File Metadata Handler for Distributed File System Parallel Processing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current integrated managed file transfer solutions, such as ActiveTransfer, face limitations in processing large files and data volumes, requiring high skill and time for custom logic implementation, and may lead to networking bottlenecks and storage management issues, especially when dealing with complex distributed file systems.

Innovation Solution

Integration of a File Metadata Handler with distributed file systems and map reduce frameworks, enabling dynamic file processing, metadata management, and custom logical splitting of files, along with support for various file formats and encryption protocols, to facilitate efficient data processing and storage across multiple nodes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If files are processed sequentially by individual clients, then networking bottlenecks are avoided, but processing time and productivity decrease

Engineering Contradiction:
Improveprocessing speedVSAvoidnetwork stability
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The system segments large files into smaller blocks that can be processed in parallel across multiple nodes. The File Metadata Handler divides files into manageable units, allowing simultaneous processing while maintaining network stability through distributed load management.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The File Metadata Handler acts as an intermediary between clients and the distributed file system. It manages metadata for multiple files, coordinates parallel processing tasks, and handles network communications, thereby enabling efficient batch processing without creating networking bottlenecks.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If custom logic is implemented for file processing, then processing flexibility is improved, but skill requirements and time consumption increase

Engineering Contradiction:
Improveprocessing flexibilityVSAvoidoperational simplicity
Core Design Contradiction:
Adaptability or versatilityVSEase of operation

Solution Approach 1:

The File Metadata Handler enables self-service processing by automatically managing metadata, file splitting, and parallel task distribution. Users can define processing logic without needing to manually manage complex distributed system operations, reducing skill requirements while maintaining flexibility.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system allows users to configure processing parameters such as file splitting strategies, parallelization degrees, and processing logic through parameter definitions. This enables flexible processing adaptation without requiring deep technical knowledge of the underlying distributed system architecture.

Inventive Principle:
Principle #35Parameter changes

3Productivity

If files are not split into blocks, then storage management is simplified, but processing efficiency and scalability decrease

Engineering Contradiction:
Improveprocessing efficiencyVSAvoidstorage management complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The File Metadata Handler automatically segments files into blocks and manages their distribution across nodes. This segmentation enables parallel processing and improved scalability while the handler itself manages the complexity of block management, avoiding the need for users to manually handle fragmented storage.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The File Metadata Handler serves as an intermediary that manages file blocking, metadata storage, and node distribution. It abstracts the complexity of block management from users and applications, providing simplified access while enabling efficient parallel processing.

Inventive Principle:
Principle #24Intermediary (Mediator)

4Productivity

If batch processing is used, then throughput is improved, but latency for data access increases

Engineering Contradiction:
Improvedata throughputVSAvoidaccess latency
Core Design Contradiction:
ProductivityVSSpeed

Solution Approach 1:

The system dynamically adjusts processing modes based on workload characteristics. The File Metadata Handler can coordinate batch processing for high throughput when appropriate, while also enabling individual file access when low latency is required, providing flexible adaptation to different operational needs.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS10255286B2File metadata handler for storage and parallel processing of files in a distributed file system, and associated systems and methods
Publication Date: 2019.04.09 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • US10255286B2 patent drawing
  • US10255286B2 patent drawing
  • US10255286B2 patent drawing

AI summary

Certain example embodiments described herein relate to a File Metadata Handler that helps an integrated managed file transfer solution perform processing in connection with complex distributed file systems, while still cooperating with more straightforward and/or conventional file systems, servers, and/or the like. The File Metadata Handler of certain example embodiments may be able to work with, or take the place of, a more conventional file handler adapter, e.g., to provide possibly required pre-processing and/or additional file processing at runtime for more complex file systems, transport protocols, and/or the like.