaller research collaborations.
Distributed e-Infrastructure is a key component of modern BIG Science. Service discovery in e-Science environments, such as Worldwide LHC Computing Grid (WLCG), is a crucial functionality that relies ...on service registry. In this paper we re-formulate the requirements for the service endpoint registry based on our more than 10 years experience with many systems designed or used within the WLCG e-Infrastructure. To satisfy those requirements the paper proposes a novel idea to use the existing well-established Domain Name System (DNS) infrastructure together with a suitable data model as a service endpoint registry. The presented ARC Hierarchical Endpoints Registry (ARCHERY) system consists of a minimalistic data model representing services and their endpoints within e-Infrastructures, a rendering of the data model embedded into DNS-records, a lightweight software layer for DNS-record management and client-side data discovery. Our approach for the ARCHERY registry required minimal software development and inherits all the benefits of one of the most reliable distributed information discovery source of the internet, the DNS infrastructure. In particular, deployment, management and operation of ARCHERY is fully relying on DNS. Results of ARCHERY deployment use-cases are provided together with performance analysis.
Particle physics experiments rely extensively on computing and data services, making e-infrastructure an integral part of the research collaboration. Constructing and operating distributed computing ...can however be challenging for a smaller-scale collaboration.
The Light Dark Matter eXperiment (LDMX) is a planned small-scale accelerator-based experiment to search for dark matter in the sub-GeV mass region. Finalizing the design of the detector relies on Monte-Carlo simulation of expected physics processes. A distributed computing pilot project was proposed to better utilize available resources at the collaborating institutes, and to improve scalability and reproducibility.
This paper outlines the chosen lightweight distributed solution, presenting requirements, the component integration steps, and the experiences using a pilot system for tests with large-scale simulations. The system leverages existing technologies wherever possible, minimizing the need for software development, and deploys only non-intrusive components at the participating sites. The pilot proved that integrating existing components can dramatically reduce the effort needed to build and operate a distributed e-infrastructure, making it attainable even for smaller research collaborations.
Particle physics experiments rely extensively on computing and data services, making e-infrastructure an integral part of the research collaboration. Constructing and operating distributed computing ...can however be challenging for a smaller-scale collaboration. The Light Dark Matter eXperiment (LDMX) is a planned small-scale accelerator-based experiment to search for dark matter in the sub-GeV mass region. Finalizing the design of the detector relies on Monte-Carlo simulation of expected physics processes. A distributed computing pilot project was proposed to better utilize available resources at the collaborating institutes, and to improve scalability and reproducibility. This paper outlines the chosen lightweight distributed solution, presenting requirements, the component integration steps, and the experiences using a pilot system for tests with large-scale simulations. The system leverages existing technologies wherever possible, minimizing the need for software development, and deploys only non-intrusive components at the participating sites. The pilot proved that integrating existing components can dramatically reduce the effort needed to build and operate a distributed e-infrastructure, making it attainable even for smaller research collaborations.
Rainbow framework: Running virtual machines on demand as a grid jobs Boretskyi, Oleksandr; Salnikov, Andrii; Sliusar, Ievgen ...
2015 IEEE 8th International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS),
2015-Sept., Letnik:
2
Conference Proceeding
Rainbow is the system for running hardware accelerated virtual machines with an interactive access capability as grid jobs submitted to the Advanced Resource Connector (ARC) 1 powered infrastructure. ...Methods for running virtual machine as a grid jobs as well as Rainbow architecture has been proposed and implemented for practical use in the Ukrainian National Grid (UNG). Rainbow framework had been successfully applied in the MedGrid project for visualization and analysis of ECG stored on UNG resources by means of running proprietary software developed for OS Windows 2.
Design and application of web service and desktop user client for working with medical DICOM-images in Ukrainian Grid infrastructure are described. Web-service provides transparent replication of ...data in grid storage elements. Client consists of graphical front-end, network back-end and provides functions of image anonymization-deanonymization, searching, visualizing, archiving etc. Clients are easily extensible so new data transfer protocols, image procession functions, grid job submission and results retrieving may be easily integrated. Proposed clients are developed, tested and deployed in several Ukrainian institutions for testing and pre-production operation.
PDF
