Resource Credit Pools for Virtual Instance Workloads

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing virtualization technologies face challenges in efficiently managing unpredictable workloads and resource utilization across multiple virtual machines sharing physical computer resources, leading to potential contention and conflicts.

Innovation Solution

Implementing resource credit pools that allow virtual compute instances to accumulate and utilize credits for physical resources dynamically, enabling flexible and high-performance resource allocation, with additional credits provided from a pool to handle bursts or high workloads, and migrating instances to optimize resource utilization.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of energy

If multiple virtual machines share physical computer resources, then resource utilization efficiency is improved, but contention and conflicts occur when utilizing different virtual computing resources

Engineering Contradiction:

Improveresource utilization efficiencyVSAvoidcontention and conflicts

Core Design Contradiction:

Loss of energyVSReliability

Solution Approach 1:

The patent segments physical computer resources into virtualized resources allocated to different virtual machines through virtualization layers. Each virtual machine receives dedicated virtual resources (CPU, memory, storage, networking) that are segmented from the physical hardware, allowing multiple VMs to share physical resources without direct contention while maintaining isolation and reliability.

Inventive Principle:

Principle #1Segmentation

2Ease of operation

If fixed resources are allocated to virtual machines, then resource allocation is simplified, but flexibility to handle unpredictable workloads is reduced

Engineering Contradiction:

Improveresource allocation simplicityVSAvoidflexibility for unpredictable workloads

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent implements dynamic resource allocation where virtual machine resource assignments can change over time based on workload demands. The system monitors resource usage patterns and dynamically adjusts resource allocation, allowing VMs to scale resources up or down as needed while maintaining operational simplicity through automated management.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The patent changes resource allocation parameters dynamically based on workload conditions. Resource allocation is not fixed but adjusts parameters such as CPU allocation, memory allocation, and storage capacity according to actual usage patterns, enabling flexibility for unpredictable workloads while maintaining ease of operation through automated parameter adjustment.

Inventive Principle:

Principle #35Parameter changes

3Reliability

If resources are over-provisioned to handle bursts, then handling of unpredictable workloads is improved, but resource waste increases

Engineering Contradiction:

Improvehandling of unpredictable workloadsVSAvoidresource waste

Core Design Contradiction:

ReliabilityVSLoss of substance

Solution Approach 1:

The patent ensures continuous useful action by maintaining a pool of available resources that can be immediately allocated to handle workload bursts without interruption. Rather than over-provisioning all resources continuously, the system keeps resources in a ready state that can be activated on-demand, eliminating waste while ensuring reliability for unpredictable workloads.

Inventive Principle:

Principle #20Continuity of useful action

Solution Approach 2:

The patent performs preliminary action by pre-configuring resource pools and allocation mechanisms in advance, but only activates additional resources when actually needed. This allows the system to handle bursts reliably without permanently over-provisioning, as resources are prepared beforehand but only consumed when workloads require them, preventing waste.

Inventive Principle:

Principle #10Preliminary action

4Adaptability or versatility

If resource credits are accumulated individually per instance, then flexibility for each instance is improved, but overall resource optimization is reduced

Engineering Contradiction:

Improveflexibility per instanceVSAvoidoverall resource optimization

Core Design Contradiction:

Adaptability or versatilityVSLoss of energy

Solution Approach 1:

The patent merges individual instance resource credit pools into a shared pool that benefits all instances collectively. While each instance maintains flexibility to request and receive credits based on its needs, the pooled approach allows resources to be optimized across the entire system, reducing waste by allocating credits from underutilized instances to those with higher demands.

Inventive Principle:

Principle #5Merging (Combining)

Data Source

PatentUS9626210B2Resource credit pools for replenishing instance resource credit balances of virtual compute instances

Publication Date: 2017.04.18 AMAZON TECH INC

AI summary

A provider network may implement resource credit pools to replenish resource credit balances for virtual compute instances. A resource credit pool may be maintained that makes resource credits available to virtual compute instances authorized to obtain resource credits from the resource credit pool. Resource credits from the resource credit pool may be applicable to increase utilization of physical computer resource for a virtual compute instance. In response to a resource credit request for an authorized virtual compute instance, a number of resource credits to add to an individual resource credit balance for the authorized virtual compute instance may be determined. A response may be sent indicating the number of resource credits to add to the individual resource credit balance and the resource credit pool may be updated to remove the number of resource credits from the resource credit pool.