Storage Offload VM Migration Across Heterogeneous Platforms
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing VM migration tools consume excessive network and CPU resources due to server-based data copy technology, and lack the ability to utilize storage-based copy technology because they do not recognize the source LDEV and storage array, leading to inefficient and costly migrations, especially in scenarios where VM platform vendors change hands.
Innovation Solution
A method and system that utilizes storage offload engines to transfer VM data efficiently by offloading data transfer operations from the CPU to the storage subsystem, selecting appropriate copy technologies based on storage conditions, and ensuring data format compatibility during migration, allowing seamless migration across virtualization platforms without additional capacity requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If server-based data copy technology is used for VM migration, then VM data can be transferred from source to target, but CPU and network resources are consumed excessively
Solution Approach 1:
The patent extracts the data copy function from the server (CPU) and relocates it to the storage array. The storage array independently performs the data copying operation, eliminating the need for server-based data transfer mechanisms and thereby reducing CPU and network resource consumption during VM migration.
Solution Approach 2:
The storage array acts as an intermediary between the source and target VM data. Instead of the server directly copying data between VMs, the storage array mediates the data transfer process, enabling efficient data movement without burdening the server's CPU and network resources.
2Reliability
If existing VM migration tools are used, then VM data can be transferred, but storage-based copy technology cannot be utilized due to lack of source LDEV and storage array recognition
Solution Approach 1:
The patent implements a universal interface that enables the storage array to recognize and work with source LDEVs from different virtualization platforms. This multi-functional capability allows the storage array to serve as a copy target regardless of the source platform, enabling both storage-based and server-based copy technologies to function across heterogeneous environments.
3Reliability
If server-based copy technology is used, then VM migration can be performed, but migration time is extended and efficiency is reduced
Solution Approach 1:
The patent extracts the data copy operation from the server processing queue and assigns it to the storage array's dedicated copy engine. This separation allows parallel execution of server tasks and data copying, significantly reducing overall migration time and improving productivity.
Solution Approach 2:
The patent leverages the storage array's native copy capability to create efficient data duplication during VM migration. The storage array's optimized copy engine performs data replication at storage speed rather than network speed, reducing migration time and improving efficiency.
Data Source
AI summary
Systems and methods involve obtaining a source identifier of a source volume to be migrated based on an execution of a process comprising transmitting an instruction to a virtual machine management system to request the source identifier of the source volume; obtaining a destination identifier of a destination volume; selecting a copy configuration based on parameters of the source volume identified by the source identifier and the destination volume identified by the destination identifier; and executing a copy operation on the source volume according to the copy configuration.