Configurable Data Packet Classification Using Dynamic Keys
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional data packet classification methods are inflexible and nonconfigurable, relying solely on implicit data packet parameters like input port number for quality of service allocation, and do not allow for the selection of explicit data packet parameters for classification.
Innovation Solution
A method and network processor that allow the selection of a subgroup of data packet parameters to form a classification key, enabling classification of data packet units into classes using a configurable classification algorithm, with further parameters allocated based on the class, including explicit and implicit parameters like transmission protocol, source and destination addresses, and arrival time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional classification methods are used, then the classification process is simple, but the classification is inflexible and nonconfigurable
Solution Approach 1:
The patent implements dynamic classification by allowing the classification key to be configured at runtime through a control interface. The classification key can be dynamically selected from multiple data packet parameters (source address, destination address, protocol type, etc.), enabling the system to adapt to different classification requirements without hardware reconfiguration. This resolves the contradiction by making the classification system flexible while maintaining a relatively simple underlying structure.
Solution Approach 2:
The patent changes the parameters used for classification by allowing selection from multiple data packet parameters (source address, destination address, protocol type, input port number, etc.) to form the classification key. The classification algorithm and key configuration can be modified through software control, enabling flexible adaptation to different network requirements without changing the fundamental system architecture, thus achieving flexibility without excessive complexity.
2Measurement precision
If only implicit data packet parameters are used for classification, then the classification process is fast, but the classification accuracy and granularity are limited
Solution Approach 1:
The patent segments the classification process into multiple stages: extracting relevant parameters from the data packet (source address, destination address, protocol type, etc.), forming a classification key from selected parameters, applying classification algorithms (direct mapping, hashing, CAM lookup), and allocating quality of service parameters. This segmentation allows the system to use multiple parameters for precise classification while optimizing each stage to minimize processing time.
Solution Approach 2:
The patent performs preliminary actions by pre-configuring classification rules and algorithms in memory before actual packet classification occurs. The classification key format and matching rules are prepared in advance, allowing the network processor to quickly classify packets by simply comparing packet parameters against pre-loaded rules, thus achieving high precision without significant time loss.
3Adaptability or versatility
If multiple data packet parameters are selected for classification, then the classification granularity is improved, but the processing complexity increases
Solution Approach 1:
The patent creates a universal classification framework that can handle multiple data packet parameters (source address, destination address, protocol type, input port number, etc.) through a unified classification key structure. The same classification hardware and algorithms can process different parameter combinations by simply changing the key configuration, achieving high configurability without proportionally increasing processing complexity.
Solution Approach 2:
The patent introduces a control interface and classification key formation unit as intermediaries between the packet data and classification algorithms. These intermediaries manage the complexity of handling multiple parameters by automatically extracting, formatting, and preparing the classification key from selected packet parameters, shielding the core classification logic from parameter complexity while maintaining high configurability.
Data Source
AI summary
In a method for classifying data packet units, each comprising a group of data packet parameters which comprises a plurality of data packet parameters, a subgroup of data packet parameters for configuring a classification key is selected, the data packet units are divided into data packet classes on the basis of the classification key and a selected classification algorithm, and the data packet units are allocated to further data packet parameters which correspond to the respective data packet class.