Storage System Parity Group Range Division

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing storage systems face limitations in expanding reliability without compromising availability, particularly when adding nodes, as excessive node distribution increases the impact of failures and reduces system availability.

Innovation Solution

A storage system that configures parity groups across multiple nodes, allowing data and parity to be stored within a predetermined range, and performs processing to divide or merge these ranges based on node state, thereby maintaining high reliability and applicability.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If nodes are distributed across a wide range to expand storage capacity, then storage capacity increases, but reliability deteriorates due to increased impact of node failures

Engineering Contradiction:
Improvestorage capacityVSAvoidsystem reliability
Core Design Contradiction:
Quantity of substanceVSReliability

Solution Approach 1:

The storage system divides the node pool into multiple predetermined ranges, and further divides parity groups into sub-parity groups that are confined within specific ranges. This segmentation limits the propagation of failure impacts within each range while maintaining overall system capacity expansion.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Different predetermined ranges are assigned different reliability characteristics through localized parity group configurations. Each range can be optimized independently, allowing the system to maintain high reliability in critical ranges while expanding capacity in other ranges.

Inventive Principle:
Principle #3Local quality

2Reliability

If nodes are concentrated in a limited range to improve reliability, then reliability improves, but storage capacity expansion is limited

Engineering Contradiction:
Improvesystem reliabilityVSAvoidstorage capacity
Core Design Contradiction:
ReliabilityVSQuantity of substance

Solution Approach 1:

The system introduces a new dimension of organization by creating multiple predetermined ranges along the storage architecture. This allows capacity expansion in the range dimension while maintaining reliability through localized parity groups within each range, effectively decoupling the two objectives.

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

3Reliability

If the system is expanded in units of minimum configuration to maintain reliability, then reliability target is maintained, but degree of freedom decreases

Engineering Contradiction:
Improvereliability targetVSAvoiddegree of freedom
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The system dynamically adjusts parity group configurations across multiple predetermined ranges based on operational needs. Parity groups can be divided into sub-parity groups and reconfigured flexibly within ranges, allowing the system to adapt to various expansion scenarios while maintaining reliability targets.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The predetermined range structure serves multiple functions: it confines failure impacts, enables flexible capacity expansion, and maintains reliability targets. This universal structure supports various system configurations and expansion patterns without requiring minimum configuration units.

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

Data Source

PatentUS11544005B2Storage system and processing method
Publication Date: 2023.01.03 HITACHI VANTARA LTD
  • US11544005B2 patent drawing
  • US11544005B2 patent drawing
  • US11544005B2 patent drawing

AI summary

In a storage system including a plurality of nodes that provide a storage area and a drive that physically stores data, a parity group is configured with a plurality of data including user data stored in the storage area and redundant data for protecting the user data, a plurality of data in the parity group are stored in a storage area within one predetermined range across a plurality of nodes, and processing for dividing the predetermined range or processing for merging a plurality of predetermined ranges is performed based on a state of the predetermined range.