Agile Resource Provisioning in Disaggregated Cloud Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cloud computing faces inflexibility in resource configuration and allocation, leading to poor resource utilization and high costs due to fixed hardware configurations and limitations in scaling and descaling, which hinder on-demand access to computing resources.
Innovation Solution
A disaggregated cloud computing environment that dynamically allocates hardware resources based on service level agreements (SLAs), allowing tenants to assemble computer systems with flexible resource configurations suitable for specific workloads, enabling real-time allocation and efficient resource utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If fixed hardware configurations are used in cloud computing, then device complexity is reduced and ease of manufacture is improved, but resource utilization deteriorates and adaptability worsens
Solution Approach 1:
The patent segments hardware resources into separate pools (CPU pool, GPU pool, storage pool, memory pool) that can be independently managed and dynamically allocated to different tenants based on workload requirements, resolving the contradiction between fixed configurations and adaptability
Solution Approach 2:
The system implements dynamic resource allocation where hardware resources can be provisioned, allocated, and de-provisioned in real-time based on service level agreements and workload demands, transforming static fixed configurations into flexible dynamic assignments
2Device complexity
If fixed hardware configurations are used, then device complexity is reduced, but resource utilization deteriorates and productivity worsens
Solution Approach 1:
The patent creates a universal resource pool architecture where a single pool of each hardware type serves multiple tenants and workloads simultaneously, allowing resources to be shared and allocated based on demand, thereby improving productivity without proportionally increasing device complexity
Solution Approach 2:
The system implements automated resource provisioning and allocation mechanisms that dynamically assign hardware resources to tenants based on service level agreements and workload requirements, eliminating manual configuration overhead while maximizing resource utilization and productivity
3Device complexity
If scaling and descaling are limited in fixed configurations, then device complexity is reduced, but adaptability worsens and loss of time increases
Solution Approach 1:
The patent implements dynamic scaling capabilities where hardware resources can be provisioned and de-provisioned on-demand based on workload fluctuations and service level agreements, enabling rapid scaling without fixed configuration constraints while maintaining manageable system complexity
Solution Approach 2:
The system pre-establishes resource pools and allocation frameworks that enable rapid resource provisioning when needed, eliminating the time loss associated with ad-hoc configuration changes while maintaining relatively simple underlying infrastructure
Data Source
AI summary
Various embodiments for agile component-level resource provisioning in a disaggregated cloud computing environment, by a processor device, are provided. Respective members of pools of hardware resources within the disaggregated cloud computing environment are allocated to each respective one of a plurality of tenants according to one of a plurality of service level agreement (SLA) classes. Each respective one of the plurality of SLA classes is characterized by a given response time for the allocation of the respective members of the pools of hardware resources corresponding to a requested workload by the tenant.