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
Workload-Static Optical Circuit Switching For Scalable LLM Inference Decode
Maximilian Thürmer, Nicolas Scotto di Perto, Eloise Stein et al.
Characterizing Serverless Workloads: A Large-Scale Analysis of Function-as-a-Service Platforms
Saman Akbari, Yassine Lazreg, Mohammadreza Malekabbasi et al.
ForgeKernel: Self-Evolving Kernels Catching and Surpassing Experts and Agents
Yaojian Chen, Dazhi Peng, Yiyun Zheng et al.
Local Distributed Computation under Crash Failures
Diana Ghinea, Fabian Kuhn, Chen-Da Liu-Zhang et al.
TapeSAC: Automated, Pareto-Optimal Fine-Grained Memory Management for Large Model Training
Kaihui Ren, Yifan Zhao, Zejian Wang et al.
Accelerating Offloading-Based MoE Inference by Interleaving Concurrent Requests
Hongseung Yu, In Gim, Kyunghan Lee et al.