Selective Port Locking for Distributed Switch Throughput
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing distributed network switch management systems face inefficiencies in processing operations due to serial processing of joint sets of ports, which can lead to bottlenecks and reduced throughput.
Innovation Solution
A method where operations on a distributed network switch are managed by queuing sets of ports into lanes, with joint sets processed serially and disjoint sets processed in parallel, allowing for concurrent operation on non-overlapping sets of ports.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If operations on joint sets of ports are processed serially, then data integrity and consistency are maintained, but processing throughput is reduced and bottlenecks occur
Solution Approach 1:
The patent segments the port operations into two distinct categories: joint sets (ports shared across multiple operations) and disjoint sets (ports exclusive to a single operation). This segmentation allows different processing strategies for each type, where disjoint sets can be processed in parallel while joint sets maintain serial processing for consistency, thereby resolving the throughput-integrity contradiction
Solution Approach 2:
The patent applies different processing qualities to different parts of the data structure. Joint sets receive serial processing with locking mechanisms to ensure data integrity, while disjoint sets receive parallel processing to maximize throughput. This local differentiation of processing quality allows the system to optimize for both reliability and productivity simultaneously
2Reliability
If all operations are processed serially, then data consistency is ensured, but processing time increases and system efficiency decreases
Solution Approach 1:
The patent introduces a dynamic processing model where the system automatically determines whether to process operations serially or in parallel based on the port set characteristics. The system dynamically assigns operations to different processing lanes and applies appropriate locking mechanisms only where necessary, reducing unnecessary serial processing delays while maintaining data consistency
Solution Approach 2:
By segmenting operations into joint and disjoint sets, the patent enables selective serial processing only where data consistency is at risk (joint sets), while allowing disjoint sets to proceed in parallel without compromising consistency. This targeted approach reduces overall processing time while maintaining reliability
3Productivity
If parallel processing is applied to all operations, then processing speed increases, but data integrity and consistency are compromised
Solution Approach 1:
The patent applies parallel processing quality locally to disjoint sets where data integrity is not compromised, while maintaining serial processing with locking for joint sets where data integrity is critical. This localized application of parallel processing maximizes speed where safe while preserving integrity where needed
Solution Approach 2:
The patent introduces locking mechanisms as intermediaries between parallel processing operations and shared data structures. These locks act as mediators that prevent concurrent modifications to joint sets while allowing disjoint sets to proceed in parallel, thus enabling safe parallel processing where appropriate
Data Source
AI summary
A management controller in a distributed network switch may operate on sets of ports such that sets of ports containing a same port are processed serially, and sets that do not contain any of the same ports can be processed in parallel. When receiving a set of ports for processing, the management controller organizes the ports into lanes that each correspond to a unique port. If any of the lanes overlap, subsequent port sets are blocked from proceeding until the lanes of preceding port sets are cleared. If no lanes overlap, the sets may be deemed disjoint, and subsequent port sets may be processed in parallel.