Mapped RAID Load Balancing via LUN Slice Migration

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Traditional RAID data storage systems face limitations in adding new disks and rebuilding data after a failure, leading to inflexibility and long rebuild times, which can result in data loss during concurrent failures.

Innovation Solution

The mapped RAID technology allows for the addition of individual non-volatile data storage drives and implements load balancing by moving slices of a logical unit between different rotation groups of RAID extent entries, spreading rebuild operations across multiple drives to reduce bottlenecks and improve performance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional RAID technology is used, then data redundancy and performance improvement are provided, but flexibility in adding new disks is limited and rebuild times are long

Engineering Contradiction:
Improveflexibility in adding new disksVSAvoidrebuild time
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent segments the storage system into rotation groups, where each group contains drives that rotate simultaneously. This segmentation allows independent addition of drives to specific rotation groups without requiring system-wide reconfiguration or lengthy rebuild operations, directly addressing the contradiction between adaptability and rebuild time.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces dynamic drive addition capability where new drives can be added to rotation groups at runtime without system shutdown. The system dynamically adjusts the rotation group configuration to accommodate new drives, maintaining performance while eliminating the need for lengthy traditional rebuild processes.

Inventive Principle:
Principle #15Dynamics

2Reliability

If traditional RAID technology is used, then data redundancy is provided, but system performance is limited by sequential rebuild operations

Engineering Contradiction:
Improvedata redundancyVSAvoidsystem performance
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

By dividing drives into separate rotation groups, the patent enables parallel rebuild operations across multiple groups simultaneously. This segmentation transforms the sequential rebuild process into a parallel one, significantly improving system performance while maintaining data redundancy through the RAID configuration.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent ensures continuous useful action during rebuild operations by allowing multiple rotation groups to operate in parallel. While one group is being rebuilt, other groups continue to serve I/O requests, eliminating the performance bottleneck of sequential rebuilds and maintaining system productivity.

Inventive Principle:
Principle #20Continuity of useful action

3Speed

If I/O operations are concentrated on fewer drives, then access speed is improved, but drive lifetime is reduced due to uneven wear

Engineering Contradiction:
ImproveI/O access speedVSAvoiddrive lifetime
Core Design Contradiction:
SpeedVSDuration of action of stationary object

Solution Approach 1:

The patent segments I/O operations across multiple rotation groups, distributing the workload evenly. Each rotation group handles a portion of the total I/O load, preventing any single drive from becoming a bottleneck while also avoiding excessive wear on individual drives, thus extending overall system lifetime.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent dynamically adjusts the mapping between logical units and rotation groups based on load conditions. By changing the distribution parameters of I/O operations across different rotation groups, the system optimizes both access speed and drive lifetime, preventing uneven wear patterns.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS10318169B2Load balancing of I/O by moving logical unit (LUN) slices between non-volatile storage represented by different rotation groups of RAID (Redundant Array of Independent Disks) extent entries in a RAID extent table of a mapped RAID data storage system
Publication Date: 2019.06.11 EMC IP HLDG CO LLC
  • US10318169B2 patent drawing
  • US10318169B2 patent drawing
  • US10318169B2 patent drawing

AI summary

Load balancing in a mapped RAID data storage system that moves slices of logical unit (LUN) address space between non-volatile storage represented by different rotation groups of RAID extent entries in a RAID extent table. The RAID extent table is divided into RAID extent groups corresponding to partnership groups of drives, and the RAID extent groups are divided into rotation groups. At least one LUN with an address space made up of slices is generated for each RAID extent group. Host data directed to each slice is stored in drive extents indicated by the RAID extent entries in the rotation group to which the slice is mapped. A rebalancing operation modifies the mapping between slices in a LUN and the rotation groups in the corresponding RAID extent group such that at least one slice is remapped from a heavily loaded rotation group to a lightly loaded rotation group.