Network Latency Measurement via Flow Records
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for determining network latency are inefficient and can cause network slowdowns, as they often require active monitoring that burdens infrastructure and may not accurately reflect real network performance, while passive monitoring systems are costly and resource-intensive.
Innovation Solution
A system that calculates network latency using existing infrastructure by collecting traffic information from flow records such as NetFlow, JFlow, or IPFIX packets, allowing for real-time data measurement without the need for additional infrastructure or synchronization of device clocks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If active monitoring systems conduct large scale network testing to determine latency accurately, then measurement precision improves, but network productivity deteriorates due to increased traffic load and potential interruptions
Solution Approach 1:
The patent applies self-service by enabling network infrastructure devices to automatically generate and export flow-based packets containing timing information without external intervention. The devices autonomously capture flow start/stop times and make this data available for latency calculation, eliminating the need for active monitoring traffic while maintaining measurement capability
Solution Approach 2:
The patent introduces flow-based packets as an intermediary carrier that transports timing information from network infrastructure devices to the monitoring system. These packets serve as a mediator that conveys necessary measurement data without requiring direct active probing of the network, thus avoiding traffic load while enabling indirect latency measurement
2Measurement precision
If traditional passive monitoring systems deploy probes throughout the network to monitor traffic, then measurement coverage improves, but device complexity and cost increase due to multiple probes and span port requirements
Solution Approach 1:
The patent applies universality by enabling network infrastructure devices to serve dual purposes: their primary network function (routing, switching) and a secondary monitoring function (generating flow-based packets with timing information). This eliminates the need for separate dedicated probes while maintaining comprehensive monitoring coverage across the network
Solution Approach 2:
The patent merges the monitoring function with existing network infrastructure devices. Instead of deploying separate probe systems that require additional span ports and complex probe management, the solution combines latency measurement capabilities directly into the network devices that already handle traffic, thereby reducing overall system complexity
3Measurement precision
If active monitoring systems transmit test traffic across the network, then network latency can be measured, but loss of substance occurs as test traffic consumes network bandwidth and resources
Solution Approach 1:
The patent converts the harmful effect of requiring measurement traffic into a beneficial solution by using the existing flow traffic itself as the measurement carrier. The same production traffic that must traverse the network is also used to carry timing information, thereby eliminating the need for separate test traffic and converting what would be wasted resources into useful measurement data
Data Source
AI summary
The disclosure presents a system, method, and computer readable medium for computing network latencies. Network devices using flow processors create network traffic summary information in the form of flow records. A harvester may gather, process, and analyze flow records to find matching flows. Using matching flows, a harvester computes the latency, either one-way or round-trip, between two devices on the network. This information may be exported or stored on other devices on the network. The teachings of the present disclosure enable wide network coverage through the use of existing network traffic summary records. Further, the present disclosure mitigates network slowdowns associated with monitoring equipment. The present disclosure also reduces or eliminates the need for clock synchronization between devices on the network.