Workload Virtual Instance Migration Across Heterogeneous Environments
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current techniques inadequately manage, distribute, and restore computing workloads among devices with different settings, leading to compatibility issues and inefficiencies in resource utilization.
Innovation Solution
A method and system for managing and distributing workloads by parking a virtual instance of a workload in a repository, allowing it to be unparked in a different environment with distinct settings, while retaining its operating state, using a park module, unpark module, policy module, and translation module to handle execution parameters and policies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a workload is migrated between devices with different settings, then adaptability is improved, but compatibility is worsened
Solution Approach 1:
The patent creates a virtual instance (copy) of the workload that can be migrated between devices. The virtual instance encapsulates the workload's execution state and configuration, allowing it to be copied and restored on different devices with different settings without losing compatibility or execution context.
Solution Approach 2:
The patent transforms the workload into a virtual instance with modifiable execution parameters. By changing the representation of the workload from device-specific to virtualized, the system enables migration across devices with different settings while maintaining functional compatibility through parameter adaptation.
2Use of energy by moving object
If a virtual instance is powered off and restored, then resource utilization is improved, but recovery time is worsened
Solution Approach 1:
The system performs preliminary actions by saving incremental recovery points during workload execution. These recovery points are prepared in advance, so when the virtual instance needs to be restored, the system can quickly resume from the most recent recovery point rather than starting from scratch, reducing recovery time while maintaining resource efficiency.
Solution Approach 2:
The patent implements periodic saving of incremental recovery points during workload execution. This periodic action allows the system to balance resource utilization (by powering off virtual instances when not needed) with recovery time (by having regularly updated recovery points available for quick restoration).
Data Source
AI summary
Apparatuses, methods, systems, and program products are disclosed for workload management and distribution. A method includes parking a virtual instance of a workload in a repository. The workload may be executing in a first virtual environment that is configured with a first set of execution parameters prior to being parked. The method includes receiving a request to unpark the virtual instance of the workload from the repository to a second virtual environment. The method includes unparking the virtual instance of the workload at the second virtual environment. The second virtual environment may be configured with a second set of execution parameters that are different than the first set of execution parameters. The virtual instance of the workload may be unparked at the second virtual environment using the second set of execution parameters such that the unparked virtual instance of the workload retains its operating state from the first virtual environment.