High-Throughput Cloud Computing with the Cloudscheduler VM Provisioning Service

Berghaus, F.; Casteels, Kevin; Driemel, Colson; Ebert, M.; Galindo, Fernando; Leavett-Brown, Colin; Macdonell, Danika Marina; Paterson, Michael; Seuster, R.; Sobie, R.; Tolkamp, S.; Weldon, J.

doi:10.1007/s41781-020-0036-1

Cited by 4 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, local NFS server were setup to provide the software infrastructure and home directories. The High Energy Physics Research Computing (HEP-RC) 6 group at UVic uses cloudscheduler to manage VMs on Openstack clouds on demand depending on jobs in an HTCondor queue [6] [7]. To make use of the same system, HTCondor was adapted as batch system and wrapper scripts written to translate LSF/TORQUE/MAUI commands to HTCondor commands.…”

Section: Preservation Of the Analysis Frameworkmentioning

confidence: 99%

BABAR’s Experience with the Preservation of Data and Analysis Capabilities

Ebert,

Roney,

Sobie

2024

EPJ Web of Conf.

View full text Add to dashboard Cite

The BABAR experiment collected electron-positron collisions at the SLAC National Accelerator Laboratory (SLAC) from 1999-2008. Although data taking has stopped 15 years ago, the collaboration is still actively doing data analyses, publishing results, and giving presentations at international conferences. Special considerations were needed to do analyses using a computing environment that was developed decades ago. A framework is required that preserves the data, data access, and the capability of doing analyses using a well defined and preserved environment. Also, BABAR’s support by SLAC ended at the beginning of 2021. Fortunately, the High Energy Physics Research Computing group at the University of Victoria (UVic), Canada, offered to provide the new home for the main BABAR computing infrastructure, the Grid Computing Centre Karlsruhe offered to host all data for access by analyses running at UVic, and CERN and the IN2P3 Computing Centre offered to store a backup of all data. This paper presents what was done at BABAR to preserve the data and analysis capabilities and what was needed to move the whole computing infrastructure, including collaboration tools and data files, away from SLAC. It will be shown how BABAR preserved the ability to continue to do data analyses and also have a working collaboration tools infrastructure. This paper will describe on BABAR’s experience with such a big change in its infrastructure and what was learned from it, which may be useful to other experiments which are interested in long term analysis support and data preservation in general.

show abstract

Section: Preservation Of the Analysis Frameworkmentioning

confidence: 99%

BABAR’s Experience with the Preservation of Data and Analysis Capabilities

Ebert,

Roney,

Sobie

2024

EPJ Web of Conf.

View full text Add to dashboard Cite

show abstract

“…While integrating opportunistic resources into an existing OBS makes resources directly accessible to users, it also restricts access to the specific group owning the OBS. For example, the meta-scheduler Cloud Scheduler [4] directly integrates resources into the distributed job submission infrastructure of specific collaborations.…”

Section: Single Point Of Entry and The Intermediate Obsmentioning

confidence: 99%

Transparent Integration of Opportunistic Resources into the WLCG Compute Infrastructure

et al. 2021

View full text Add to dashboard Cite

The inclusion of opportunistic resources, for example from High Performance Computing (HPC) centers or cloud providers, is an important contribution to bridging the gap between existing resources and future needs by the LHC collaborations, especially for the HL-LHC era. However, the integration of these resources poses new challenges and often needs to happen in a highly dynamic manner. To enable an effective and lightweight integration of these resources, the tools COBalD and TARDIS are developed at KIT. In this contribution we report on the infrastructure we use to dynamically offer opportunistic resources to collaborations in the World Wide LHC Computing Grid (WLCG). The core components are COBalD/TARDIS, HTCondor, CVMFS and modern virtualization technology. The challenging task of managing the opportunistic resources is performed by COBalD/TARDIS. We showcase the challenges, employed solutions and experiences gained with the provisioning of opportunistic resources from several resource providers like university clusters, HPC centers and cloud setups in a multi VO environment. This work can serve as a blueprint for approaching the provisioning of resources from other resource providers.

show abstract

“…We use MinIO [10] to provide the object storage on single VM instances started on different clouds, each with storage space at the order of 100GB, as well as for a distributed multi-host cluster with a storage capacity of about 45TB. The most used data (in general files needed for most Figure 2: Cloudscheduler schema, Cloudscheduler [2] polls the job scheduler for job requirements and starts/stops VMs on attached clouds when needed depending on those requirements. simulation jobs) is replicated manually to the different MinIO instances and then instantly available via Dynafed as an additional copy.…”

Section: Uvic Instance For Belle-iimentioning

confidence: 99%

“…Instead of using static bare-metal worker nodes, our worker nodes are VMs started dynamically on distributed clouds depending on the resource requirements of a job. The management of the VMs and cloud resources is done by Cloudscheduler [2]. Fig.…”

Section: Introductionmentioning

confidence: 99%

The Dynafed data federator as a grid site storage element

et al. 2020

View full text Add to dashboard Cite

The Dynafed data federator is designed to present a dynamic and unified view of a distributed file repository. We describe our use of Dynafed to construct a production-ready WLCG storage element (SE) using existing grid storage endpoints as well as object storage. Dynafed is used as the primary SE for the Canadian distributed computing cloud systems for the Belle-II experiment, where we use it in production for reading input files. We have run up to 6,000 Belle-II jobs simultaneously on distributed cloud resources, requiring the transfer of approximately 60 TB of input data per day. Similarly, we have been using a Dynafed-based SE in pre-production testing for the ATLAS experiment. We will describe the configuration of Dynafed to make it suitable as a WLCG SE. In particular, we will highlight the improvements within Dynafed that make it possible to do checksum based file verification and 3rd-party file copy via WebDAV. We will also report on a new monitoring system and an automated system that collects storage information from all endpoints.

show abstract

High-Throughput Cloud Computing with the Cloudscheduler VM Provisioning Service

Cited by 4 publications

References 21 publications

BABAR’s Experience with the Preservation of Data and Analysis Capabilities

BABAR’s Experience with the Preservation of Data and Analysis Capabilities

Transparent Integration of Opportunistic Resources into the WLCG Compute Infrastructure

The Dynafed data federator as a grid site storage element

Contact Info

Product

Resources

About