Simultaneous Queue and Global Random Early Detection Dropping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Random Early Detection (RED) packet dropping methods in packet processing systems often lead to inefficient distribution of queue space, causing network congestion due to 'tail drop' phenomena, where packets are dropped when queues are full, leading to suboptimal performance.
Innovation Solution
The implementation of instantaneous RED packet dropping with drop precedence, where a packet descriptor's drop probability is determined based on its instantaneous queue depth and drop precedence value, using a state machine and random number generators to decide whether to store or drop packets, allowing for variable drop probabilities across different queue depth ranges.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If RED packet dropping based on average queue depth is implemented, then queue space distribution efficiency is improved, but device complexity increases
Solution Approach 1:
The patent segments the queue management by dividing it into multiple independent queues, each with its own depth counter and drop probability calculation. This allows differentiated handling of different packet flows while maintaining manageable complexity through modular queue structures rather than a monolithic complex system
Solution Approach 2:
The patent applies local quality by allowing each queue to have its own drop probability and depth characteristics tailored to specific traffic flows. Each queue can be optimized independently with appropriate drop precedence values, enabling fine-grained control without requiring complex global management mechanisms
2Productivity
If instantaneous RED packet dropping with drop precedence is implemented, then network congestion is reduced, but processing time increases
Solution Approach 1:
The patent performs preliminary action by pre-calculating and storing drop probability thresholds in lookup tables before packets arrive. When a packet needs dropping decision, the system simply queries the pre-computed table based on current queue depth and drop precedence, avoiding complex real-time probability calculations and reducing processing time
Solution Approach 2:
The patent introduces an intermediary lookup table that mediates between the complex drop probability logic and the actual packet processing. The lookup table translates queue depth and drop precedence into simple pass/fail decisions, acting as a buffer that simplifies the processing path and reduces time overhead
3Productivity
If variable drop probabilities are applied across different queue depth ranges, then bandwidth allocation is improved, but measurement precision requirements increase
Solution Approach 1:
The patent applies dynamics by making drop probabilities adaptive rather than static. The system continuously monitors queue depth and dynamically adjusts drop decisions based on current conditions, allowing the network to respond to changing traffic patterns and optimize bandwidth allocation in real-time rather than relying on fixed predetermined values
Data Source
AI summary
A method for receiving a packet descriptor associated with a packet and a queue number indicating a queue stored within a memory unit, determining a priority level of the packet and an amount of free memory available in the memory unit. Applying a global drop probability to generate a global drop indicator and applying a queue drop probability to generate a queue drop indicator. The global drop probability is a function of the amount of free memory. The queue drop probability is a function of instantaneous queue depth or drop precedence value. The packet is transmitted whenever the priority level is high. When the priority level is low, the packet is transmitted when both the global drop indicator and the queue drop indicator are a logic low value. When the priority level is low, the packet is not transmitted when either drop indicator is a logic low value.