Cache Modified Data Recovery in Dual Cluster Storage Systems

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In a dual cluster system, if one non-volatile storage (NVS) fails during a recovery operation, the modified data in the cache of the other cluster cannot be recovered, necessitating additional recovery operations to determine the modified data that was in the cache.

Innovation Solution

A method is implemented where each subsystem's cache and backup storage are scanned to detect and store indications of modified data units, allowing these indications to be used during recovery operations, ensuring that modified data can be recovered even if the backup storage of one cluster is unavailable.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If backup storage is used to store modified data, then data reliability is improved, but device complexity increases

Engineering Contradiction:
Improvedata reliabilityVSAvoiddevice complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent creates a copy of modified data from the primary cache to a backup storage location in a different cluster. This copy mechanism ensures that if the primary cache or its associated backup storage fails, the modified data can be recovered from the backup location, thereby improving data reliability while maintaining a manageable system architecture through distributed redundancy.

Inventive Principle:
Principle #26Copying

2Reliability

If additional recovery operations are performed, then data integrity is improved, but loss of time increases

Engineering Contradiction:
Improvedata integrityVSAvoidrecovery time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent performs preliminary actions by pre-identifying and pre-storing modified data in backup locations before failures occur. The system maintains a record of which data has been modified and stores it in advance in remote backup storage, so that during recovery operations, the system can quickly retrieve the necessary data without performing extensive scanning or additional recovery operations, thus reducing recovery time while ensuring data integrity.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP2382544B1Determining modified data in cache for use during a recovery operation
Publication Date: 2012.03.28 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • EP2382544B1 patent drawingFigure 1
  • EP2382544B1 patent drawingFigure 2~3
  • EP2382544B1 patent drawingFigure 4

AI summary

Provided are a method, system, and article of manufacture for determining modified data in cache for use during a recovery operation. An event is detected during which processing of writes to a storage device is suspended. A cache including modified data not destaged to the storage device is scanned to determine the data units having modified data in response to detecting the event. The data units having the modified data is indicated in a backup storage. The indication of the data units having the modified data in the backup storage is used during a recovery operation.