Queue State Release Threshold Jitter for Network Traffic Fairness
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Network devices face challenges in handling queued data units due to unfair treatment of data units from different sources or types, leading to oscillation in queue states and potential overruns, which can result in unfair traffic management and resource imbalances.
Innovation Solution
Implementing a system that tracks queue size over time, updates queue state information based on thresholds, and adjusts the state release point randomly or pseudo-randomly to introduce jitter, ensuring fair treatment across multiple source ports and reducing periodic patterns in queue state transitions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If the queue size threshold is used to determine queue state transitions, then the queue management is simplified, but it causes unfair treatment of data units from different sources and leads to queue oscillation
Solution Approach 1:
The patent applies dynamics by making the release point variable rather than fixed. The release point is adjusted dynamically based on the queue length and a random offset, allowing the system to adapt to changing traffic conditions and prevent periodic oscillations while maintaining fairness across different data sources
Solution Approach 2:
The patent changes the parameter of the release point from a static threshold value to a dynamic value that incorporates random offsets. This parameter change transforms the deterministic queue state transition into a probabilistic one, preventing synchronized behavior across different queues and improving fairness
2Reliability
If the state release point is fixed at a threshold value, then the queue state transition is deterministic, but it causes periodic oscillation and unfair discarding of data units
Solution Approach 1:
The patent introduces dynamics by making the release point variable through random offsets. This prevents the deterministic periodic oscillation that occurs with fixed thresholds while maintaining enough structure through the base threshold to ensure predictable queue management behavior
Solution Approach 2:
The patent addresses periodic oscillation by introducing random offsets that break the periodicity. The random variation in release points prevents the synchronized periodic behavior that would otherwise occur when multiple queues operate with identical fixed thresholds
3Device complexity
If multiple queues operate with the same threshold, then resource allocation is simplified, but it leads to disproportionate discarding from specific sources
Solution Approach 1:
The patent applies local quality by allowing each queue to have its own randomized release point offset. This local variation in release points ensures that queues from different sources experience slightly different transition thresholds, preventing synchronized discarding patterns while maintaining overall resource allocation efficiency
Solution Approach 2:
The patent introduces asymmetry through random offsets that create slight differences in release points across queues. This asymmetric approach breaks the symmetry of identical threshold behavior, preventing unfair preferential treatment or disproportionate discarding of specific data sources
Data Source
AI summary
Techniques for improved handling of queues of data units are described, such as queues of buffered data units of differing types and/or sources within a switch or other network device. When the size of a queue surpasses the state entry threshold for a certain state, the queue is said to be in the certain state. While in the certain state, data units assigned to the queue may be handled differently in some respect, such as being marked or being dropped without further processing. The queue remains in this certain state until its size falls below the state release threshold for the state. The state release threshold is adjusted over time in, for example, a random or pseudo-random manner. Among other aspects, in some embodiments, this adjustment of the state release threshold addresses fairness issues that may arise with respect to the treatment of different types or sources of data units.