Virtual Computer Performance Monitoring via Resource Correlation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In virtual computer systems, monitoring performance is inadequate as it only focuses on a single guest OS, failing to account for dynamic resource allocation and potential impacts on other virtual computers sharing resources, leading to ineffective management strategies.

Innovation Solution

A method is introduced that involves a computer system with a processor for executing a virtualization program, allowing resources to be logically divided into independent virtual computers, where performance information from both virtual computers is collected and correlated with resource allocation data, enabling effective decision-making even when resources fluctuate dynamically.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If performance monitoring is carried out only for a single guest OS, then monitoring complexity is reduced, but performance management completeness deteriorates because dynamic resource allocation and impacts on other virtual computers cannot be detected

Engineering Contradiction:
Improvemonitoring complexityVSAvoidperformance management completeness
Core Design Contradiction:
Device complexityVSLoss of information

Solution Approach 1:

The patent merges performance monitoring of multiple guest OSes into a unified monitoring system. The performance information acquisition unit collects performance data from multiple guest operating systems simultaneously, and the storage unit stores this information together with resource allocation data, enabling comprehensive performance management while maintaining manageable system complexity through integrated architecture.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The monitoring system is designed with multi-functionality to handle diverse virtual computer environments. The performance information acquisition unit can obtain performance data from any guest OS, and the storage unit universally stores this information along with resource allocation data from the virtualization program, making the system adaptable to various virtualization scenarios without requiring separate monitoring mechanisms for each guest OS.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Productivity

If resource allocation is dynamically adjusted based on load, then resource utilization efficiency is improved, but performance monitoring reliability deteriorates because performance data may not reflect actual resource states

Engineering Contradiction:
Improveresource utilization efficiencyVSAvoidperformance monitoring reliability
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent implements preliminary action by acquiring performance information from guest OSes and resource allocation information from the virtualization program simultaneously and storing them together with timestamp correlation. This ensures that performance data and resource allocation data are captured at the same moment, preventing mismatches that would occur if resources were dynamically adjusted between measurement and recording, thereby maintaining monitoring reliability despite dynamic resource allocation.

Inventive Principle:
Principle #10Preliminary action

3Adaptability or versatility

If virtualization settings are changed to optimize performance, then system adaptability is improved, but system stability deteriorates because setting changes may affect other virtual computers sharing the same host resources

Engineering Contradiction:
Improvesystem adaptabilityVSAvoidsystem stability
Core Design Contradiction:
Adaptability or versatilityVSStability of the object's composition

Solution Approach 1:

The patent implements feedback by storing both performance information from guest OSes and resource allocation information from the virtualization program in a correlated manner with timestamp data. This creates a feedback mechanism where system administrators can observe the actual impact of virtualization setting changes on multiple virtual computers simultaneously, allowing them to adjust settings adaptively while maintaining system stability through informed decision-making based on comprehensive performance data.

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS8826290B2Method of monitoring performance of virtual computer and apparatus using the method
Publication Date: 2014.09.02 HITACHI LTD
  • US8826290B2 patent drawing
  • US8826290B2 patent drawing
  • US8826290B2 patent drawing

AI summary

Provided are a method and an apparatus for monitoring performance of a virtual computer. In a method of controlling a computer system including a computer, the computer executes a virtualization program for causing logically divided resources of the computer to operate as first and second virtual computers, the first virtual computer executes a first OS, and the second virtual computer executes a second OS. In the method, information regarding the resources allocated to the first virtual computer and the second virtual computer by the virtualization program is obtained from the virtualization program, information indicating performance of the first virtual computer is obtained from the first OS, information indicating performance of the second virtual computer is obtained from the second OS, the obtained information and information indicating a time of obtainment of the information are stored in a storage system, and stored information is output.