Traffic Processing Unit State Migration via Packet Class Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for stateful traffic processing in communication networks face complexity and cost issues when migrating state information from one traffic processing unit to another, especially when the processing unit is inactivated.
Innovation Solution
A method and system where traffic processing units assign packet classes based on activity indicators to determine if state information is locally available or needs to be fetched from a central storage, allowing for efficient retrieval and processing of stateful packets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If state information is stored locally at each traffic processing unit, then processing speed is improved, but device complexity increases when migration is required
Solution Approach 1:
The patent segments state information into packet class-specific groups, with each traffic processing unit maintaining state information only for its assigned packet classes. This segmentation allows independent management and migration of state information by packet class, reducing overall complexity when migration is required.
Solution Approach 2:
The patent introduces a distribution device as an intermediary that coordinates state information migration between traffic processing units. The distribution device receives migration requests, identifies the appropriate target unit for a packet class, and facilitates the transfer, thereby simplifying the migration process for individual processing units.
2Productivity
If traffic is distributed across multiple processing units, then processing capacity and scalability are improved, but complexity of state information management increases
Solution Approach 1:
The patent implements local quality by having each traffic processing unit maintain state information specifically for its assigned packet classes rather than all packet classes. This localized storage approach enables distributed processing capacity while reducing the state information management burden at each unit.
Solution Approach 2:
The patent applies preliminary action by pre-assigning packet classes to specific traffic processing units and pre-configuring the distribution device with this mapping information. This preliminary organization simplifies subsequent state information management and migration operations across the distributed system.
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
A method and a traffic processing unit (200) for handling traffic in a communication network when the traffic is distributed across a set of traffic processing units. When receiving a packet of a traffic flow distributed to said traffic processing unit, the traffic processing unit (200) assigns a packet class to the received packet, which class can be active or inactive in the traffic processing unit. The traffic processing unit obtains state information of the assigned packet class. If the packet class is detected as active the state information is retrieved from a local storage (200C) in the traffic processing unit, and if the packet class is detected as inactive the state information is fetched from a central storage (204). The traffic processing unit then performs stateful packet processing of the received packet based on the obtained state information.