Service Latency Monitoring via Two-Way Active Measurement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods, such as two-way active measurement protocols, fail to distinguish between latency caused by network devices and latency associated with services performed on network traffic, making it difficult for users to determine service-specific latencies and optimize network design.
Innovation Solution
A system that establishes a secure communication session between a client device and a monitoring device to record and transmit timestamps of network traffic, allowing the client device to calculate service latency by subtracting send time from receive time, thereby isolating service latency from network device latency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If two-way active measurement protocols are used to measure latency, then round-trip latency can be measured, but it is impossible to distinguish between latency caused by network devices and latency associated with services
Solution Approach 1:
The patent segments the latency measurement process into distinct components by introducing separate timestamp records for different events (packet injection, service completion, packet receipt). This segmentation allows the client to calculate specific service latency by subtracting the service start timestamp from the service completion timestamp, thereby isolating service latency from network device latency.
Solution Approach 2:
The patent introduces a service provider device as an intermediary that inserts timestamp records into network packets. This intermediary enables the client device to obtain precise timing information about service processing by acting as a mediator between the client and the service, allowing accurate service latency measurement without requiring modifications to the service itself.
2Productivity
If traditional latency measurement methods are used, then overall network latency can be obtained, but service-specific latency cannot be determined for optimization purposes
Solution Approach 1:
The patent implements a feedback mechanism where the service provider device sends timestamp information back to the client device through network packets. This feedback loop enables the client to calculate and determine service-specific latency, providing the necessary data for network optimization and service evaluation.
Solution Approach 2:
The patent applies preliminary action by having the service provider device insert timestamp records at the beginning and end of service processing before the packet reaches the client. This preliminary timing action allows the client to accurately calculate service latency without requiring complex measurements after the fact.
Data Source
AI summary
A device may establish a communication session, with a client device, for monitoring a latency of a service. The device may receive, from the client device, a request for a monitored service list. The monitored service list may identify one or more services for which service latency monitoring is supported. The device may provide, to the client device, the monitored service list. The device may receive, from the client device, a service latency monitoring session request that may identify the service to be monitored. The device may establish, with the client device, the service latency monitoring session based on the service latency monitoring session request. The device may cause the service to be performed. The device may generate information for determining the latency of the service. The device may transmit, to the client device and via the service latency monitoring session, the information for determining the latency of the service.