Credential Map Resource Allocation in Compute Clusters
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current resource management systems in compute environments, such as grids and clusters, face inefficiencies due to the complexity of allocating resources, heterogeneous resource availability, and the inability to reserve resources effectively over time, leading to management overhead and fragmentation, which limits flexibility in meeting performance goals and user requirements.
Innovation Solution
A system and method that generates credential maps and resource availability maps to optimize resource allocation within a compute environment, allowing for dynamic reservation and allocation of resources based on available resources and constraints, ensuring optimal usage while maintaining policy compliance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If resources are reserved in advance for future jobs, then resource availability and quality of service are improved, but system complexity and management overhead increase
Solution Approach 1:
The system performs preliminary actions by creating standing reservations in advance for future resource allocation. These reservations are established before actual job execution, allowing the system to pre-allocate resources based on predicted needs and organizational policies, thereby improving resource availability while automating the management process
Solution Approach 2:
The system implements self-service through automated policy enforcement and credential mapping. The credential map automatically translates user credentials into resource allocation decisions, and the system self-regulates resource distribution according to predefined policies without requiring manual intervention, reducing management overhead while maintaining reliability
2Adaptability or versatility
If resource allocation is optimized for specific users and groups, then user satisfaction and performance goals are improved, but system complexity increases
Solution Approach 1:
The system changes parameters by dynamically adjusting resource allocation based on user credentials, organizational policies, and job requirements. The credential map transforms static user identities into dynamic allocation parameters, allowing the system to adapt resource distribution to specific user needs while managing complexity through automated policy-based decisions
Solution Approach 2:
The system segments resource allocation by creating distinct credential maps for different users and groups. Each credential map independently handles resource distribution for specific organizational units, allowing customized allocation strategies for different segments while maintaining overall system coherence through centralized policy enforcement
3Reliability
If multiple credential types are tracked and enforced, then policy compliance and security are improved, but processing time and system complexity increase
Solution Approach 1:
The system performs preliminary action by pre-computing credential maps that encode policy compliance rules. These maps are generated in advance and store the results of complex credential evaluations, allowing the system to quickly enforce multiple credential types during resource allocation without repeating time-consuming verification processes
Solution Approach 2:
The system creates simplified copies of complex credential information in the form of credential maps. These maps contain condensed representations of user credentials, group memberships, and policy rules, allowing the system to enforce comprehensive policy compliance while processing time is reduced by working with the simplified map structures rather than raw credential data
Data Source
AI summary
The invention relates to a system, method and computer-reliable medium, as well as grids and clusters managed according to the method described herein. An example embodiment relates to a method of processing a request for resources within a compute environment. The method is practiced by a system that contains modules configured or programmed to carry out the steps of the invention. The system receives a request for resources, generates a credential map for each credential associated with the request, the credential map comprising a first type of resource mapping and a second type of resource mapping. The system generates a resource availability map, generates a first composite intersecting map that intersects the resource availability map with a first type of resource mapping of all generated credential maps and generates a second composite intersecting map that intersects the resource availability map and a second type of resource mapping of all the generated credential maps. With the first and second composite intersecting maps, the system can allocate resources within the compute environment for the request based on at least one of the first composite intersecting map and the second composite intersecting map. The allocations or reservation for the request can then be made in an optimal way for parameters such as the earliest time possible based on available resources and also that maintains the constraints on the requestor.