TCP/IP Stack Logical Link Pairing for Mainframe I/O Throughput
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
High network latency in mainframe computing environments, particularly in systems like IBM's System z series, negatively impacts I/O throughput due to limitations in single network performance.
Innovation Solution
A computer-implemented method and system that manages two physical links using a TCP/IP stack to configure and activate interfaces, associating them logically to exchange traffic under a single internet protocol address, allowing for the use of different physical link types to enhance throughput.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a single network link is used for I/O communication, then device complexity is reduced, but network latency increases and throughput is limited
Solution Approach 1:
The network interface is segmented into multiple physical links (first physical link and second physical link) that can be independently configured and activated. Each link can be associated with different physical link types, allowing selective use of high-speed links for throughput-critical traffic while maintaining simpler configuration for individual links.
Solution Approach 2:
The system dynamically activates or deactivates physical links based on traffic conditions and performance requirements. The TCP/IP stack can activate the first interface, detect CHPID, create a second interface, and associate them logically, enabling dynamic adaptation of network topology to optimize throughput while managing complexity through on-demand configuration.
2Speed
If multiple physical links with different link types are used, then throughput is enhanced, but device complexity increases
Solution Approach 1:
The TCP/IP stack serves as a universal interface manager that handles multiple physical link types through a unified abstraction layer. It configures, activates, and manages diverse physical links (e.g., Ethernet, Fibre Channel) using the same procedural framework, enabling high-speed communication while hiding the complexity of different link types from applications.
Solution Approach 2:
The TCP/IP stack acts as an intermediary between applications and physical network links. It translates application-level network requests into appropriate physical link operations, managing the complexity of coordinating multiple different physical link types while presenting a simplified interface to upper-layer protocols.
3Adaptability or versatility
If multiple interfaces are associated logically, then packet routing flexibility is improved, but measurement and detection difficulty increases
Solution Approach 1:
The system uses feedback mechanisms where the TCP/IP stack detects channel path identifiers (CHPID) and uses this information to automatically associate interfaces and configure traffic routing. This feedback-driven approach enables flexible packet routing decisions while simplifying detection through structured monitoring of link status and traffic patterns.
Data Source
AI summary
A method, system and computer program product for managing at least two physical links. A TCP/IP stack configures a first interface with attributes. The TCP/IP stack activates the first interface. The TCP/IP stack detects a channel path identifier (CHPID). The TCP/IP stack creates a second interface. The TCP/IP stack associates the second interface with the first interface. The first interface and the second interface are logically linked to exchange traffic corresponding to a single internet protocol address. The TCP/IP stack configures the second interface with at least one attribute. The TCP/IP stack activates the second interface. The two physical links may rely on two different physical link types.