SDN Packet Flow Monitoring via Data-Plane Telemetry
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In Software-Defined Networking (SDN) environments, conventional network troubleshooting and debugging tools like ping and traceroute are inadequate for identifying network issues in complex topologies, as they rely on ICMP messages that may not follow application traffic paths and do not provide comprehensive network state information.
Innovation Solution
Implementing a data-plane telemetry process that adds metadata to packets as they traverse the network, allowing for improved packet flow monitoring and troubleshooting by collecting network state information from intermediate devices, reducing reliance on centralized control-plane approaches.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional troubleshooting tools like ping and traceroute are used, then simplicity of operation is maintained, but measurement precision and reliability of network state information are insufficient
Solution Approach 1:
The patent introduces an intermediary data-plane telemetry system that acts as a mediator between the network infrastructure and troubleshooting tools. This telemetry system collects accurate network state information from intermediate devices and forwards it to troubleshooting applications, thereby improving measurement precision without requiring complex modifications to existing troubleshooting tools or operations
Solution Approach 2:
The patent replaces the traditional control-plane-based troubleshooting mechanism with a data-plane telemetry mechanism. Instead of relying on control-plane messages that may not reflect actual data traffic paths, the system uses data-plane packet telemetry to capture real network state information, substituting one mechanical system for another more effective one
2Productivity
If control-plane approaches are used for packet flow monitoring, then centralized control is maintained, but loss of time occurs due to stale data and implementation overhead increases
Solution Approach 1:
The patent inverts the traditional control-plane approach by implementing telemetry in the data-plane. Instead of having the control-plane query network state information, the data-plane actively pushes telemetry data about packet flows and network state to the control-plane, reversing the information flow direction and eliminating delays associated with periodic control-plane polling
Solution Approach 2:
The patent establishes continuous telemetry collection in the data-plane as packets traverse the network. This continuous action ensures that network state information is constantly updated and pushed to troubleshooting systems, eliminating the time losses associated with periodic sampling or stale data from control-plane approaches
3Loss of information
If ICMP messages are used for troubleshooting, then ease of operation is maintained, but loss of information occurs as ICMP messages do not follow application traffic paths
Solution Approach 1:
The patent segments the troubleshooting function into two independent parts: the simple user-facing troubleshooting tools that users operate, and the backend data-plane telemetry system that collects actual network state information. This segmentation allows users to continue using simple tools while the complex telemetry infrastructure operates transparently in the background, preventing information loss without increasing user operational complexity
Data Source
AI summary
Example methods are provided a first host to perform packet flow monitoring in a software-defined networking (SDN) environment. One example may comprise the first host receiving a request to monitor a packet flow and triggering a telemetry process based on a predetermined event associated with the packet flow. The method may also comprise: in response to the triggered telemetry process and detecting an egress packet associated with the packet flow, generating an encapsulated packet by encapsulating the egress packet with an outer header; configuring a telemetry instruction in the outer header; and sending the encapsulated packet with the telemetry instruction to the second host via one or more intermediate network devices. The telemetry instruction may be configured to cause the one or more intermediate network devices to add, to the encapsulated packet, metadata associated with a network state experienced by the encapsulated packet.