Virtual Machine Cloud Restore via Page-Cached Disk Transfers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Uploading and backing up virtual machine data to cloud storage is slow, impacting productivity and putting disaster recovery scenarios at risk.
Innovation Solution
A cloud-based storage account is mounted as a local storage directory on a proxy computing device, enabling page-by-page operations for restore-to-cloud and backup-from-cloud without using mass storage resources at the proxy server, utilizing a pseudo-disk driver for intercepting write and read operations and employing a small cache storage area for staging data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If virtual machine data is uploaded to cloud storage using traditional methods, then data backup is achieved, but the process is slow and impacts productivity
Solution Approach 1:
The patent segments the virtual disk data into pages and processes them individually through a page cache. Instead of restoring the entire virtual disk at once, the system divides the data into manageable page-sized units, allowing parallel processing and efficient cloud upload without requiring mass storage at the proxy server.
Solution Approach 2:
The patent introduces a page cache as an intermediary component between the virtual disk and cloud storage. This small cache storage area acts as a mediator that temporarily holds pages during restore and backup operations, enabling streamlined data flow without requiring large local storage resources at the proxy server.
2Reliability
If mass storage is used at the proxy server for restore operations, then data restoration is possible, but storage resources are consumed and time is increased
Solution Approach 1:
The patent extracts the storage requirement from the proxy server by eliminating the need for mass storage at the proxy location. Instead of storing restored data locally at the proxy, the system directly uploads pages from the page cache to cloud storage, removing the storage burden from the proxy server while maintaining restoration capability.
Solution Approach 2:
The patent changes the storage dimension by moving from local mass storage at the proxy server to cloud-based storage. Instead of requiring large local storage capacity, the system leverages cloud storage resources, effectively shifting the storage dimension from local to remote and eliminating the resource constraint at the proxy server.
3Reliability
If entire virtual disks are downloaded to proxy server before backup, then backup operations can proceed, but the process is slow and consumes resources
Solution Approach 1:
The patent performs preliminary actions by pre-loading only the necessary pages into the page cache before backup operations, rather than downloading entire virtual disks. This selective pre-loading of data pages enables backup operations to proceed efficiently with minimal data transfer and storage requirements at the proxy server.
Solution Approach 2:
The patent applies partial action by downloading and processing only the necessary portions of virtual disk data (pages) rather than the entire disk. This selective approach to data transfer and backup enables faster operation with reduced resource consumption while maintaining complete backup capability through iterative page processing.
Data Source
AI summary
Uploads of restored virtual machine (“VM”) data to cloud storage, e.g., VM restore-to-cloud operations, are performed without having to write whole restored virtual disk files to a proxy server before the virtual disk data begins uploading to cloud. Restored data blocks from a backup source are locally cached, staged for efficiency, and asynchronously uploaded to the cloud page-by-page without tapping mass storage resources on the proxy. Downloads of VM data from cloud storage, e.g., VM backup-from-cloud, are performed without having to download a virtual disk file in its entirety to the proxy server before the backup operation begins generating a backup copy. This speeds up “pulling” VM data from the cloud by pre-fetching and locally caching downloaded data blocks. The cached data blocks are processed for backup and stored page-by-page directly into a secondary copy of the cloud VM virtual-disk file without tapping mass storage resource at the proxy.