End Point Multiplexing for Transport Layer Switch Memory
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Transport layer switches face inefficiencies when handling connections over links with significantly different effective rates, leading to memory waste and CPU processing issues, especially when dealing with a large number of connections and varying link quality.
Innovation Solution
Implementing an end point-multiplexing scheme using a shared logical ring buffer for memory allocation, where packets are dynamically allocated packet-by-packet, and a pointer mechanism ensures consecutive packet management across connections, optimizing resource utilization and reducing switching overhead.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If separate memory buffers are allocated for each connection to ensure efficient data transfer, then connection performance is improved, but memory utilization deteriorates when link rates differ significantly
Solution Approach 1:
The patent merges separate memory buffers for different connections into a shared memory pool, allowing dynamic allocation and reuse of memory space across multiple connections, thereby improving overall memory utilization while maintaining connection performance
Solution Approach 2:
The patent implements dynamic memory allocation where buffer sizes and assignments are adjusted in real-time based on actual link rates and traffic conditions, enabling the system to adapt to varying link qualities and optimize both performance and resource utilization
2Reliability
If separate memory buffers are allocated for each connection to maintain data integrity, then connection reliability is improved, but device complexity deteriorates when handling large numbers of connections
Solution Approach 1:
The patent segments the memory management system into modular components including a shared memory pool, allocation manager, and connection-specific control structures, allowing complex memory management to be handled through organized, manageable segments rather than monolithic buffer assignments
Solution Approach 2:
The patent creates a universal memory management framework that handles multiple connections through a common set of procedures and data structures, reducing complexity by eliminating the need for separate dedicated management systems for each connection
3Ease of operation
If fixed-size memory buffers are allocated to each connection to simplify management, then ease of operation is improved, but resource utilization deteriorates due to internal fragmentation
Solution Approach 1:
The patent transitions from static fixed-size buffer allocation to dynamic buffer management where memory sizes and assignments are adjusted based on actual needs, eliminating internal fragmentation while maintaining operational simplicity through automated management
Data Source
AI summary
This disclosure provides for an enhancement to a transport layer switch and, in particular the management of end points. In this approach, a memory space, such as a large logical ring buffer, is shared by incumbent connections to facilitate a space multiplexing end point management scheme. Preferably, memory allocation in the memory space is done packet-by-packet dynamically. Because the memory space is shared by all admitted connections, packets belonging to the same connection are not necessarily located physically consecutive to each other. A packet indexing mechanism that implements a set of pointers ensures that consecutiveness for packets on the same connection is maintained. This approach to end point multiplexing provides significant benefits by improving resource utilization, and enabling a higher number of connections to be served.