In biomedical research, computational methods have become indispensable and their use is increasing, making the efficient allocation of computing resources paramount. Practitioners routinely allocate resources far in excess of what is required for batch processing jobs, leading to not just inflated wait times and costs, but also unnecessary carbon emissions. This is not without reason however, as accurately determining resource needs is complex, affected by the nature of tools, data size, and analysis parameters, especially on popular servers that handle numerous jobs. The Galaxy platform, a web-based hub for biomedical analysis used globally by scientists, exemplifies this challenge. Serving nearly half a million registered users and managing around 2 million monthly jobs, Galaxy's growth outpaces the resources at its disposal. This is necessitating smarter resource utilization. To address this, we have developed a tool named Total Perspective Vortex (TPV) - a software package that right-sizes resource allocations for each job. TPV is able to dynamically set resource requirements for individual jobs and perform meta-scheduling across heterogeneous resources. It also includes a first-ever community-curated database of default resource requirements for nearly 1,000 popular bioinformatics tools. Deployments in Galaxy Australia and Europe demonstrate its effectiveness with meta-scheduling user jobs and an improved experience for systems administrators managing Galaxy servers.

翻译：在生物医学研究中，计算方法已成为不可或缺的工具且其应用日益增长，这使得计算资源的高效分配至关重要。研究人员通常为批处理作业分配远超实际所需的资源，不仅导致等待时间和成本增加，还会产生不必要的碳排放。然而这并非毫无缘由，因为准确确定资源需求十分复杂，受工具特性、数据规模和分析参数等因素影响，尤其在处理大量作业的流行服务器上。以Galaxy平台为例——这个全球科学家广泛使用的生物医学分析网络中心，拥有近50万注册用户，每月管理约200万项作业，其增长速度已超过可用资源。这要求更智能的资源利用方式。为此，我们开发了名为"全视角旋涡"（TPV）的工具包，能够为每项作业合理配置资源。TPV可动态设置单个作业的资源需求，并在异构资源间执行元调度。该工具还首次建立了涵盖近1000种常用生物信息学工具的社区维护默认资源需求数据库。在Galaxy澳大利亚和欧洲的部署证明，该系统在元调度用户作业及改善系统管理员管理Galaxy服务器体验方面均具有显著效果。