Dynamic Resource Model for Composed System Workloads

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In cloud computing environments, data centers face inefficiencies due to either over- or under-allocation of resources for workloads, leading to suboptimal utilization of available computing hardware.

Innovation Solution

The method involves receiving a workload, extracting its characteristics, matching them to a resource model that defines an initial compute element configuration and modifications, composing a composed system from a resource pool, and dynamically adjusting resources based on the model to optimize resource utilization.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If more resources are dedicated to each workload, then reliability is improved, but loss of substance increases due to inefficient utilization

Engineering Contradiction:

Improveworkload execution reliabilityVSAvoidresource utilization efficiency

Core Design Contradiction:

ReliabilityVSLoss of substance

Solution Approach 1:

The system dynamically modifies the configuration of compute elements during workload execution based on monitored performance metrics and resource utilization. The resource model specifies configuration modifications that are applied in response to changing workload conditions, transforming static resource allocation into dynamic adaptation that maintains reliability while optimizing utilization.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The invention changes the parameters of compute element configuration (such as number of processors, memory allocation, I/O capabilities) based on the resource model and actual workload performance. By adjusting these parameters during execution, the system ensures adequate resources for reliability while avoiding excessive allocation that would waste resources.

Inventive Principle:

Principle #35Parameter changes

2Loss of substance

If fewer resources are dedicated to each workload, then loss of substance decreases, but productivity deteriorates due to over-utilization

Engineering Contradiction:

Improveresource utilization efficiencyVSAvoidworkload execution efficiency

Core Design Contradiction:

Loss of substanceVSProductivity

Solution Approach 1:

The system continuously monitors workload execution performance and resource utilization metrics, then uses this feedback to determine when configuration modifications should be applied. The resource model defines trigger conditions based on monitored parameters, creating a closed-loop control system that adjusts resources to maintain optimal productivity while preventing over-utilization.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The resource model pre-defines configuration modifications and trigger conditions before workload execution begins. By preparing these modification rules in advance, the system can quickly respond to changing conditions without delaying workload execution, thus maintaining productivity while optimizing resource usage.

Inventive Principle:

Principle #10Preliminary action

3Device complexity

If static resource allocation is used, then device complexity is reduced, but adaptability deteriorates due to inability to respond to changing workload conditions

Engineering Contradiction:

Improveresource allocation management complexityVSAvoidworkload condition adaptability

Core Design Contradiction:

Device complexityVSAdaptability or versatility

Solution Approach 1:

The system uses a resource model that copies and adapts proven configuration patterns for different workload types. Instead of managing complex dynamic allocation logic for each workload, the system applies pre-defined resource models that capture optimal configurations, reducing management complexity while maintaining adaptability through model selection and parameter adjustment.

Inventive Principle:

Principle #26Copying

4Adaptability or versatility

If dynamic resource modification is implemented, then adaptability is improved, but device complexity increases due to configuration management overhead

Engineering Contradiction:

Improveworkload condition adaptabilityVSAvoidconfiguration management complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The resource allocation system is segmented into distinct components: workload characterization, resource model selection, configuration modification application, and monitoring. This segmentation allows each component to be independently managed and optimized, reducing overall system complexity while enabling sophisticated dynamic adaptation through coordinated operation of the segments.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS11288102B2Modifying resources for composed systems based on resource models

Publication Date: 2022.03.29 LENOVO GLOBAL TECHNOLOGIES SWITZERLAND INTERNATIONAL GMBH

AI summary

Modifying resources for composed systems based on resource models including receiving a workload for execution on a composed system; extracting workload characteristics from the workload; matching the workload characteristics to a resource model, wherein the resource model comprises an initial configuration of compute elements for the composed system and a configuration modification to the initial configuration of the compute elements as the workload executes; composing the composed system using the initial configuration of compute elements described by the resource model, wherein the composed system comprises a subset of compute elements from a resource pool of compute elements; and executing, based on the resource model, the workload using the composed system, including modifying the initial configuration of the compute elements according to the resource model.