Generalized Resource Accounting with Boundary-Level Metric Agents
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods struggle to accurately attribute compute resource usage to specific nodes, particularly in cloud environments where resources are shared among multiple tenants, leading to improper charging and inefficiencies.
Innovation Solution
Implementing metric tracking agents and counters that define the scope of processes and log resource usage at each compute node, allowing precise attribution of resource usage to individual nodes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If cloud resources are shared among multiple tenants to improve resource utilization and reduce costs, then resource efficiency is improved, but the ability to accurately attribute resource usage to specific compute nodes deteriorates
Solution Approach 1:
The patent segments resource usage tracking by implementing metric tracking agents at each compute node boundary and using scope definitions to partition the tracking responsibility. Each node's resource consumption is measured independently through dedicated metric counters, allowing precise attribution even in shared cloud environments where multiple tenants utilize common infrastructure.
2Measurement precision
If metric tracking agents are implemented at each system boundary to improve resource usage tracking accuracy, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The metric tracking agents operate autonomously at each compute node boundary, independently collecting and reporting their own resource usage metrics without requiring centralized control or complex coordination mechanisms. This self-service approach simplifies the overall system architecture while maintaining high measurement precision across distributed cloud infrastructure.
3Measurement precision
If scope definitions are transmitted across system boundaries to improve resource attribution accuracy, then measurement precision is improved, but loss of information increases due to potential scope definition mismatches
Solution Approach 1:
The system implements feedback mechanisms where metric tracking agents continuously monitor resource usage against defined scopes and report discrepancies. This feedback loop enables real-time detection and correction of scope definition mismatches, ensuring consistent resource attribution across system boundaries while maintaining the precision benefits of scoped metric tracking.
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
Techniques for utilizing a metric tracking agent to track how resources are used to process a payload across different network boundaries are disclosed herein. A process that is to be performed on a payload within a boundary is identified. A metric tracking agent is also identified, where this metric tracking agent defines a scope of the process and is associated with a metric counter used to determine a metric value for the process. While the process is being performed in accordance with the defined scope, the metric value is calculated so as to reflect the resource usage expended by the network boundary and is logged by a log associated with the metric tracking agent. The metric tracking agent, which includes the metric value, is then provided to either a subsequent system boundary or to a metric store.