Packet Flow Identification Using Reduced Header Decoding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current network packet analysis methods incur a high per-packet cost due to the need to blindly parse every network packet, which is inefficient, especially in dense processor configurations and with the expected exponential increases in network traffic volumes accompanying 5G technologies.
Innovation Solution
The method involves determining packet-to-flow membership using a reduced number of header fields and a defined time window, focusing on matching tunnel identifiers and source port identifiers to assign packets to flows without the need for extensive decapsulation of protocol layers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional packet analysis methods blindly parse every network packet to assign packets to flows, then packet flow identification accuracy is maintained, but processing time and computational resources increase significantly
Solution Approach 1:
The patent applies preliminary action by pre-defining flow templates with expected header field patterns before packet analysis begins. When a packet arrives, the system checks if it matches an existing flow template pattern, allowing rapid assignment without complete parsing. This preliminary pattern-matching approach maintains identification accuracy while dramatically reducing processing time for packets that conform to expected flow patterns.
Solution Approach 2:
The patent implements partial action by performing only the necessary subset of parsing operations needed for flow identification rather than completely parsing all packet headers. The system extracts only the specific header fields required for flow matching (such as source/destination IP addresses and ports) while skipping unnecessary decapsulation steps, thereby maintaining sufficient identification accuracy while reducing computational overhead.
2Loss of information
If traditional methods perform extensive decapsulation of protocol layers to characterize packets, then complete packet information is obtained, but the number of operations required increases
Solution Approach 1:
The patent applies the extraction principle by selectively removing and analyzing only the specific header fields necessary for flow identification from the packet structure. Instead of performing extensive decapsulation of all protocol layers, the system extracts only the relevant information (source IP, destination IP, source port, destination port, protocol type) needed to determine flow membership, thereby maintaining information completeness for flow purposes while reducing operational complexity.
Solution Approach 2:
The patent implements segmentation by dividing the packet analysis process into distinct stages: first checking packet headers against flow templates, then performing detailed analysis only for packets that require it. This segmented approach allows the system to process the majority of packets through a lightweight path that maintains sufficient information for flow identification without the overhead of complete decapsulation, thereby improving throughput while preserving necessary information.
3Quantity of substance
If the system processes increasing network traffic volumes with traditional parsing methods, then all packets can be analyzed in detail, but processor load and operational complexity increase
Solution Approach 1:
The patent applies universality by creating flow templates that can match multiple packets with similar characteristics through a single template definition. Instead of processing each packet independently through complete parsing, the system uses universal flow patterns that can rapidly categorize large volumes of packets belonging to the same flow, thereby handling increased traffic volumes without proportionally increasing processor complexity or operational overhead.
Data Source
AI summary
In one example, a processing system including at least one processor may obtain a first packet, determine a first tunnel identifier from a tunnel identifier field and a first source port identifier from a source port identifier field of the header of the first packet, and assign the first packet to a first flow. The processing system may further obtain a second packet, extract a first value from a tunnel identifier field and a second value from a source port identifier field of a header of the second packet, determine that the first value matches the first tunnel identifier and that the second value matches the first source port identifier, and assign the second packet to the first flow in response to the determining that the first value matches the first tunnel identifier and that the second value matches the first source port identifier.