Multi-Stage CAM Packet Classification Engine
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional content-addressable memory (CAM) devices are impractical for classifying packets due to their limited capacity and high cost when dealing with large packet sizes, as they require a large number of entries to accommodate various classification criteria, leading to scalability issues.
Innovation Solution
A multi-stage classification engine is employed, where each stage examines specific criteria associated with a packet, using VLAN and port/channel tables, and content-addressable memory (CAM) stages to generate rules and identifiers, allowing for efficient classification of packets using conventional CAM devices that would otherwise be impractical.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional CAM devices are used for packet classification, then classification accuracy can be achieved, but the device capacity and cost become prohibitively large
Solution Approach 1:
The patent divides the single large CAM structure into multiple smaller CAM stages (first CAM stage, second CAM stage, third CAM stage). Each stage handles a portion of the classification task, examining different packet fields sequentially. This segmentation reduces the memory capacity requirement of each individual CAM device while maintaining overall classification accuracy through multi-stage processing.
2Adaptability or versatility
If CAM capacity is increased to handle larger packet sizes, then classification completeness improves, but cost and scalability deteriorate
Solution Approach 1:
The classification process is segmented into multiple stages, each handling specific packet fields. The first CAM stage examines certain fields, the second CAM stage examines other fields, and the third CAM stage performs final classification. This allows the system to achieve comprehensive classification without requiring a single oversized CAM, thereby reducing cost and improving scalability.
Solution Approach 2:
The patent transitions from a single-dimension CAM structure to a multi-dimensional multi-stage structure. Instead of increasing capacity in one dimension (single CAM size), the solution adds another dimension (multiple stages), allowing the system to achieve the same classification completeness with smaller, more affordable individual components.
3Adaptability or versatility
If a single large CAM is used for all classification criteria, then all packet fields can be classified, but device complexity and resource requirements increase
Solution Approach 1:
The patent segments the classification functionality across multiple CAM stages, where each stage is responsible for examining specific packet fields. This functional segmentation simplifies the structure of each individual CAM device while collectively achieving comprehensive classification coverage through the series of stages.
Data Source
AI summary
A versatile and efficient technique for classifying packets in an intermediate node. According to the technique, criteria and rules associated with the packet are applied to one or more classification stages containing content-addressable memories (CAMs). Each stage examines specific criteria associated with the packet, e.g., a packet field, and generates a rule and additional criteria. The additional rule and criteria are provided to the next classification stage. This process continues until a final rule is provided to a final classification stage. At the final classification stage, the final rule is used to generate an identifier, e.g., queue identifier (ID), associated with the classified packet.