Datacenter Memory Resource Mapping for Application Interference
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current datacenter application scheduling lacks understanding of interaction between applications and underlying computing architecture, leading to ad hoc resource assignment that can hinder performance and cause interference among applications or within the same application.
Innovation Solution
The system determines mapping configurations for applications onto system resources based on performance metrics and resource sharing characteristics, using control circuitry to manage resource allocation and prioritize applications for optimal thread-to-core mapping, potentially leveraging online adaptive learning to adjust mappings dynamically.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If applications are assigned to resources in an ad hoc fashion, then resource allocation is simple and quick, but performance is hindered and interference among applications occurs
Solution Approach 1:
The system changes the parameters of resource mapping by transitioning from ad hoc assignment to mappings based on application characteristics and resource sharing topologies. This involves adjusting mapping configurations to optimize performance metrics while managing complexity through systematic approaches.
Solution Approach 2:
The patent replaces the mechanical/ad hoc resource assignment system with an intelligent system that uses performance metrics, application characteristics, and automated decision-making. This substitution enables performance optimization without proportionally increasing operational complexity.
2Productivity
If multiple applications share system resources, then resource utilization efficiency improves, but interference among applications increases
Solution Approach 1:
The system applies local quality by tailoring resource mappings to specific application characteristics and resource sharing topologies. Each application receives customized mapping configurations based on its needs, reducing interference while maintaining efficient resource utilization.
Solution Approach 2:
The system implements feedback mechanisms by measuring performance metrics and using this information to adjust resource mappings. This feedback loop enables the system to reduce interference among applications while maintaining high resource utilization efficiency through continuous optimization.
Data Source
AI summary
Systems and methods for mapping applications onto system resource of a computing platform are discussed. The computing platform may receive, using control circuitry, a request to run a plurality of applications on a computing platform having a plurality of system resources. The computing platform may determine a plurality of mapping configurations for the plurality of applications onto the plurality of system resources. The computing platform may execute the plurality of applications with each of the plurality of mapping configurations. The computing platform may determine at least one performance metric based on the executed plurality of applications for each of the plurality of mapping configurations. The computing platform may select a selected mapping configuration among the plurality of mapping configurations based on at least one determined performance metric.