Lazy Byte Batching for QoS Throughput Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Quality of Service (QoS) processing in data communication networks causes overhead delays that scale with increasing throughput, becoming a bottleneck during high-demand periods and limiting maximum packet per second communication rates.
Innovation Solution
Implementing 'lazy' QoS processing by applying it only to a subset of packets or on a byte size basis, allowing packets to bypass QoS processing while maintaining similar QoS settings, thereby reducing overhead and minimizing accuracy decline.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If QoS processing is applied to every packet, then QoS accuracy is improved, but overhead delay increases and throughput decreases
Solution Approach 1:
The patent applies QoS processing to only a subset of packets (e.g., every Nth packet or based on byte batching) rather than every packet. This partial application of processing maintains sufficient QoS accuracy for monitoring and control while dramatically reducing the overhead delay that would occur with full packet inspection, thereby resolving the contradiction between QoS accuracy and throughput.
Solution Approach 2:
The patent segments the packet processing stream into batches or groups, applying QoS processing at interval boundaries rather than continuously to each individual packet. This segmentation approach maintains QoS measurement accuracy at the batch level while reducing per-packet processing overhead, thus improving overall throughput without completely sacrificing QoS accuracy.
2Measurement precision
If QoS processing is applied to every packet, then QoS accuracy is improved, but overhead delay increases
Solution Approach 1:
By applying QoS processing to only a partial subset of packets rather than every packet, the system maintains adequate QoS measurement accuracy while significantly reducing the time spent on processing operations. This partial action approach directly addresses the contradiction by accepting slightly reduced per-packet accuracy in exchange for much lower cumulative overhead delay.
Solution Approach 2:
The patent implements periodic QoS processing where inspection occurs at regular intervals (e.g., every N packets or at fixed time intervals) rather than continuously for every packet. This periodic approach maintains QoS accuracy at the interval level while minimizing the time lost to processing, as the processing burden is distributed over time rather than applied uniformly to every packet.
3Measurement precision
If QoS processing is applied to every packet, then QoS accuracy is improved, but device performance becomes a bottleneck
Solution Approach 1:
The patent reduces device processing complexity by applying QoS processing to only a subset of packets rather than every packet passing through the device. This partial processing approach maintains sufficient QoS accuracy for network management purposes while dramatically reducing the computational burden and eliminating the processing bottleneck that would occur with full packet inspection.
Solution Approach 2:
The patent extracts QoS processing from the fast packet forwarding path, applying it only to selected packets (e.g., control packets or periodic samples) rather than all packets. This extraction separates the QoS measurement function from the high-speed data plane, reducing device complexity and eliminating the processing bottleneck while maintaining adequate QoS accuracy through strategic sampling of packets.
Data Source
AI summary
Described embodiments improve the performance of a computer network via selectively forwarding packets to bypass quality of service (QoS) processing, avoiding processing delays during critical periods of high demand, increasing throughput and efficiency may be increased by sacrificing a small amount of QoS accuracy. QoS processing may be applied to a subset of packets of a flow or connection, referred to herein as “lazy” processing or lazy byte batching. Packets that bypass QoS processing may be immediately forwarded with the same QoS settings as packets of the flow for which QoS processing is applied, resulting in tremendous overhead savings with only minimal decline in accuracy.