Transaction Boundary Detection for Network QoS Latency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing quality of service (QoS) systems face challenges in identifying and prioritizing latency-sensitive network traffic, leading to increased latency and retransmission timeouts, which negatively impact interactive and streaming traffic.
Innovation Solution
The system employs transaction boundary detection to prioritize packets based on transaction size, retransmitting additional packets to ensure timely notification of dropped packets and reducing retransmission delays by retransmitting dropped packets multiple times.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If QoS systems prioritize interactive traffic to reduce latency, then latency-sensitive traffic performance improves, but bandwidth allocation cannot guarantee latency and packet identification becomes difficult
Solution Approach 1:
The system performs preliminary actions by detecting transaction boundaries before packets are transmitted. It identifies the start and end of transactions in advance, allowing the QoS system to prioritize packets belonging to the same transaction together. This preliminary detection enables the system to group and handle latency-sensitive packets as a unit, improving latency performance while solving the identification problem through boundary markers.
Solution Approach 2:
Transaction boundary markers serve as intermediaries between the application layer and the QoS system. These markers are inserted into the data stream to indicate transaction boundaries, acting as a mediator that enables the QoS system to identify and prioritize latency-sensitive traffic without requiring complex analysis of application protocols or packet contents.
2Reliability
If standard retransmission timeout (RTO) is used to handle dropped packets, then packet loss is corrected, but retransmission delays are excessive (e.g., TCP default RTO of one second)
Solution Approach 1:
The system performs preliminary retransmission of packets immediately after detecting a transaction boundary, before the standard RTO period expires. By proactively retransmitting packets at the transaction boundary level rather than waiting for protocol-level timeouts, the system reduces retransmission delays significantly while maintaining reliable packet delivery through the transaction boundary detection mechanism.
3Reliability
If retransmitted packets are sent once after loss detection, then packet delivery is attempted, but additional delays occur when retransmitted packets are also dropped
Solution Approach 1:
The system applies beforehand cushioning by proactively retransmitting packets at transaction boundaries before losses are detected. By sending cushioning retransmissions in advance at the transaction level, the system creates a buffer against potential packet losses, reducing the impact of dropped packets and minimizing cumulative retransmission delays compared to reactive protocol-level retransmissions.
Data Source
AI summary
Systems and methods for utilizing transaction boundary detection methods in queuing and retransmission decisions relating to network traffic are described. By detecting transaction boundaries and sizes, a client, server, or intermediary device may prioritize based on transaction sizes in queuing decisions, giving precedence to smaller transactions which may represent interactive and/or latency-sensitive traffic. Further, after detecting a transaction boundary, a device may retransmit one or more additional packets prompting acknowledgements, in order to ensure timely notification if the last packet of the transaction has been dropped. Systems and methods for potentially improving network latency, including retransmitting a dropped packet twice or more in order to avoid incurring additional delays due to a retransmitted packet being lost are also described.