Virtual Storage Migration via Snapshot Change Logs

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The migration of large virtual storage devices between nodes is time-consuming due to the need to transfer extensive data over network infrastructure, which can take hours or days, posing a challenge in efficiently relocating virtual resources across different hardware setups.

Innovation Solution

A method that involves capturing snapshots of virtual storage devices at specific points in time and transmitting only the changes made since then, allowing the new node to generate and update a new instance of the resource based on these snapshots, thereby reducing the data transfer required during migration.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the entire virtual storage device data is copied from one node to another node, then the migration is complete and accurate, but the data transfer time is extremely long (hours or days)

Engineering Contradiction:
Improvemigration accuracyVSAvoiddata transfer time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by creating snapshots of the virtual storage device at the source node before migration begins. These snapshots capture the state of the storage device at specific points in time, allowing the destination node to reconstruct the data without receiving the entire dataset during migration. This preliminary capture of data states enables faster migration while maintaining accuracy.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The invention extracts only the necessary data elements from the complete virtual storage device - specifically, it extracts snapshot data and change logs rather than transferring the entire storage device data. By taking out only the essential components (snapshots and changes since snapshot), the system achieves migration with minimal data transfer while ensuring the destination node can reconstruct the complete state.

Inventive Principle:
Principle #2Taking out (Extraction)

2Reliability

If the entire virtual storage device data is transmitted over the network, then the migration is complete, but the network bandwidth consumption is extremely high

Engineering Contradiction:
Improvemigration completenessVSAvoidnetwork bandwidth
Core Design Contradiction:
ReliabilityVSLoss of energy

Solution Approach 1:

The system extracts and transmits only the minimal necessary data components - snapshots and change logs - rather than the complete virtual storage device data. This extraction approach ensures migration completeness while dramatically reducing network bandwidth consumption, as only the differences and state references need to be transmitted rather than the entire dataset.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

Instead of copying and transmitting the entire virtual storage device data, the system creates copies of snapshot data and change information at the source node, then transmits these lightweight copies to the destination node. The destination node uses these copies to reconstruct the complete virtual storage device state, achieving migration with minimal network bandwidth usage.

Inventive Principle:
Principle #26Copying

Data Source

PatentUS9542108B2Efficient migration of virtual storage devices to a remote node using snapshots
Publication Date: 2017.01.10 SCALE COMPUTING INC
  • US9542108B2 patent drawing
  • US9542108B2 patent drawing
  • US9542108B2 patent drawing

AI summary

A system, method, and computer program product are provided for performing fast migration of a virtual resource from one node to another node. The method includes the steps of receiving a first request to migrate a resource from a first node to a second node, transmitting a second request to the second node to create a new instance of the resource, collecting a set of changes associated with the resource in a data structure, and transmitting the data structure that includes the set of changes to the second node. The second node generates the new instance of the resource based on a snapshot of the resource captured by the first node at a previous point in time and updates the new instance of the resource based on the set of changes such that the new instance of the resource on the second node matches the resource on the first node.