Copy-on-read Blob System for Instant VM Data Access
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cloud computing environments face delays and resource inefficiencies due to the slow process of copying large source blobs for virtual machines, which consumes storage resources and prolongs the time before virtual machines can begin operation.
Innovation Solution
Implementing a copy-on-read blob system where data is copied only when requested, with a link blob to store changes, allowing virtual machines to access data immediately without copying the entire source blob, thus enabling quicker operation and conserving storage resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the entire source blob is copied to each node before virtual machine operation, then data availability is ensured, but the time delay increases and storage resources are consumed
Solution Approach 1:
The source blob is prepared in advance and stored in a repository, with metadata pre-configured to enable rapid access. Virtual machines can immediately access the source blob from the repository without waiting for full copying, while data is pre-stage to target nodes as needed
Solution Approach 2:
Only the necessary portions of the source blob are extracted and copied to individual nodes based on specific virtual machine requirements, rather than copying the entire blob. This selective extraction reduces both time delay and storage consumption while maintaining data availability for required operations
2Ease of operation
If the entire source blob is copied to each node, then data access is enabled, but storage resources are considerably consumed
Solution Approach 1:
Different nodes store different portions of the source blob based on their specific requirements. Each node maintains only the local quality or subset of data it needs, rather than duplicating the entire blob, thereby reducing overall storage consumption while maintaining data access capability
Solution Approach 2:
The source blob is segmented into multiple portions or blocks that can be independently stored and accessed. Nodes receive only the specific segments they require, enabling efficient storage utilization while maintaining the ability to access necessary data portions
3Reliability
If the source blob is copied in its entirety, then complete data is available, but the copying process is slow especially for large blobs
Solution Approach 1:
Instead of copying the entire source blob, only the necessary partial portions are copied to each node. This partial action approach achieves the required data availability for virtual machine operations without the time penalty of copying excessive data that may not be needed
Data Source
AI summary
Methods, systems, apparatuses, and computer program products are provided that enable immediate access to data associated with a source blob. The foregoing is achieved by creating a copy-on-read blob based on the source blob and a link blob based on the copy-on-read blob for each virtual machine to be deployed. When creating the copy-on-read blob, the source blob is not copied. Instead, data from the source blob is copied to the copy-on-read blob upon request by a virtual machine. Subsequent requests for that data are retrieved from the copy-on-read blob. Each link blob stores write data provided by its corresponding virtual machine. When a virtual machine requests data, its corresponding link blob is checked for the data. If the data is not stored therein, the copy-on-read blob is checked for the data. If the copy-on-read blob does not store the data, the data is retrieved from the source blob.