Dynamic RAID Level Selection Based on Storage Segment Reliability

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Legacy RAID systems face challenges in providing adequate data protection due to varying error rates among physical drives, leading to increased data loss probability when multiple drives fail, especially in Mapped RAID groups where drives with different health levels are combined.

Innovation Solution

A method that receives telemetry data from storage devices to define reliability levels, partitions devices into segments, and dynamically selects RAID levels based on segment reliability, opting for single parity when all segments are reliable, double parity when one is unreliable, and mirroring when multiple segments are unreliable, allowing for adaptive data protection.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If a single RAID level is used for all storage device segments, then device complexity is reduced, but data protection reliability deteriorates because drives with different health levels are combined in the same RAID group

Engineering Contradiction:
ImproveRAID configuration complexityVSAvoiddata protection reliability
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The patent divides the storage system into multiple RAID groups, with each RAID group containing storage device segments from drives of similar reliability levels. This segmentation allows different RAID levels to be applied to different groups based on their specific reliability characteristics, resolving the contradiction by preventing mixing of drives with different health levels while maintaining manageable system complexity through organized grouping.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies different RAID levels (e.g., RAID 5, RAID 6, RAID 1) to different RAID groups based on the specific reliability characteristics of the drives in each group. This local quality approach ensures that each group receives the appropriate level of protection tailored to its drive health status, rather than applying a uniform RAID level across all drives, thereby improving overall data protection reliability without excessive complexity.

Inventive Principle:
Principle #3Local quality

2Productivity

If drives with different error rates are combined in the same RAID group, then resource utilization is optimized, but the probability of data loss increases when multiple drives fail

Engineering Contradiction:
Improveresource utilizationVSAvoiddata loss probability
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent segments drives into different RAID groups based on their reliability metrics, such as error rates and health status. This segmentation ensures that drives with similar error rates are grouped together, reducing the probability that multiple drives in the same RAID group will fail simultaneously, thereby lowering data loss probability while still achieving good resource utilization through flexible allocation.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent dynamically adjusts RAID group compositions and RAID levels based on changing drive reliability parameters such as error rates and health status. This parameter-based approach allows the system to adapt to drive degradation over time, maintaining optimal data protection by redistributing segments from failing drives to healthier drives or upgrading RAID levels in high-risk groups, thus balancing resource utilization with data loss prevention.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS11275513B2System and method for selecting a redundant array of independent disks (RAID) level for a storage device segment extent
Publication Date: 2022.03.15 EMC IP HLDG CO LLC
  • US11275513B2 patent drawing
  • US11275513B2 patent drawing
  • US11275513B2 patent drawing

AI summary

A method, computer program product, and computing system for receiving telemetry data associated with a plurality of storage devices. A storage device reliability level may be defined for each storage device based upon, at least in part, the telemetry data associated with the plurality of storage devices. Each storage device may be partitioned into a plurality of storage device segments. A storage device segment reliability level may be defined for the plurality of storage device segments based upon, at least in part, the storage device reliability level of the plurality of storage devices. A subset of the plurality of storage device segments may be combined, thus defining a storage device segment extent. A RAID level for the storage device segment extent may be selected based upon, at least in part, the storage device segment reliability level of each storage device segment of the storage device segment extent.