Physics development of web-based tools for use in hardware clusters doing lattice physics

TL;DR

This paper discusses the development of web-based tools that enable lattice QCD researchers to manage and utilize multiple computational clusters as a unified meta-facility, improving job management and data handling.

Contribution

It introduces a prototype Lattice Portal that integrates cluster management, data browsing, and file transfer, with plans for multi-site job submission and advanced data policies.

Findings

Prototype system allows job submission and monitoring

Enables browsing data caches and file transfers

Plans for multi-site job management and data policies

Abstract

Jefferson Lab and MIT are developing a set of web-based tools within the Lattice Hadron Physics Collaboration to allow lattice QCD theorists to treat the computational facilities located at the two sites as a single meta-facility. The prototype Lattice Portal provides researchers the ability to submit jobs to the cluster, browse data caches, and transfer files between cache and off-line storage. The user can view the configuration of the PBS servers and to monitor both the status of all batch queues as well as the jobs in each queue. Work is starting on expanding the present system to include job submissions at the meta-facility level (shared queue), as well as multi-site file transfers and enhanced policy-based data management capabilities.