Distributed Storage Global Replication via Intelligent Elements

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current distributed data storage systems lack flexibility in presenting virtual storage to hosts, requiring data to be copied between controllers for efficient access, which hampers I/O performance and scalability.

Innovation Solution

A distributed storage system with a virtualization engine and intelligent storage elements (ISEs) that replicate data independently of access commands, allowing for global replication and optimized I/O performance by identifying and utilizing storage spaces with higher processing capabilities for data access.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If data is stored under one controller, then data integrity is maintained, but data access efficiency deteriorates when accessed from another controller requiring data copying

Engineering Contradiction:
Improvedata integrityVSAvoiddata access efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent segments data storage by creating multiple storage volumes across different controllers, allowing data to be divided and stored in distributed locations. This enables different controllers to access different segments of the same logical volume without requiring complete data copying, thus maintaining data integrity while improving access efficiency.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a new dimension of data access by enabling cross-controller access to storage volumes. Instead of restricting access to a single controller, the system allows multiple controllers to access the same logical volume simultaneously through the storage network, transforming the access model from single-point to multi-point access.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Speed

If data is copied between controllers for efficient access, then data access speed improves, but system complexity and resource consumption increase

Engineering Contradiction:
Improvedata access speedVSAvoidsystem complexity
Core Design Contradiction:
SpeedVSDevice complexity

Solution Approach 1:

The patent makes storage controllers universal by enabling them to access and manage multiple storage volumes that were originally designated for other controllers. Each controller gains the capability to access any logical volume in the system through the storage network, eliminating the need for dedicated data copying mechanisms and reducing overall system complexity.

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

3Productivity

If storage capacity is consolidated in SANs, then storage handling capability increases, but flexibility in altering virtual storage presentation deteriorates

Engineering Contradiction:
Improvestorage handling capabilityVSAvoidvirtual storage flexibility
Core Design Contradiction:
ProductivityVSAdaptability or versatility

Solution Approach 1:

The patent implements dynamic virtual storage allocation where logical volumes can be dynamically assigned to different controllers based on access patterns and performance requirements. The system can dynamically create, modify, and relocate virtual storage presentations without requiring physical data movement, providing both high storage handling capability and flexible virtual storage allocation.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS7644228B2Distributed storage system with global replication
Publication Date: 2010.01.05 SEAGATE TECH LLC
  • US7644228B2 patent drawing
  • US7644228B2 patent drawing
  • US7644228B2 patent drawing

AI summary

A data storage system apparatus and associated method with a virtualization engine connectable to a remote device over a network for passing access commands between the remote device and a storage space. A plurality of intelligent storage elements (ISEs) are configured for replicating data from a first ISE to a second ISE independently of access commands being simultaneously passed between the virtualization engine and the first ISE.