Cloud Bursting Resource Allocation Automation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current cloud bursting mechanisms rely heavily on manual monitoring and administration to identify resource shortages and excesses, leading to inefficiencies in resource allocation and increased costs, as users must manually request additional resources or return them to providers.
Innovation Solution
A computer program and method that automatically determines unused resources in a cluster, calculates the required resources for pending workloads, and identifies allocatable host systems to remove or add, using updated workload class profiling information to optimize resource allocation and minimize costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual monitoring and administration is used to identify resource shortages and excesses, then resource allocation can be adjusted, but the process requires significant manual intervention and administrative effort
Solution Approach 1:
The system enables self-service automation where the cloud bursting mechanism automatically monitors resource usage, identifies shortages and excesses, and adjusts resource allocation without manual intervention. The workload manager continuously evaluates resource metrics and autonomously provisions or de-provisions cloud resources based on current workload demands
Solution Approach 2:
The system implements continuous feedback loops where resource usage metrics are monitored, analyzed, and used to automatically adjust resource allocation. The workload manager receives feedback on resource consumption patterns and dynamically modifies cloud resource provisioning to optimize both cost and performance
2Reliability
If cloud hosts are provisioned to meet peak resource demand, then resource availability is sufficient during spikes, but excess capacity incurs unnecessary costs when demand is low
Solution Approach 1:
The system dynamically adjusts cloud resource provisioning based on real-time workload demands. Resource allocation is not static but continuously adapts to changing conditions, scaling up during peak demand periods and scaling down during low-utilization periods to optimize the balance between availability and cost
Solution Approach 2:
The system changes resource allocation parameters dynamically based on workload metrics. By monitoring resource usage patterns and demand fluctuations, the system adjusts the number of provisioned cloud hosts to match actual needs, transitioning between different provisioning states to eliminate waste while maintaining reliability
3Adaptability or versatility
If cloud bursting mechanism is implemented, then scalability is improved and cost savings are achieved, but complex resource management and coordination between local and cloud resources are required
Solution Approach 1:
The workload manager serves multiple functions within a single unified system. It simultaneously handles local resource management, cloud resource provisioning, workload scheduling, and cost optimization, eliminating the need for separate complex management systems for each function
Data Source
AI summary
Provided are a computer program product, system, and method for determining allocatable host system resources to remove from a cluster and return to a host service provider. A determination is made of unused host system resources, that are not currently being used by workloads, in a plurality of host systems. A determination is made of required resources for computational resources required to complete processing unfinished workloads that have not completed. A determination is made of an amount of resources to remove from the cluster by subtracting the unused host system resources by the required resources for computational resources. At least one of the host systems available for the workloads is selected to remove from the cluster having resources that satisfy the amount of resources to remove.