Adaptive Queue Priority Control for Network Node Overload
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Network switches, routers, and gateways face instantaneous overload conditions leading to frame drops due to unbalanced utilization of internal queues, particularly affecting high-priority packets and degrading Quality of Service (QoS).
Innovation Solution
Implementing a controller that dynamically adjusts Internal Priority Values (IPV) based on queue utilization thresholds, re-orienting frames from overloaded high-priority queues to underutilized low-priority queues to optimize memory usage and prevent drops.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If fixed depth queues and queue management algorithms per queue are implemented, then queue management is simplified, but frame drops occur during network overload due to unbalanced utilization
Solution Approach 1:
The patent implements dynamic queue depth allocation where the controller continuously monitors queue utilization and adjusts the depth of individual queues in real-time. During normal operation, queues maintain fixed depths for simple management. During overload conditions, the controller dynamically increases the depth of overloaded queues and decreases the depth of underutilized queues, allowing the system to adapt to changing traffic patterns and prevent frame drops while maintaining operational simplicity through automated control.
Solution Approach 2:
The system employs feedback mechanisms where the controller monitors the utilization state of each queue and uses this information to adjust queue depths. The controller receives feedback about queue fullness and traffic patterns, then modifies queue allocations accordingly. This closed-loop feedback system enables the network node to respond to overload conditions by redistributing buffer resources from underutilized queues to overloaded queues, preventing frame drops while maintaining simple fixed-depth queue structures during normal operation.
2Ease of operation
If queues of low activity ports are maintained with fixed depth, then queue management is easier, but memory is wasted when other ports are overloaded
Solution Approach 1:
The patent transforms fixed queue depth configuration into a dynamic system where queue depths are adjusted based on real-time traffic conditions. The controller monitors which queues are overloaded and which have excess capacity, then dynamically reallocates memory resources by increasing the depth of overloaded queues and decreasing the depth of underutilized queues. This dynamic adjustment allows the system to efficiently utilize available memory across all queues rather than wasting capacity in low-activity queues during periods when other queues are overloaded.
3Stability of the object's composition
If internal priority values are statically assigned, then frame prioritization is deterministic, but high priority frames are dropped during queue overload
Solution Approach 1:
The patent implements dynamic internal priority value assignment that adjusts based on queue utilization conditions. While priority values are traditionally static, this system makes them dynamic by modifying the internal priority values of frames based on the current state of queues. When a high-priority queue becomes overloaded, the controller can adjust priority values to redirect frames to underutilized queues, ensuring that high-priority frames are not dropped even though the overall priority structure remains stable and deterministic for normal operation.
4Reliability
If queue depth is increased to prevent frame drops, then frame loss is reduced, but memory consumption increases
Solution Approach 1:
The patent implements dynamic queue depth adjustment that increases the depth of only those queues that are actually overloaded, rather than uniformly increasing all queue depths. The controller monitors each queue's utilization and dynamically expands the depth of overloaded queues to prevent frame drops, while simultaneously reducing or maintaining the depth of underutilized queues. This selective, dynamic approach prevents frame loss in critical queues without unnecessarily consuming additional memory resources across the entire system.
Data Source
AI summary
The present disclosure relates to controlling queue release in a network. In particular, the disclosure proposes a controller configured to obtain a state of each of a plurality of queues of a network node and determine, based on the states of the queues, whether the utilization of one or more queues exceeds one or more thresholds. If one or more thresholds are exceeded, the controller is configured to generate one or more new priority entries for one or more queues of the plurality of queues and provide the one or more new priority entries to the one or more queues of the network node. Further, the disclosure proposes a network node being configured to provide a state of each of a plurality of queues to a controller, and obtain one or more new priority entries for one or more queues of the plurality of queues from the controller.