Intelligent Rack Testing via Virtual Machine Load Balancing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Managing and maintaining large quantities of computing hardware in internet data centers is challenging due to the complexity of testing and maintaining numerous items of computing hardware.
Innovation Solution
A system comprising an intelligent computer rack with a processor and storage device, connected to a server, which includes modules for time detection, load balancing, testing, and repair, allowing for efficient testing and maintenance of physical machines by transferring virtual machines based on load balancing strategies and executing test scripts during low peak periods.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If testing and maintenance is performed on large quantities of computing hardware, then hardware reliability is improved, but system complexity and management difficulty increase
Solution Approach 1:
The system segments the large quantity of computing hardware into individual testable units within a rack-mounted configuration. Each computing device can be independently tested, maintained, and replaced without affecting the entire system, thereby managing complexity through modular organization while maintaining high hardware reliability through systematic testing.
Solution Approach 2:
The patent introduces an intermediary testing system that acts as a mediator between the computing hardware and maintenance personnel. This intermediary system automates the testing and maintenance processes, reducing the complexity burden on operators while ensuring thorough hardware reliability checks through standardized test procedures.
2Reliability
If computing hardware is tested and maintained frequently, then hardware reliability is improved, but productivity and operational time are reduced
Solution Approach 1:
The system implements periodic testing and maintenance schedules for computing hardware, where devices are taken offline for testing only when necessary (e.g., when failure symptoms are detected or during scheduled maintenance windows). This periodic action ensures hardware reliability through regular checks while minimizing productivity loss by avoiding continuous or overly frequent testing that would unnecessarily reduce operational time.
3Ease of operation
If manual testing and maintenance procedures are used, then operational flexibility is maintained, but time consumption and labor costs increase
Solution Approach 1:
The patent implements self-service capabilities where the testing system can autonomously diagnose hardware issues, execute appropriate test sequences, and even trigger maintenance procedures without extensive manual intervention. This self-service approach maintains operational flexibility by allowing the system to adapt to different hardware configurations while dramatically reducing the time required for testing and maintenance compared to purely manual procedures.
Data Source
AI summary
A method for testing computing hardware detects the current time as being within a predetermined time period and transfers virtual machines (VMs) from a plurality of physical machines to other physical machines as targets according to a load balancing strategy. The load balancing strategy sums of a load ratio of one physical machine including the VM and a load ratio of one physical machine as a target for the transfer; if the sum of the two ratios is less than a preset load ratio, the VM-transferring physical machine is put into a standby state when the transfer takes place as long as the current time is still inside the predetermined time period. Physical machines which are in the standby state and have not been tested are awoken, and the awoken physical machines are connected to the server for testing.