Network Device Packet Processing Control Path Optimization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Network devices face inefficiencies in processing packets due to varying processing requirements based on packet origin, leading to bottlenecks in the control path, especially when handling packets of different sizes and origins from external networks and within data centers.

Innovation Solution

The network device implements different sets of processing operations for packets received through various ports, extracting reduced sets of bits from packet headers and combining them into a single data unit for faster processing, thereby reducing the load on the control path and enhancing throughput.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If different sets of processing operations are performed on packets from different ports, then processing accuracy and reliability are improved, but device complexity increases

Engineering Contradiction:
Improvepacket processing accuracyVSAvoidprocessing operation complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments packet processing into different operation sets based on packet origin (external network vs. data center). The processing system is divided into multiple port groups, each associated with a specific set of processing operations. This segmentation allows the device to apply appropriate processing complexity selectively, improving reliability for critical packets while maintaining simplicity for less critical traffic.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent implements dynamic processing operation selection based on real-time packet characteristics and port identification. The control path dynamically determines which set of processing operations to apply by examining packet origin information, allowing the system to adapt processing complexity to actual needs rather than applying a fixed complex processing regime to all packets.

Inventive Principle:
Principle #15Dynamics

2Reliability

If full processing operations are performed on all packets, then processing completeness is improved, but control path throughput decreases

Engineering Contradiction:
Improveprocessing completenessVSAvoidcontrol path packet rate
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent applies partial processing operations to packets based on their origin. For data center packets, a reduced set of processing operations is performed (partial action), while external network packets receive the full set of processing operations. This approach ensures processing completeness for critical packets while maintaining high control path throughput by avoiding unnecessary processing on less critical traffic.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The patent implements local quality by assigning different processing operation sets to different port groups. Each port group is configured with processing operations appropriate to the typical traffic characteristics of packets arriving from that port. This local optimization ensures that processing completeness is maintained where needed while improving overall control path throughput through selective processing.

Inventive Principle:
Principle #3Local quality

3Productivity

If reduced sets of bits are extracted and combined into single data units, then processing speed is improved, but information loss risk increases

Engineering Contradiction:
Improvepacket processing speedVSAvoidpacket header information
Core Design Contradiction:
ProductivityVSLoss of information

Solution Approach 1:

The patent extracts only the essential bits from packet headers that are needed for control path processing decisions. By identifying and extracting only the critical header fields required for routing and processing decisions, the system reduces the amount of data that needs to be processed while maintaining all necessary information for accurate packet handling. This extraction approach improves processing speed without causing information loss.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent performs preliminary extraction and combination of packet header bits before control path processing. By pre-processing the packet headers to extract and combine essential information into compact data units in advance, the system reduces the processing burden on the control path while ensuring that all necessary information is preserved and organized for efficient processing.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3085036B1Increasing packet process rate in a network device
Publication Date: 2020.08.19 MARVELL WORLD TRADE LTD
  • EP3085036B1 patent drawingFigure 1
  • EP3085036B1 patent drawingFigure 2
  • EP3085036B1 patent drawingFigure 3

AI summary

In a method for processing packets in a network device, a first packet is received at a first port of the network device. A first set of bits, corresponding to a first set of bit locations in a header of the first packet, is extracted from the header of the first packet. A first set of processing operations is performed to process the first packet using the first set of bits. A second packet is received at a second port of the network device. A second set of bits, corresponding to a second set of bit locations in a header of the second packet, is extracted from the header of the second packet. A second set of processing operations is performed to process the second packet using the second set of bits.