Workload Migration via Background Caching in Hybrid Networks

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Traditional workload migration to cloud servers often results in significant downtime and disruption due to the need for extensive up-front planning and data synchronization, especially when dealing with large data transfers, and the workload data remains unused until fully migrated.

Innovation Solution

The technique involves migrating workload data in the background using pre-fetching and caching, allowing the workload to execute on the target node with minimal downtime and enabling on-demand data access, while maintaining the primary data source at the source node until the migration is complete.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional workload migration is performed by copying data to cloud servers before workload execution, then data consistency is ensured, but significant downtime and workload disruption occur

Engineering Contradiction:
Improvedata consistencyVSAvoiddowntime
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary data copying to cloud storage before workload execution, but uses caching mechanisms to pre-load data into memory, so that when the workload starts, the data is already available in both on-premises and cloud locations, eliminating the traditional sequential dependency

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

A caching layer is introduced as an intermediary between the workload and the storage systems. The cache can serve data requests from either on-premises or cloud storage, allowing the workload to execute without waiting for complete data migration while maintaining data consistency through coordinated updates

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If workload data is migrated to cloud servers, then additional computing resources become available, but the migration process requires stopping computing processes and causes significant downtime

Engineering Contradiction:
Improvecloud resource availabilityVSAvoidworkload continuity
Core Design Contradiction:
Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system dynamically switches between on-premises and cloud storage based on workload needs and migration progress. The caching layer can adaptively serve data from the fastest available source, allowing continuous workload execution while data is being migrated in the background

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

Data is pre-copied to cloud storage and pre-loaded into cache memory before the workload needs it. This preliminary action ensures that when the workload executes on cloud infrastructure, the data is already available, eliminating migration-induced downtime

Inventive Principle:
Principle #10Preliminary action

3Reliability

If data synchronization is performed during workload migration, then data consistency is maintained, but productivity is reduced due to the sequential nature of the process

Engineering Contradiction:
Improvedata synchronizationVSAvoidmigration speed
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system maintains continuous data synchronization between on-premises and cloud storage through the caching layer. While the workload executes and accesses data, the cache continuously updates with data from both sources, ensuring consistency without interrupting the workload or requiring sequential migration steps

Inventive Principle:
Principle #20Continuity of useful action

Solution Approach 2:

Data synchronization is performed in parallel with workload execution through background copying and caching operations. The most frequently accessed data is pre-synchronized to the cache, allowing the workload to access up-to-date data without waiting for complete migration of all data

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3249889B1Workload migration across a hybrid network
Publication Date: 2023.07.05 GOOGLE LLC
  • EP3249889B1 patent drawingFigure 1
  • EP3249889B1 patent drawingFigure 2
  • EP3249889B1 patent drawingFigure 3

AI summary

A method and system for workload migration across a hybrid network is provided. The method and system are directed to migrating a workload to a cloud by transferring the workload computing processes to the cloud, streaming workload data as necessary to execute the workload processes in the cloud, transferring the remaining workload data in a background process to cloud storage, and then completing migration by switching the primary data source of the workload computing processes to the cloud storage.