IO Request Rerouting via Proxy Systems for Disconnected Storage

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In clustered computing environments, channel disconnections with remote storage devices disrupt IO operations, leading to failed testing and costly disruptions, as systems without direct connections are unable to perform IO operations.

Innovation Solution

The implementation of a method where a first system reroutes IO requests to a second system acting as a proxy, which maintains channel connections to the target remote storage device, enabling continued IO operations even during channel disconnections.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If systems establish direct channel connections to remote storage devices, then IO operation reliability is improved, but system complexity and connection management overhead increase

Engineering Contradiction:
ImproveIO operation reliabilityVSAvoidconnection management complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent introduces a proxy system that acts as an intermediary between the first system and the remote storage device. The proxy system maintains the channel connection to the storage device and forwards IO requests from the first system, eliminating the need for the first system to establish and manage direct channel connections while ensuring IO operations can proceed reliably.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The proxy system serves multiple functions: it acts as a channel connection maintainer, an IO request forwarder, and a connection management hub for multiple systems. By consolidating these functions in a single system, the patent reduces overall system complexity while maintaining reliable IO operations for multiple clients.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Speed

If systems maintain direct channel connections to storage devices, then IO operation speed is improved, but system availability during connection failures deteriorates

Engineering Contradiction:
ImproveIO operation speedVSAvoidsystem availability
Core Design Contradiction:
SpeedVSReliability

Solution Approach 1:

The proxy system serves as a resilient intermediary that maintains persistent channel connections to storage devices. When a first system experiences connection failure, the proxy system continues to maintain the connection and forward IO requests, ensuring system availability without sacrificing IO operation speed.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The proxy system preemptively maintains channel connections to storage devices on behalf of multiple systems, cushioning against connection failures before they occur. This allows systems to rely on the proxy for connection resilience while maintaining fast IO operations through the established connection pathways.

Inventive Principle:
Principle #11Beforehand cushioning (Prior cushioning)

3Reliability

If proxy systems are introduced to handle IO requests, then system availability is improved, but device complexity increases

Engineering Contradiction:
Improvesystem availabilityVSAvoidsystem architecture complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The proxy system is designed to perform multiple functions including connection maintenance, IO request forwarding, and failure recovery. This multi-functionality consolidates what would otherwise require multiple separate systems or components, actually reducing overall system architecture complexity while improving availability.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The proxy system autonomously manages channel connections and IO request routing without requiring complex coordination protocols between multiple systems. By handling connection management and failure recovery independently, the proxy simplifies the overall system architecture compared to distributed failure management approaches.

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS20250199683A1Apparatus, systems and methods for providing input/output (IO) request rerouting
Publication Date: 2025.06.19 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • US20250199683A1 patent drawing
  • US20250199683A1 patent drawing
  • US20250199683A1 patent drawing

AI summary

Methods, apparatus and systems receive an IO reroute request for a first system to reroute an IO request with a target storage device that is disconnected from the first system and provides proxy communication of the IO request with the target storage device on behalf of the first system based on the received IO reroute request, using at least a second system that is connected to the same target storage device.