Shared Network Filesystem for Remote Job Submission

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current distributed computer systems require clients to manually manage job submission and result retrieval, limiting real-time monitoring and increasing complexity in accessing and executing jobs across remote processing environments.

Innovation Solution

A remote file system accessible via a local file system interface allows clients to submit job requests and view execution results without halting the process, using a backend data center with input, active, and output directories for job management and execution.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If clients manually manage job submission and result retrieval using web forms or FTP servers, then job execution can be achieved, but the system complexity increases and real-time monitoring capability is limited

Engineering Contradiction:
Improvejob submission and result retrievalVSAvoiduser interface and protocol management
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent introduces a shared network filesystem as an intermediary layer between the client and the remote processing system. The client interacts with the remote filesystem through standard filesystem operations (read, write, delete) rather than through complex web forms or FTP protocols. The filesystem automatically detects job requests when files are written to the input directory, eliminates the need for manual protocol management, and provides real-time monitoring capabilities through standard filesystem read operations on the output directory.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Loss of time

If clients use web forms or FTP servers to submit jobs, then remote processing can be achieved, but real-time result monitoring requires halting the execution process

Engineering Contradiction:
Improvejob execution timeVSAvoidreal-time result viewing
Core Design Contradiction:
Loss of timeVSEase of operation

Solution Approach 1:

The patent enables continuous job execution without interruption while allowing real-time result monitoring. The shared network filesystem maintains the output directory continuously accessible during job execution. Clients can read results from the output directory at any time during execution without needing to halt the process, as the filesystem automatically manages the execution state and makes results available as they are generated.

Inventive Principle:
Principle #20Continuity of useful action

3Ease of operation

If a remote file system is made accessible via local file system interface, then client interaction is simplified, but the underlying remote system complexity increases

Engineering Contradiction:
Improveremote file system accessVSAvoidbackend data center architecture
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent creates a virtual copy of the remote filesystem interface that mirrors the backend data center's directory structure and file operations through a shared network filesystem. The client interacts with this virtual copy using standard local filesystem operations, while the backend maintains the actual complex processing infrastructure. The network filesystem translates simple read/write/delete operations into the appropriate remote processing commands, hiding the backend complexity from the client.

Inventive Principle:
Principle #26Copying

Data Source

PatentUS8427668B2Grid job submission using shared network filesystem
Publication Date: 2013.04.23 ORACLE AMERICAN INC
  • US8427668B2 patent drawing
  • US8427668B2 patent drawing
  • US8427668B2 patent drawing

AI summary

A method for executing a job using a remote file system that includes obtaining a plurality of job data files by the remote file system, wherein the plurality of job data files are created on the remote file system, detecting a job request for the job in an input directory to obtain a detected job request, wherein the job request is generated by a client, and executing the job based on the job data files and the detected job request, wherein executing the job generates an output file, wherein the remote file system is accessible using a local file system of the client.