Shared Swap File Deduplication for Clone VM Memory Efficiency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In virtual desktop infrastructure (VDI) environments with multiple clone virtual machines (VMs) executing common applications, the storage space required for swap files becomes burdensome due to redundant memory blocks being written to storage multiple times, leading to inefficiencies in both storage space and computing speed.
Innovation Solution
Implementing across-chain deduplication by generating a common deduplication ID and hash table for a chain of VMs, allowing for the identification and reuse of duplicate memory blocks, thereby avoiding redundant writes to storage and optimizing storage usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If hypervisor swapping is used to free host physical memory for other VMs, then memory availability is improved, but storage space required by swap files becomes burdensome
Solution Approach 1:
The patent merges the swap files of multiple clone VMs into a single shared swap file. Instead of each clone VM having its own separate swap file, all clones share a common swap file located in the parent VM's folder, thereby consolidating storage requirements and eliminating redundant storage of identical memory blocks across multiple VMs.
Solution Approach 2:
The shared swap file serves multiple functions: it acts as the swap file for the parent VM and simultaneously serves as the swap file for all clone VMs. This multi-functional approach allows a single storage resource to fulfill the swapping needs of multiple VMs, reducing overall storage consumption.
2Adaptability or versatility
If multiple clone VMs are spawned from a common parent, then virtualization scalability is improved, but storage space consumption increases due to redundant swap file data
Solution Approach 1:
The patent combines the swap files of the parent VM and all its clones into a single shared swap file. This merging approach allows multiple VMs to share the same swap space, eliminating the need to store identical swapped memory blocks multiple times and significantly reducing storage requirements as the number of clones increases.
Solution Approach 2:
Instead of creating physical copies of swap file data for each clone VM, the system creates a reference or link to the shared swap file. The clone VMs reference the same swap file location as the parent VM, allowing them to access the same swap space without duplicating the actual data, thus enabling scalability without proportional storage growth.
3Ease of operation
If swap files are created for each VM, then memory management independence is improved, but storage efficiency deteriorates due to redundant data
Solution Approach 1:
The patent merges the swap files of parent and clone VMs into a single shared swap file, eliminating redundant storage of identical memory blocks while maintaining virtual memory management independence through the virtualization layer.
Solution Approach 2:
The hypervisor acts as an intermediary between the VMs and the shared swap file, managing memory swapping operations for multiple VMs through a single swap file. This intermediary approach allows multiple VMs to share swap space while maintaining the illusion of independent memory management for each VM.
Data Source
AI summary
Virtual memory space may be saved in a clone environment by leveraging the similarity of the data signatures in swap files when a chain of virtual machines (VMs) includes clones spawned from a common parent and executing common applications. Deduplication is performed across the chain, rather than merely within each VM. Examples include generating a common deduplication identifier (ID) for the chain; generating a logical addressing table linked to the deduplication ID, for each of the VMs in the chain; and generating a hash table for the chain. Examples further include, based at least on a swap out request, generating a hash value for a block of memory to be written to a storage medium; and based at least on finding the hash value within the hash table, updating the logical addressing table to indicate a location of a prior-existing duplicate of the block on the storage medium.