Ingress Rate Limiting via Feedback Signals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Receiving devices face challenges in managing high data traffic volumes from network-attached devices, as they do not directly control the transmission sources, leading to potential service cost increases and performance degradation when traffic exceeds predetermined thresholds.
Innovation Solution
Implementing a rate limiting network controller at the ingress port that monitors traffic and signals source devices to reduce data transmission rates through unicast congestion messages, Explicit Congestion Notifications, or packet dropping when thresholds are exceeded, allowing for threshold enforcement at both port and virtual machine levels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the receiving device allows high data traffic volume from network sources, then the data transmission capacity is improved, but the service costs increase and performance of high priority traffic flows decreases
Solution Approach 1:
The receiving device monitors incoming traffic rates and sends feedback signals (congestion notifications) to source devices when traffic exceeds predetermined thresholds. This feedback mechanism enables source devices to adjust their transmission rates dynamically, resolving the contradiction by maintaining high overall capacity while preventing performance degradation through active traffic rate control.
Solution Approach 2:
Source devices are empowered to self-regulate their transmission rates based on congestion notifications received from the receiving device. Instead of the receiving device actively controlling each source, the sources autonomously adjust their behavior in response to signals, reducing the complexity of traffic management while maintaining performance guarantees.
2Ease of operation
If the receiving device monitors and controls traffic from multiple source devices, then the traffic management capability is improved, but the device complexity increases
Solution Approach 1:
Source devices autonomously monitor their own transmission rates and self-adjust based on congestion notifications received from the receiving device. This shifts the active control burden from the receiving device to the source devices, simplifying the receiving device's role to monitoring and signaling only, thereby reducing device complexity while maintaining effective traffic management.
Solution Approach 2:
The receiving device implements a simplified feedback-based control mechanism where it only needs to monitor traffic rates and send congestion notifications when thresholds are exceeded. This feedback approach avoids complex active control of multiple sources, achieving effective traffic management through simple monitoring and signaling.
3Productivity
If the receiving device sends congestion notifications to source devices, then the traffic rate control is improved, but the network communication overhead increases
Solution Approach 1:
The receiving device sends congestion notifications only when traffic rates exceed predetermined thresholds, rather than continuously monitoring and signaling. This partial action approach provides effective traffic rate control only when needed, reducing network communication overhead while maintaining control capability during congestion conditions.
Data Source
AI summary
A network device monitors the traffic of individual flows through one of its ingress ports and, if the traffic volume exceeds a predetermined threshold, signals for a reduction in data traffic volume transmitted to that ingress port from one or more source devices. Example signals may include without limitation a unicast congestion message sent to the source of a flow, an Explicit Congestion Notification to one or more source devices, and the dropping of packets by the receiving device. In response to such signals, one or more of the source devices decrease the transmission rate of data traffic to the receiving device.