Asynchronous Replication via Full-Path File Handles

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current cloud storage solutions face challenges in efficiently replicating data between on-premises and cloud storage systems, particularly in generating reliable file-handles for remote inode numbers, which affects data replication and access latency, and requires costly and resource-intensive methods like hashing and directory hierarchy maintenance.

Innovation Solution

The method involves identifying independent filesystems that use file-handles and those that operate independently, generating file-handles based on full-paths for data replication, and leveraging inodes to optimize data movement between systems, enabling asynchronous replication and caching without the need for hashing or directory hierarchy maintenance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional hashing and directory hierarchy maintenance methods are used for data replication, then data can be replicated between on-premises and cloud storage, but the process becomes resource-intensive and costly

Engineering Contradiction:
Improvedata replication reliabilityVSAvoidreplication process complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent extracts the file handle generation process from traditional hashing and directory hierarchy maintenance, replacing it with a direct full-path based approach. This removes the complex intermediate steps while maintaining the essential function of unique file identification and replication tracking.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

Instead of generating file handles through hashing algorithms and maintaining directory hierarchies (traditional approach), the patent inverts the approach by directly using full-paths as the basis for file handle generation. This reversal simplifies the process while achieving the same reliability goals.

Inventive Principle:
Principle #13The other way round (Inversion)

2Quantity of substance

If cloud storage is used for data replication, then storage capacity and accessibility are improved, but data access latency increases

Engineering Contradiction:
Improvestorage capacityVSAvoiddata access latency
Core Design Contradiction:
Quantity of substanceVSLoss of time

Solution Approach 1:

The patent implements preliminary action by pre-generating file handles based on full-paths during the replication process. This allows the system to have file handles ready in advance, reducing the time needed for data access and operations without sacrificing cloud storage capacity benefits.

Inventive Principle:
Principle #10Preliminary action

3Productivity

If asynchronous replication is implemented, then data movement flexibility is improved, but file handle reliability becomes problematic

Engineering Contradiction:
Improvedata replication efficiencyVSAvoidfile handle reliability
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent introduces full-paths as an intermediary element that mediates between the asynchronous replication process and file handle generation. This intermediary ensures that even in asynchronous operations, reliable and consistent file handles can be generated without compromising replication efficiency.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS11086557B2Continuous asynchronous replication from on-premises storage to cloud object stores
Publication Date: 2021.08.10 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • US11086557B2 patent drawing
  • US11086557B2 patent drawing
  • US11086557B2 patent drawing

AI summary

A system identifies (I) a first independent filesystem that (i) includes a file and (ii) uses file-handles to locate files and (II) a second independent filesystem that (i) operates independently of file-handles, associated with the first independent filesystem, when locating files and (ii) includes a copy of the file. The system generates a file-handle for the copy of the file on an inode of first independent filesystem based on a full-path for the copy of the file on the second independent filesystem. The system replicates one or more data blocks between the first independent filesystem and the second independent filesystem based, at least in part, on the full-path.