Fine-Grained Authorization for Job and Resource Management Using Akenti and the Globus Toolkit
M. Thompson, A. Essiari, K. Keahey, V. Welch, S. Lang, B. Liu
Abstract
As the Grid paradigm is adopted as a standard way of sharing remote resources across organizational domains, the need for fine-grained access control to these resources increases. This paper presents an authorization solution for job submission and control, developed as part of the National Fusion Collaboratory, that uses the Globus Toolkit 2 and the Akenti authorization service in order to perform fine-grained authorization of job and resource management requests in a Grid environment. At job startup, it allows the system to evaluate a user's Resource Specification Language request against authorization policies on resource usage (determining how many CPUs or memory a user can use on a given resource or which executables the user can run). Furthermore, based on authorization policies, it allows other virtual organization members to manage the user's job.
Create a lesson
Related papers
PixelFlow: Token-Level Workload Management for Efficient Distributed DiT Serving
Zhexiang Zhang, Minchen Yu, Yifan Sun et al.
A Kubernetes-Native Request Router for Quality-Aware Inference Serving in the Computing Continuum
Ignjat Karanovic, Pantelis A. Frangoudis, Ivan Čilić et al.
Accelerating Sharded Data Parallelism at Scale with Federated Learning
Gianluca Mittone, Marco Aldinucci
Distributed Edge Inference: an Experimental Study on Multiview Detection
Gianluca Mittone, Giulio Malenza, Marco Aldinucci et al.
P-GADMM: Parallel Group-Based ADMM for Asynchronous Optimization in Heterogeneous Edge Networks
Gaiguo Wei, Qingying Zhang, Heqiang Wang et al.
VERA: Reinforcement Learning for Dynamic Memory Scaling of HPC Workloads in Kubernetes
Ade Pramono, Jie Ren, Ivy Peng