Hypervisor VM Pinning for Uninterrupted Execution

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In multi-processor systems, existing fair resource allocation methods, such as completely fair schedulers, do not allow for prioritization of certain processes or virtual machines, which can lead to interruptions during computationally intensive tasks like audiovisual rendering or gaming, despite the need for uninterrupted resource allocation.

Innovation Solution

Implementing an unfair resource allocation method where an important virtual machine is pinned to a specific processing device, ensuring it receives substantially all time slots and processing power, thereby avoiding interruptions from other processes or interrupts.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a completely fair scheduler is used to allocate processing resources, then processing resources are allocated fairly among processes, but important virtual machines cannot receive prioritized resource allocation and may be interrupted during computationally intensive tasks

Engineering Contradiction:

Improveuninterrupted execution of important virtual machinesVSAvoidresource allocation fairness

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The patent segments processing resources by dedicating specific processing devices to specific virtual machines. Important virtual machines are assigned dedicated processing devices that are isolated from interruptions by other processes, while other virtual machines share remaining resources. This segmentation resolves the contradiction by providing guaranteed resource allocation for important VMs without completely eliminating fairness for other processes.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent applies local quality by providing different resource allocation characteristics to different virtual machines based on their importance. Important virtual machines receive dedicated processing devices with guaranteed resource access, while less important virtual machines receive shared resources. This creates localized optimization for critical tasks without compromising overall system fairness.

Inventive Principle:

Principle #3Local quality

2Productivity

If processing resources are allocated fairly among all processes, then overall processing device utilization is maximized, but important processes cannot ensure uninterrupted execution during computationally intensive tasks

Engineering Contradiction:

Improveoverall processing device utilizationVSAvoiduninterrupted execution of important processes

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system segments processing devices into dedicated assignments for important virtual machines and shared assignments for other virtual machines. This segmentation allows important processes to have guaranteed uninterrupted execution while the shared pool maintains high utilization through fair scheduling of remaining resources.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent implements dynamic resource allocation where the hypervisor can assign processing devices to virtual machines based on their current needs and importance levels. The system adapts resource distribution in real-time, allowing important processes to secure dedicated resources when needed while maintaining overall system productivity through flexible resource management.

Inventive Principle:

Principle #15Dynamics

3Reliability

If an unfair resource allocation method pins important virtual machines to specific processing devices, then uninterrupted execution is ensured, but processing resource allocation flexibility is reduced

Engineering Contradiction:

Improveuninterrupted execution of important virtual machinesVSAvoidprocessing resource allocation flexibility

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent segments virtual machines into important and less important categories, applying different allocation strategies to each segment. Important virtual machines receive dedicated processing devices for uninterrupted execution, while less important virtual machines receive flexible shared resource allocation. This segmentation maintains adaptability for resource management while ensuring reliability for critical tasks.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system applies local quality by providing dedicated processing devices to important virtual machines while maintaining flexible shared resource allocation for other virtual machines. This creates differentiated service levels that preserve both reliability for critical processes and adaptability for overall resource management.

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS9792152B2Hypervisor managed scheduling of virtual machines

Publication Date: 2017.10.17 RED HAT ISRAEL

AI summary

A hypervisor determines that a virtual machine is important. In response, the hypervisor selects one or more processing devices of a multiprocessor computer system and pins the virtual machine to the selected processing devices. The virtual machine exclusively executes in the selected processing devices resulting in an unfair resource allocation.