Identifying High Importance Devices in Storage Consistency Groups

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In computing systems, identifying high importance devices within a consistency group is challenging due to the inclusion of devices that do not exhibit dependent write operations, leading to unnecessary failure over and increased workload for consistency group management applications.

Innovation Solution

A method involving monitoring write patterns to determine high activity devices, forming pairs with low activity devices, and analyzing coordinated write probabilities and ratios to identify high importance devices, with a learning process trained to select candidate devices for removal or inclusion based on write dependencies.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If all devices are included in the consistency group, then data consistency is maintained, but system complexity and workload increase

Engineering Contradiction:
Improvedata consistencyVSAvoidconsistency group management complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments devices into different importance levels (high importance vs. low importance devices) based on write dependency analysis. This segmentation allows the consistency group to be managed in tiers, where only high importance devices require full consistency management, while low importance devices can be optimized or removed, thereby reducing overall system complexity while maintaining data consistency for critical devices.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies local quality by treating different devices within the consistency group differently based on their individual write dependency characteristics. Instead of applying uniform consistency management to all devices, the system identifies and applies optimized management strategies to specific devices based on their local properties (write patterns, dependency relationships), reducing unnecessary complexity for devices that don't require full consistency management.

Inventive Principle:
Principle #3Local quality

2Measurement precision

If all devices are monitored for write patterns, then accurate identification of high importance devices is achieved, but processing time and computational resources increase

Engineering Contradiction:
Improvedevice importance identification accuracyVSAvoidanalysis time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent extracts and focuses monitoring efforts on specific high-value metrics (write operations, write dependencies) rather than monitoring all possible device attributes. By extracting only the critical write pattern data needed for importance determination, the system achieves accurate device classification while minimizing the time and computational resources required for analysis.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The system uses the write pattern data that is already being collected for consistency management purposes to simultaneously determine device importance. This self-service approach allows the same monitoring infrastructure to serve dual purposes: maintaining consistency and identifying high importance devices, thereby reducing additional processing time and computational overhead.

Inventive Principle:
Principle #25Self-service

3Productivity

If low importance devices are removed from the consistency group, then workload is reduced, but data consistency may be compromised

Engineering Contradiction:
Improveconsistency group management efficiencyVSAvoiddata consistency
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent implements dynamic device classification where devices are categorized as high or low importance based on their actual write dependency patterns observed during operation. This dynamic approach allows the system to adaptively adjust which devices require full consistency management, enabling low importance devices to be removed or optimized without compromising consistency for the critical high importance devices that truly require it.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS20220107875A1Method and Apparatus for Identifying High Importance Devices of a Consistency Group
Publication Date: 2022.04.07 EMC IP HLDG CO LLC
  • US20220107875A1 patent drawing
  • US20220107875A1 patent drawing
  • US20220107875A1 patent drawing

AI summary

A consistency group is defined to include a set of required devices on a set of storage systems. High activity devices are determined, and write dependencies between each high activity device and each low activity devices are monitored. A set of high importance devices is determined to include the high activity devices and low activity devices with a high write dependency on at least one of the high activity devices. Comparative write patterns between the high importance devices and low importance devices are used to determine a set of candidate devices for removal from the consistency group. The high importance devices, rather than all devices of the consistency group, are also used to determine a set of devices that have inadvertently not been included in the consistency group.