Multi-field Packet Classifier Using Subkey Tables
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current content-addressable memories (CAMs) and ternary content-addressable memories (TCAMs) are costly in terms of chip area, necessitating an improved system and method for classifying data packets based on packet header field values.
Innovation Solution
A system and method involving multiple subkey tables and a decision table, where each subkey table searches for a respective packet header field value, generating subkeys that are combined to form a decision key, which is then used to determine how to process the packet, utilizing a two-stage process for efficient classification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If CAMs or TCAMs are used for packet classification, then classification speed and accuracy are improved, but chip area and cost increase
Solution Approach 1:
The patent divides the packet classification task into multiple independent subkey tables, each handling a specific field or combination of fields. Instead of using a single large CAM/TCAM structure, the system segments the classification function across multiple smaller tables that can be processed in parallel, reducing the area required for each individual table while maintaining overall classification performance.
Solution Approach 2:
The patent introduces a hierarchical dimension to packet classification by using multiple levels of tables (subkey tables at one level, decision tables at another). This dimensional approach allows the system to classify packets through a multi-stage process where each table handles a specific aspect of classification, reducing the complexity and area requirement of any single table while improving overall classification capability.
2Area of stationary object
If multiple subkey tables are used for packet classification, then chip area is reduced, but device complexity increases
Solution Approach 1:
The patent designs the subkey tables and decision tables to serve multiple functions within the packet classification system. Each table structure is optimized to handle both exact matches and range queries, and the same table architecture can be reused for different packet fields. This multi-functionality reduces the need for specialized hardware for each classification task, thereby reducing overall device complexity despite having multiple tables.
Solution Approach 2:
The patent uses identical or similar table structures (subkey tables) that can be instantiated multiple times with different data. Instead of creating unique complex structures for each classification function, the system copies and reuses the same efficient table architecture, filling it with field-specific data. This approach simplifies the overall system design while maintaining the benefits of multiple tables for area reduction.
Data Source
AI summary
A system and method for classifying packets according to packet header field values. Each of a set of subkey tables is searched for a respective packet header field value; each such search results in a value for a subkey. The subkeys are combined to form a decision key. A decision table is then searched for the decision key. The search of the decision table results in an action code and a reason code, one or both of which may be used to determine how to further process the packet.