Consistency Group Integrity Application for Storage Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Inconsistency groups in computing systems often fail to include all necessary devices, leading to data inconsistencies and potential business disruptions during failures, as write operations on excluded devices are not managed, causing data to be present on target sites that should not be there.
Innovation Solution
A learning process is trained to analyze write patterns and identify devices missing from a consistency group by comparing write operations between included and excluded devices, using a device pairing data structure to calculate coordinated write probabilities and ratios, and deploying a consistency group integrity application to automatically include or alert for inclusion of missing devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If devices are manually added to consistency groups, then data consistency is improved, but device complexity and manual operation burden increase
Solution Approach 1:
The system automatically identifies devices that should be in consistency groups by analyzing write patterns, and automatically adds them without requiring manual intervention. The learning process continuously monitors write operations and self-adjusts the consistency group composition based on detected patterns.
Solution Approach 2:
The system implements continuous monitoring of write patterns and uses this feedback to dynamically adjust consistency group membership. The learning process analyzes write coordinate probabilities and continuously refines which devices should be included in consistency groups based on observed behavior.
2Reliability
If all devices are included in consistency groups, then data consistency is improved, but system performance and productivity deteriorate due to excessive monitoring and management overhead
Solution Approach 1:
The system segments devices into different consistency groups based on their write pattern characteristics. Rather than including all devices in a single consistency group, devices are divided into multiple groups based on their coordination requirements, reducing the management overhead for each group while maintaining overall data consistency.
Solution Approach 2:
The system applies partial action by only including devices in consistency groups when the write coordinate probability threshold is exceeded. Rather than universally including all devices, the system selectively includes only those devices that demonstrate coordinated write patterns, avoiding unnecessary monitoring overhead for devices that don't require consistency management.
3Measurement precision
If manual monitoring of write patterns is performed, then missing devices are identified, but time consumption and operational burden increase
Solution Approach 1:
The system replaces manual monitoring and analysis with an automated learning process that uses machine learning algorithms to analyze write patterns. The learning process automatically detects coordinated write behaviors and identifies devices that should be in consistency groups, eliminating the need for manual pattern recognition and analysis.
Solution Approach 2:
The learning process acts as an intermediary between raw write pattern data and device identification decisions. It processes the complex write pattern data, calculates write coordinate probabilities, and translates this information into actionable insights about which devices should be included in consistency groups.
Data Source
AI summary
A consistency group is defined to include a set of required devices on a set of storage systems. Write patterns on each of the required devices are monitored and write patterns on each of the other devices on the set of storage systems is monitored. Pairs of devices are formed, in which each pair includes one required device and one other device. Write patterns of the pairs of devices are compared to determine respective percentage coordinated write probabilities for pairs of devices. Write patterns of the pairs of devices are also compared to determine ratios of write operations for pairs of devices. A coordinate write probability above a threshold, or a determined ratio of write operations that occurs sufficiently frequently, is interpreted as an indication that one of the other devices should be included in the consistency group. A learning process is trained and used to analyze the write patterns.