Switch Congested Flow Queues for HOL Blocking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Head-Of-Line (HOL) blocking in computer networks reduces bandwidth utilization due to congestion at intermediate switches, requiring extensive queuing systems that become impractically complex and resource-intensive as network complexity increases.
Innovation Solution
Implementing a separate queue per output port and utilizing Congested Flow (CF) queues, where packets destined for congested paths are diverted, allowing other packets to continue transmission without the need for extensive queuing structures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If separate queues are implemented for each output port to reduce HOL blocking, then bandwidth utilization improves, but device complexity and resource requirements increase
Solution Approach 1:
The patent segments the queuing system into two distinct parts: (1) standard output port queues for normal packet transmission, and (2) a separate Congested Flow Queue (CFQ) specifically for packets destined to congested output ports. This segmentation allows the system to handle congested and non-congested flows differently, reducing HOL blocking for non-congested packets while isolating congestion management to a dedicated structure.
Solution Approach 2:
The patent extracts packets destined for congested output ports from the standard output port queues and places them into a separate CFQ. This extraction removes the blocking effect these packets would have on other packets in the queue, allowing non-congested packets to be transmitted without waiting for congested flow packets.
2Reliability
If extensive queuing structures are implemented to manage congestion at intermediate switches, then packet delivery reliability improves, but memory requirements and buffer space increase
Solution Approach 1:
The patent applies local quality by creating a specialized CFQ with specific properties tailored for congested flow management, rather than uniformly expanding all queues. The CFQ is positioned locally at the input port and works in conjunction with the standard output port queues, providing targeted congestion management only where needed rather than throughout the entire switching fabric.
3Productivity
If look-ahead congestion management is implemented to reduce HOL blocking, then network throughput improves, but device complexity increases
Solution Approach 1:
The patent implements preliminary action by proactively identifying packets that are destined for congested output ports before they reach the head of the queue. The system uses congestion information from output ports to pre-sort packets into the CFQ, so that when congestion is detected, the blocked packets are already separated and do not prevent other packets from being transmitted.
Solution Approach 2:
The patent employs feedback mechanisms where output ports provide congestion status information back to the input port. The input port uses this feedback to determine which packets should be placed in the CFQ versus the standard output port queues, creating a closed-loop congestion management system that dynamically adapts to network conditions.
Data Source
AI summary
The invention utilizes a separate queue per output port as implemented in the traditional simple queuing schemes of the prior art. Further, it also uses the information found in the packet header to determine the output port and the next output port. Based on this information, it utilizes queues dedicated to congested flows, or “Congested Flow” queues. When the switch determines that, based on the first output port and the second subsequent output port, a packet in the output queue is destined for a congested path, it sets the offending packet aside in a Congested Flow queue, thereby allowing other packets destined for the first output port to continue to be transmitted. In this way, the HOL blocking issue is addressed, without the need for a significantly increased number of output queues.


