Autoscaling VM Resource Control via Dependency Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autoscaling technologies face challenges in appropriately controlling the number of virtual machines (VMs) and containers, as manual effort is required to set resource allocation thresholds, leading to inefficient performance improvements due to complex dependencies between VMs/containers and resource allocation amounts.
Innovation Solution
An autoscale-type performance assurance system that includes a server for collecting resource allocation data and another server for calculating dependency and determining resource control amounts, allowing for automated adjustment of VMs/containers and resources based on performance metrics, eliminating the need for manual intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual threshold values for resource allocation are set beforehand, then resource control can be performed, but the system requires significant time and effort for configuration and cannot appropriately control the number of VMs/containers
Solution Approach 1:
The system performs self-service by automatically analyzing performance logs and determining the appropriate number of VMs/containers without manual intervention. The determination unit automatically identifies which VMs/containers should be scaled based on performance data, eliminating the need for manual threshold configuration and expert knowledge while achieving appropriate resource control.
Solution Approach 2:
The system implements feedback by continuously collecting performance logs and using them to automatically adjust the number of VMs/containers. The determination unit analyzes performance data and feeds back control decisions to the autoscaling function, creating a closed-loop system that automatically optimizes resource allocation based on actual performance outcomes.
2Reliability
If the number of VMs/containers is increased to enhance server performance, then communication service quality improves, but resources are wasted when access is low
Solution Approach 1:
The system applies dynamics by making the number of VMs/containers adjustable and responsive to changing conditions. Instead of fixed resource allocation, the system dynamically scales the number of VMs/containers based on real-time performance logs and access patterns, allowing optimal adaptation between high and low traffic conditions to maintain service quality while avoiding resource waste.
3Device complexity
If resource allocation amounts are manually stipulated for each VM/container, then resource control is possible, but the complex dependencies between VMs/containers and resources make appropriate control difficult
Solution Approach 1:
The system extracts the complex task of determining optimal resource allocation from manual processes. The determination unit automatically analyzes performance logs to identify which VMs/containers should be scaled and by how much, separating this complex analytical task from manual configuration and enabling effective autoscaling control without requiring manual stipulation of resource allocation amounts.
Data Source
AI summary
An autoscale-type performance assurance system performs autoscaling to increase or reduce the number of VMs/containers V1 to V4 generated in a server and resources of V1 to V4. A compute includes a plurality of types of V1 to V4, a data collection unit that collects a resource allocation amount of V1 to V4, and a resource control unit that performs autoscaling to increase or reduce the amount of resources of V1 to V4 according to a resource control amount. A controller includes a dependency calculation unit that calculates, based on the collected resource allocation amount, a degree of dependency indicating whether the resource allocation amount is dependent on a performance related to V1 to V4 for providing a communication service quality, and an autoscaling determination unit that obtains a resource control amount for increasing or reducing only resources related to the calculated degree of dependency indicating being dependent.