Network Telemetry Metadata Skipping for Lower Packet Overhead
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network telemetry standards like INT and IOAM collect redundant metadata, leading to increased packet size, network congestion, and processing delays, without mechanisms to identify and eliminate redundant telemetry data.
Innovation Solution
Implementing an optimization field in network packets to signal redundant telemetry elements for skipping, using unused bits in INT or IOAM metadata, and maintaining a flow data comparison to omit redundant metadata, with an instructional mask indicating omitted elements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If telemetry node level metadata is collected from all network nodes along a path, then measurement completeness is improved, but packet size increases and network congestion worsens
Solution Approach 1:
The patent extracts only the necessary telemetry metadata elements from network nodes, excluding redundant information. By selectively taking out only the essential measurement data needed for performance tracking, the system maintains measurement completeness while reducing the quantity of data transmitted in each packet.
Solution Approach 2:
The patent applies partial action by collecting telemetry data from a subset of critical network nodes rather than all nodes along the path. This selective approach provides sufficient measurement information for effective network monitoring while minimizing the overhead and congestion caused by comprehensive data collection from every node.
2Measurement precision
If telemetry metadata is collected from all network nodes, then measurement completeness is improved, but network processing time increases
Solution Approach 1:
The patent extracts and transmits only the essential telemetry metadata elements needed for network performance monitoring, excluding redundant information. This extraction approach maintains measurement completeness by capturing critical data points while significantly reducing the processing time required to handle and analyze telemetry information.
3Measurement precision
If redundant telemetry elements are included in packets, then measurement completeness is improved, but network load increases
Solution Approach 1:
The patent extracts and includes only the necessary telemetry metadata elements in network packets, deliberately excluding redundant information. This selective extraction maintains measurement completeness by capturing essential performance data while reducing network load by eliminating duplicate and unnecessary telemetry elements.
4Measurement precision
If comprehensive telemetry data is collected, then troubleshooting capability is improved, but packet transmission speed decreases
Solution Approach 1:
The patent extracts and transmits only the critical telemetry metadata elements required for effective network troubleshooting. By taking out only the essential diagnostic information needed to identify and resolve network issues, the system maintains comprehensive troubleshooting capability while improving packet transmission speed through reduced data volume.
Data Source
AI summary
Methods are provided to decrease amount of the telemetry data traversed in a network. The methods involve obtaining, by a first network device, a packet of a traffic flow. The packet has a header and a payload. The methods further involve adding, by the first network device, to the header of the packet, telemetry node level metadata while skipping at least one element of the telemetry node level metadata that is redundant to telemetry node level information of the traffic flow and providing the packet to a second network device in a path of a network.