Unified Server Storage Virtualization Migration

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current technologies face challenges in coordinating server virtualization management with storage virtualization management, particularly in geographically dispersed data centers, and fail to effectively manage power consumption, leading to increased operational costs and potential overuse of resources.

Innovation Solution

The solution integrates server and storage virtualization management, allowing for dynamic and automatic migration of applications across data centers while considering data replication availability and power consumption, using virtual machine software and Storage Area Networks to ensure seamless operation and efficient resource allocation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If server virtualization is implemented to consolidate servers and improve resource efficiency, then server resource utilization and availability are improved, but coordination with storage virtualization management becomes complex and difficult

Engineering Contradiction:
Improveserver resource utilizationVSAvoidcoordination complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent combines server virtualization management and storage virtualization management into a unified management framework. The system integrates server resource allocation with storage resource allocation, allowing coordinated management of both resources through a single platform. This merging eliminates the complexity of separate management systems and enables seamless migration of virtual machines along with their associated storage resources across geographically dispersed data centers.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The management system performs multiple functions including server virtualization management, storage virtualization management, resource allocation, and migration coordination. This universal system can manage diverse resources (servers, storage, networks) across multiple data centers through standardized interfaces, reducing operational complexity while maintaining high resource utilization.

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

2Reliability

If applications are migrated across geographically dispersed data centers to balance load and improve availability, then service continuity is improved, but ensuring data replication availability and consistency becomes more difficult

Engineering Contradiction:
Improveservice continuityVSAvoiddata replication management
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system performs preliminary data replication and validation before initiating application migration. Storage resources are pre-provisioned and data is replicated to target data centers in advance, ensuring data availability and consistency is maintained during the migration process. This preliminary action prevents data loss and ensures seamless service continuity.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements continuous monitoring and feedback mechanisms to track data replication status, consistency, and availability during migration. Real-time feedback allows the system to adjust migration processes, ensure data integrity, and maintain service continuity across geographically dispersed data centers.

Inventive Principle:
Principle #23Feedback

3Productivity

If server consolidation is pursued to reduce costs and improve efficiency, then operational costs are reduced, but power consumption per cubic volume increases

Engineering Contradiction:
Improveoperational efficiencyVSAvoidpower consumption density
Core Design Contradiction:
ProductivityVSUse of energy by moving object

Solution Approach 1:

The system dynamically allocates and migrates workloads across data centers based on real-time conditions including power consumption levels, resource utilization, and environmental factors. This dynamic approach allows the system to optimize the balance between operational efficiency and energy consumption by shifting loads to more efficient locations or times, reducing overall power consumption density while maintaining high productivity.

Inventive Principle:
Principle #15Dynamics

4Power

If data centers operate at higher power consumption levels to support increased computing capacity, then processing capability is improved, but operational costs and cooling requirements increase significantly

Engineering Contradiction:
Improveprocessing capabilityVSAvoidoperational cost
Core Design Contradiction:
PowerVSUse of energy by stationary object

Solution Approach 1:

The system adds the dimension of geographic distribution to resource allocation, enabling workloads to be shifted across multiple data centers based on power consumption conditions. By utilizing spatial distribution, the system can maintain high processing capability while reducing operational costs by operating in locations or time periods with lower energy costs and better cooling efficiency.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Data Source

PatentUS8285849B2Storage and service provisioning for virtualized and geographically dispersed data centers
Publication Date: 2012.10.09 HITACHI VANTARA LTD
  • US8285849B2 patent drawing
  • US8285849B2 patent drawing
  • US8285849B2 patent drawing

AI summary

Geographically dispersed data centers each include servers and storage systems and are in communication with each other. An application is installed on a guest operating system on a virtual machine set up on a server at a first data center. The application accesses a logical unit on a storage system at the first data center. When migration of the application is initiated, the process determines whether any of the data centers has server resources and storage resources required to receive migration of the application. A destination data center is selected from candidate data centers meeting requirements for migration of the application. The application and guest operating system are migrated from the first data center to a second virtual machine set up on a second server at the destination data center. If a replica of the LU is not already present at the destination data center, the LU is also replicated.