Buffer Shortage Management via Flow Redirection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional buffer shortage management systems in information handling systems often result in network congestion and disruptions due to high data traffic, as they rely on mechanisms like Priority Flow Control and Explicit Congestion Notification, which are inefficient and require hardware support, leading to delayed congestion remediation.
Innovation Solution
An information handling system with a buffer shortage management engine that identifies data flows with high relative buffer pool utilization and redirects them away from congested ports, using a buffer shortage notification mechanism to alleviate network congestion by rerouting data flows through connected networking devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If Priority Flow Control is used to prioritize particular data flows, then data flow prioritization is improved, but network-wide disruptions still occur and device complexity increases
Solution Approach 1:
The patent changes the parameter of congestion management from flow-based prioritization to buffer-pool-based load shedding. Instead of prioritizing individual data flows, the system monitors buffer pool utilization thresholds and applies uniform load shedding across all flows when thresholds are exceeded, simplifying the control mechanism while maintaining network reliability.
Solution Approach 2:
The patent segments the buffer memory into multiple buffer pools, each associated with specific egress ports or port channels. This segmentation allows independent monitoring and management of buffer utilization for different network segments, enabling targeted load shedding without affecting entire network-wide operations, thus reducing overall system complexity.
2Measurement precision
If Explicit Congestion Notification is used to identify congestion, then congestion identification is improved, but remediation delay increases due to destination-to-source notification requirement
Solution Approach 1:
The patent implements preliminary action by proactively shedding load at the ingress switch when buffer pool utilization thresholds are approached, before congestion fully develops. This prevents the need for reactive congestion notification and remediation cycles, eliminating the time delay associated with ECN's destination-to-source notification requirement.
Solution Approach 2:
The patent inverts the traditional congestion management approach by having the ingress switch (rather than the egress switch) take primary action in managing buffer congestion. Instead of allowing congestion to develop and then notifying the source, the ingress switch proactively prevents congestion by shedding load before buffers are fully utilized, reversing the conventional flow of congestion management control.
3Quantity of substance
If buffer pool utilization reaches high levels, then data storage capacity is improved, but network congestion and disruptions increase
Solution Approach 1:
The patent implements feedback control by continuously monitoring buffer pool utilization levels and dynamically adjusting load shedding actions based on real-time buffer status. When buffer utilization approaches threshold levels, the system automatically sheds load to prevent congestion, creating a closed-loop control system that maintains buffer storage capacity while preventing harmful congestion effects.
Solution Approach 2:
The patent applies beforehand cushioning by establishing buffer pools with reserved capacity and setting utilization thresholds that trigger proactive load shedding. This creates a cushion of unused buffer capacity that prevents congestion before it occurs, allowing the system to maintain high storage capacity utilization while having pre-planned protection mechanisms in place to prevent harmful congestion effects.
Data Source
AI summary
A buffer shortage management system includes a first networking device with ports included in a buffer pool. A second networking device forwards a first data flow to the first networking device through LAG port(s) in the buffer pool. The first networking device determines that a total buffer pool utilization has reached a threshold that effects a first data flow received through a non-LAG port on the first networking device. The first networking device then identifies that the first data flow and third data flow(s) are received through the LAG port(s), determines that the first data flow has a higher utilization of the buffer pool than the third data flow(s) and, in response, transmits a first buffer shortage notification to the second networking device that causes the second networking device to modify its forwarding parameters to redirect the first data flow from the first networking device to a third networking device.