Multi-Core Monitor Distribution for Network Processing Workloads
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
As networks expand in size and capacity, the increased number of nodes to be monitored can overwhelm a single processor, leading to inefficiencies in processing monitoring workloads in data communication networks.
Innovation Solution
The method involves distributing monitoring tasks across multiple cores in a multi-core system, where each core operates a packet engine, establishing configurations for monitors, computing values based on monitor and service names, and determining which packet engine to assign monitoring tasks to, allowing for efficient workload distribution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single processor is used to handle monitoring tasks, then the system structure is simple, but the processor becomes overburdened as networks expand in size and capacity
Solution Approach 1:
The patent divides the monitoring workload into multiple segments by distributing monitors across multiple packet engines operating on different cores. Each packet engine handles a portion of the monitoring tasks, preventing any single processor from becoming overburdened while maintaining system scalability as networks expand.
2Productivity
If multiple packet engines are deployed to handle increased monitoring tasks, then processing capability improves, but workload distribution complexity increases
Solution Approach 1:
The patent implements self-service through automatic load balancing where each packet engine independently computes a value based on monitor and service names, determines its own workload assignments, and distributes monitoring tasks without requiring complex external coordination or manual configuration.
3Productivity
If monitoring tasks are distributed across multiple cores, then processing efficiency improves, but the complexity of managing monitor configurations increases
Solution Approach 1:
The patent applies universality by using a consistent configuration format and value computation method across all packet engines. Each engine uses the same algorithm to compute values from monitor and service names, ensuring uniformity in workload distribution and simplifying configuration management despite the distributed architecture.
Data Source
AI summary
The present invention is directed towards systems and methods for monitoring services in a multi-core system. The systems and methods distribute the monitors for a service and the ownership of a service across the cores of the multi-core device. The greater resources of the multi-core device process the workload of the monitors for the services and the workload for monitoring the states of the services more efficiently than a single packet engine on a core.