Network Traffic Sampling via Virtual Output Queues on Non-Accelerated Line Cards
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Monitoring network traffic in interconnected device networks often burdens processors, affecting network device performance due to the workload required for sampling network traffic.
Innovation Solution
Configuring a network device with a virtual output queue (VOQ) associated with an internal interface of a non-accelerated line card connected to an accelerated line card, allowing for selective sampling and processing of network traffic data units, which reduces the workload on processors by offloading sampling activities to a sampling engine.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If network traffic sampling is performed using processors, then network traffic monitoring functionality is achieved, but processor workload increases and network device performance deteriorates
Solution Approach 1:
The patent divides the network device into multiple line cards, where only specific line cards are equipped with sampling engines. This segmentation allows sampling functionality to be distributed rather than centralized in processors, reducing overall processor workload while maintaining monitoring capability across the network device.
Solution Approach 2:
The patent introduces sampling engines as intermediary components between network traffic and processors. These sampling engines perform the sampling function independently, acting as mediators that handle the workload of traffic analysis without burdening the main processors, thus resolving the contradiction between monitoring capability and processor performance.
2Productivity
If sampling engines are added to all line cards, then sampling capability is improved, but device complexity and cost increase
Solution Approach 1:
The patent applies local quality by equipping only specific line cards with sampling engines rather than all line cards. This selective approach ensures that sampling capability is enhanced where needed while avoiding the complexity and cost of adding sampling engines to every line card, maintaining system efficiency without unnecessary complexity.
3Measurement precision
If network traffic is sampled at high rate, then monitoring precision is improved, but processor workload and energy consumption increase
Solution Approach 1:
Sampling engines serve as intermediaries that perform high-rate sampling operations independently of the main processors. This allows the system to achieve high measurement precision through detailed traffic sampling while the energy-intensive processing is handled by dedicated sampling engines rather than general-purpose processors, reducing overall energy consumption.
Data Source
AI summary
Accelerating monitoring of network traffic by: configuring a first network chip of a non-accelerated line card with a VOQ associated with an internal interface that is connected to a second network chip of a first accelerated line card; receiving, at the first network chip, a data unit; selecting, by the first network chip, the data unit based on a traffic sampling rate; adding information identifying the data unit as having been selected for sampling to obtain a selected data unit; and sending the selected data unit from the first network chip to the second network chip using the VOQ and the internal interface. The second network chip identifies the selected data unit and, based on the identification, appends a sampling header to the data unit to obtain a sampled data unit, and transmits the sampled data unit to the sampling engine of the first accelerated line card.