Task Allocation in Cloud Environments

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Cloud computing architectures face inefficiencies due to resource fragmentation, leading to performance degradation and increased costs, as resource instances become fragmented over time and are not optimally utilized.

Innovation Solution

A method is implemented where tasks are assigned to resource instances based on their average time to finish, determining if a resource instance has matching average time to finish and available capacity, and if not, another instance is identified or a new one is provisioned to minimize fragmentation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If tasks are assigned to the first available resource instance, then task service speed is improved, but resource fragmentation increases

Engineering Contradiction:

Improvetask service speedVSAvoidresource instance fragmentation

Core Design Contradiction:

SpeedVSStability of the object's composition

Solution Approach 1:

The patent changes the assignment parameter from simple availability to matching average task completion times. By comparing the average time to finish for incoming tasks with the average time to finish for tasks already assigned to resource instances, the system assigns tasks to instances with matching time characteristics, preventing fragmentation while maintaining service speed.

Inventive Principle:

Principle #35Parameter changes

2Productivity

If resource instances are scaled up to handle incoming tasks, then task servicing capability is improved, but resource utilization efficiency deteriorates

Engineering Contradiction:

Improvetask servicing capabilityVSAvoidresource utilization efficiency

Core Design Contradiction:

ProductivityVSLoss of energy

Solution Approach 1:

The system performs preliminary classification of resource instances by their average task completion times before assigning new tasks. By pre-grouping instances based on their performance characteristics, the system can quickly identify suitable matches without trial-and-error assignment, improving both productivity and utilization efficiency.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements a feedback mechanism where the system continuously monitors task completion times and updates the average time to finish for each resource instance. This feedback loop enables dynamic adjustment of task assignments, ensuring that instances are consistently matched with appropriate tasks and preventing both fragmentation and underutilization.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS20230138568A1Task allocation in a cloud environment

Publication Date: 2023.05.04 CITRIX SYSTEMS INC

AI summary

In one aspect, an example methodology implementing the disclosed techniques includes, by a computing device, determining an average time to finish for a first task to be executed and determining whether there is a resource instance that is designated to service tasks whose average time to finish matches the average time to finish for the first task. The method also includes, responsive to a determination that there is a resource instance that is designated to service tasks whose average time to finish matches the average time to finish for the first task, determining whether the resource instance has available capacity to service the first task. The method further includes, responsive to a determination that the resource instance has available capacity to service the first task, assigning the first task to the resource instance.