Storage System Drive Log Check for Write Hole Prevention

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing RAID systems face the 'write hole' problem where data and parity mismatch due to simultaneous power shutdown or failure during data writing, leading to unrecoverable data, and current countermeasures impose a significant load on the system.

Innovation Solution

A storage system with a computer, nonvolatile storage device, and high-speed storage device, where the storage area is divided into user and meta areas, with write log information recorded in the high-speed storage device, allowing for drive log check processing to identify redundant write log records and update their status, thereby reducing unnecessary data writes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If ID value assignment and collation is performed for each write command and corresponding write data to prevent write hole problems, then data reliability is improved, but system load increases enormously

Engineering Contradiction:
Improvedata reliabilityVSAvoidsystem load
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by recording the drive log in the high-speed storage device before actually writing data to the nonvolatile storage device. This allows the system to check and validate write operations in advance, ensuring data reliability while reducing the complexity of real-time validation during data writing operations.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces a drive log as an intermediary structure stored in the high-speed storage device. This drive log acts as a mediator between the write commands and the actual data writing process, allowing the system to track and validate write operations without imposing enormous load during the critical data writing phase.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Productivity

If write log information is recorded in the high-speed storage device and drive log check processing is performed, then the number of additional processing writes is reduced, but storage device structure complexity increases

Engineering Contradiction:
Improveprocessing efficiencyVSAvoidstorage device structure
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent segments the storage device into two distinct parts: a high-speed storage device for storing drive log information and a nonvolatile storage device for storing actual data. This segmentation allows the system to perform drive log check processing efficiently in the high-speed storage device, reducing the number of additional processing writes to the nonvolatile storage device while managing structure complexity through clear functional separation.

Inventive Principle:
Principle #1Segmentation

3Reliability

If the storage area is divided into user area and meta area with separate write log management, then data protection against write hole is improved, but storage management complexity increases

Engineering Contradiction:
Improvedata protectionVSAvoidstorage management complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent divides the storage area into a user area for storing actual data and a meta area for storing write log information. This segmentation enables separate management of data and metadata, improving data protection against write hole by allowing independent validation of write operations in the meta area while maintaining straightforward storage management through clear functional separation.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS11775175B2Storage system, storage management method, and storage management program
Publication Date: 2023.10.03 HITACHI VANTARA LTD
  • US11775175B2 patent drawing
  • US11775175B2 patent drawing
  • US11775175B2 patent drawing

AI summary

An amount of writing data to storage devices can be kept low in additional processing for solving the write hole problem. A storage system includes a computer(s), a nonvolatile storage device(s), and a high-speed storage device(s) which can be accessed at a higher speed than the above-mentioned storage device(s), and a drive log including write log information is recorded in the high-speed storage device. When the computer receives a write request for write data, the computer firstly performs drive log check processing and then performs data write processing. In the drive log check processing, if a redundant write log record is recorded in a drive log, the computer changes the write log status of the redundant write log record to “completed” by targeting at the drive log and the write log information and then proceeds to the data write processing; and if the redundant write log record is not recorded in the drive log, the computer proceeds to the data write processing without changing the drive log or the write log information.