High-Precision Packet Train Generation in OpenFlow SDN
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current packet processing platforms in high-speed communications networks face challenges in generating high-precision packet trains due to the low resolution of operating system clocks and the inability of general-purpose control processing elements or OAM processors to produce precise inter-packet gaps, leading to suboptimal performance in bandwidth estimation and network monitoring.
Innovation Solution
The method involves configuring an initial packet generation flow and a main packet generation flow using OpenFlow standard constructs, with a loopback port configured for traffic shaping to establish a predetermined inter-packet gap, and incrementing source port parameters to ensure precise packet train generation, allowing for high-precision packet train generation in OpenFlow SDN networks without requiring specialized hardware.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If general-purpose control processing elements or OAM processors are used for packet generation, then device complexity is reduced and ease of manufacture is improved, but measurement precision and inter-packet gap accuracy deteriorate
Solution Approach 1:
The system divides packet generation into two distinct functional segments: a control plane processor that manages flow configuration and a data plane processor that executes precise packet generation. This segmentation allows each component to be optimized for its specific function, with the data plane handling time-critical operations with microsecond precision while the control plane manages higher-level configuration tasks.
Solution Approach 2:
A flow configuration message acts as an intermediary carrier that transmits inter-packet gap parameters from the control plane to the data plane. This intermediary mechanism enables precise timing parameters to be communicated without requiring the control processor to directly generate each packet, thus maintaining measurement precision while using general-purpose processors.
2Measurement precision
If specialized circuits are developed for generating high-speed, high-precision packet trains, then measurement precision and speed are improved, but device complexity and manufacturing cost increase
Solution Approach 1:
The data plane processor is designed to perform multiple functions including packet generation, traffic shaping, and flow management. By making the data plane multi-functional, the system eliminates the need for dedicated specialized circuits while maintaining high-precision packet train generation capabilities through software-configurable parameters.
Solution Approach 2:
The system uses software-configurable parameters in flow configuration messages to dynamically adjust inter-packet gap values and packet generation rates. This parameter-based control allows the same hardware to adapt to different measurement requirements without requiring physical reconfiguration or specialized circuits for each scenario.
3Productivity
If higher port bandwidths are implemented, then network throughput and productivity are improved, but the difficulty of generating precise packet trains increases due to timing resolution requirements
Solution Approach 1:
The system pre-configures flow rules with inter-packet gap parameters before packet generation begins. By calculating and setting the inter-packet gap in advance based on desired bandwidth estimation parameters, the system avoids complex real-time timing calculations at high speeds, making precise packet train generation feasible even at higher bandwidths.
Solution Approach 2:
The patent replaces hardware-based timing mechanisms with software-based flow configuration messages that carry timing parameters. This substitution allows flexible, programmable control of packet timing without being constrained by fixed hardware timing resolutions, enabling precise measurement even as port bandwidths increase.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method for generating a high-precision packet train includes configuring an initial packet generation flow of duration T in a network node and sending a packet to a loopback port to initiate the initial packet generation flow in the network node, where the loopback port loops packets back to the network node or recirculates packets within the network node, and where the loopback port is configured for traffic shaping that establishes a pre-determined inter-packet gap for packets output by the loopback port. The method further includes configuring a main packet generation flow having a duration t1 that commences on expiration of the duration T. Looped back packets in the network node are sent to the loopback port for the entirety of durations T and t1, while one copy of each looped back packet in the network node is sent to a network port during the duration t1.