Cloud Compute Farm Resource Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Allocating compute resources in a cloud environment is time-consuming and inefficient, leading to increased costs and resource wastage due to the need for users to lease extra instances to ensure availability during peak demand.
Innovation Solution
A system that monitors the use of compute resources across multiple client cloud systems, calculates an aggregate compute resource schedule, and intelligently allocates and delivers compute workers to a compute farm, allowing for efficient transfer of resources to client systems based on demand.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If users lease extra instances to ensure availability during peak demand, then service reliability is improved, but resource cost and complexity increase
Solution Approach 1:
Multiple client cloud systems are merged into a single compute farm, allowing their compute workers to be pooled together. This consolidation enables efficient resource sharing and eliminates the need for each client to independently lease extra instances for peak demand, thereby maintaining service reliability while reducing overall resource management complexity
Solution Approach 2:
The compute farm creates a universal resource pool that serves multiple client cloud systems simultaneously. A single compute worker in the farm can be allocated to any client that needs it, providing multi-functional capability that replaces the need for dedicated redundant instances at each client site
2Adaptability or versatility
If compute resources are allocated on-demand from cloud provider, then resource flexibility is improved, but allocation time increases
Solution Approach 1:
Client cloud systems pre-allocate compute workers to a compute farm before they are actually needed. This preliminary action creates a ready pool of compute resources that can be immediately transferred to clients when demand arises, eliminating the time-consuming on-demand allocation process while maintaining flexibility through the pre-established resource pool
3Reliability
If users lease extra compute instances to ensure availability, then service reliability is improved, but resource wastage increases
Solution Approach 1:
The compute farm implements a dynamic allocation system where compute workers are temporarily assigned to clients during peak demand and then recovered back to the pool when no longer needed. This recovering mechanism ensures that redundant instances are not permanently leased but instead are reused across multiple clients, eliminating resource wastage while maintaining availability during demand periods
Data Source
AI summary
Apparatus, methods, and computer-readable media facilitating access, security, and management of compute resources in a cloud environment are disclosed herein. In one aspect, a computer system, for example a server or a cloud computer system, may monitor a use of compute resources by a plurality of client cloud systems to calculate an aggregate compute resource schedule. The computer system may request and allocate a first set of compute workers to a compute farm based on the aggregate compute resource schedule. The computer system may transfer a first subset of the allocated first set of compute workers from the compute farm to a first client cloud system based on the monitored use of compute resources and a second subset of the allocated first set of compute workers from the compute farm to a second client cloud system based on the monitored use of compute resources.