Virtual Machine Pooling for Low-Latency Access Under High Load

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Launching virtual machines (VMs) on demand can take a long time, leading to increased wait times and potential failures when multiple requests are received simultaneously, especially in host servers with high loads.

Innovation Solution

A VM management platform maintains a pool of VMs for on-demand access, utilizing machine learning and artificial intelligence to dynamically allocate VMs based on user characteristics, such as organization, role, project, historical usage, and geographical location, reducing wait times and improving reliability.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If VMs are launched on demand in response to client requests, then VM availability is improved, but wait time increases and system reliability deteriorates under high load

Engineering Contradiction:

ImproveVM availabilityVSAvoidwait time

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-launching and maintaining a pool of VMs in a ready state before they are actually needed. The VM management platform continuously maintains multiple VM instances that are pre-configured and available, so when a client requests a VM, an already-running VM can be immediately allocated rather than waiting for a new VM to be launched from scratch.

Inventive Principle:

Principle #10Preliminary action

2Productivity

If VMs are launched on demand, then resource utilization is improved, but system reliability deteriorates when host servers experience high loads

Engineering Contradiction:

Improveresource utilizationVSAvoidVM loading reliability

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system pre-launches VMs in advance and maintains them in a ready state within a managed pool, ensuring that when client requests arrive, pre-configured VMs are immediately available for allocation. This eliminates the risk of VM launch failures under high load conditions while maintaining efficient resource utilization through dynamic allocation from the pre-prepared pool.

Inventive Principle:

Principle #10Preliminary action

3Adaptability or versatility

If multiple VM requests are handled simultaneously, then client service coverage is improved, but host server load increases causing further delays

Engineering Contradiction:

Improveclient service coverageVSAvoidsystem efficiency

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The system pre-launches multiple VMs in advance and maintains them in a ready state within a managed pool. When multiple client requests arrive simultaneously, the VM management platform can immediately allocate pre-configured VMs from the pool without experiencing the overhead of launching new VMs under load, thus maintaining high client service coverage while avoiding the performance degradation that would result from simultaneous VM launches.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20260003662A1Systems and methods for providing virtual machine pooling

Publication Date: 2026.01.01 SCHLUMBERGER TECH CORP

AI summary

Systems and method presented herein are configured to provide pooling of virtual machines (VMs) to improve the functionality of such VMs. For example, a VM management platform is configured to maintain a pool of VMs including a plurality of VMs for on-demand access via a plurality of client devices; to receive a request for access to a VM from a first client device of the plurality of client devices; to identify a first VM from the pool of VMs for use by the first client device; and to provide the first client device with access to the first VM.