Dynamic Connection Setup Request Throttling in Network Control Cards
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Network elements face inefficiencies in processing connection setup request packets due to hard-coded throttling mechanisms, leading to processor underutilization or overload, resulting in increased latency and potential timeouts, especially when handling multiple types of requests with varying resource requirements.
Innovation Solution
A dynamic adjustment mechanism that modifies connection setup request rate and burst values based on real-time processor utilization and queue occupancy, allowing the control plane to adapt the number of packets processed and scheduled across multiple points of entry, optimizing processor utilization and reducing latency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If hard-coded connection setup request throttling parameters are used, then the system structure is simple, but the processor utilization is inefficient and latency increases
Solution Approach 1:
The patent implements dynamic adjustment of connection setup request rate and burst parameters based on real-time processor utilization metrics. The throttling mechanism transitions from static hard-coded values to dynamically adjustable parameters that adapt to current system load conditions, thereby optimizing processor utilization efficiency without requiring complex system architecture changes.
Solution Approach 2:
The patent changes the throttling parameters (rate and burst values) from fixed hard-coded constants to dynamically modifiable variables. By adjusting these parameters based on processor utilization feedback, the system optimizes connection setup request handling efficiency while maintaining the existing simple throttling mechanism structure.
2Reliability
If worst-case scenario throttling parameters are assumed, then connection timeout issues are reduced, but the processor becomes underutilized
Solution Approach 1:
The patent implements a feedback mechanism that monitors processor utilization metrics and uses this information to dynamically adjust connection setup request throttling parameters. This closed-loop control allows the system to maintain reliable connection setup handling while optimizing processor utilization by adapting to actual system conditions rather than assuming worst-case scenarios.
Solution Approach 2:
The system transitions from static worst-case parameter assumptions to dynamic parameter adjustment based on real-time processor utilization. This allows the throttling mechanism to adapt its behavior to current system conditions, maintaining reliability while preventing processor underutilization.
3Productivity
If best-case scenario throttling parameters are assumed, then processor utilization is maximized, but queue occupancy increases causing timeouts and thrashing
Solution Approach 1:
The patent employs feedback control by monitoring both processor utilization and queue occupancy metrics. When queue occupancy reaches critical thresholds, the system dynamically reduces the connection setup request rate and burst parameters, preventing timeout conditions and thrashing while maintaining high processor utilization under normal conditions.
Solution Approach 2:
The throttling parameters are made dynamic and adaptive, adjusting in real-time based on system conditions. This allows the system to maximize processor utilization when conditions permit while automatically reducing parameters when queue occupancy becomes problematic, thereby maintaining both productivity and reliability.
4Productivity
If connection setup request rate is increased to improve productivity, then more requests are processed, but latency increases and timeouts occur
Solution Approach 1:
The patent implements dynamic adjustment of connection setup request rate parameters based on real-time monitoring of processing latency and queue occupancy. This allows the system to optimize throughput by increasing the request rate when processing capacity is available while automatically reducing the rate when latency begins to increase, preventing timeout conditions.
Solution Approach 2:
The system dynamically changes the connection setup request rate and burst parameters based on observed system performance. By adjusting these parameters in response to latency measurements, the system optimizes request processing throughput while maintaining acceptable latency levels.
Data Source
AI summary
A method, performed in a network element having a control card and a plurality of linecards of processing a plurality of different types of connection setup requests. A latency of processing each of the plurality of the different types of the connection setup requests is determined. A number of connection setup requests to be initiated to be processed by the control card is dynamically adjusted based on the determined latencies of processing each of the plurality of the different types of the connection setup requests. Other methods and network elements are also disclosed.


