Inferring Application Type via Storage I/O Patterns
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Storage administrators in data centers face challenges in determining the type of application associated with multiple storage volumes, leading to inadequate or inappropriate support due to the lack of standardized information logging methods.
Innovation Solution
A method is introduced that infers the type of application by analyzing operational characteristics such as I/O patterns and matching them with known application templates, using unsupervised learning techniques to generate labels and determine the best-fit application type.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual documentation efforts are performed by storage administrators to document grouping information of storage resources, then accuracy of application type identification is improved, but time consumption and labor requirements increase
Solution Approach 1:
The system performs automatic inference of application types by analyzing I/O operational characteristics of storage volumes, eliminating the need for manual documentation efforts. The inference engine autonomously determines application types based on stored operational data, allowing the system to serve itself rather than requiring continuous human intervention for documentation.
Solution Approach 2:
The patent replaces manual mechanical documentation processes with automated computational inference. Instead of storage administrators manually documenting grouping information, the system uses algorithms to analyze I/O patterns and automatically infer application types, substituting human cognitive work with automated mechanical processing.
2Ease of operation
If standardized information logging methods are implemented across applications, then ease of determining application type is improved, but flexibility in capturing diverse application behaviors is reduced
Solution Approach 1:
The system monitors multiple operational parameters of storage volumes including I/O operational characteristics, and dynamically adjusts the inference process based on the specific patterns observed. By changing and analyzing multiple parameters rather than relying on a single standardized log format, the system maintains flexibility while achieving ease of operation.
Solution Approach 2:
The patent introduces an intermediary inference engine that sits between the storage volumes and the application type determination process. This intermediary analyzes operational characteristics and mediates the information gathering process, making the system both easy to operate and adaptable to diverse application behaviors without requiring direct modification of logging methods.
3Measurement precision
If detailed description of associated application is captured and stored, then accuracy of support and management is improved, but data storage requirements and system complexity increase
Solution Approach 1:
The system extracts only the essential operational characteristics from storage volume operations - specifically I/O patterns and behaviors - rather than capturing comprehensive detailed descriptions of applications. By taking out only the necessary information for inference, the system reduces data storage requirements and system complexity while maintaining accuracy for support and management purposes.
Solution Approach 2:
Instead of capturing detailed application descriptions and then inferring storage characteristics, the patent inverts the approach by analyzing storage operational characteristics to infer application types. This inversion eliminates the need to store and manage complex application detail descriptions, reducing system complexity while achieving the same accuracy goal.
Data Source
AI summary
A method for inferring an application type, based on an operational characteristic I/O pattern of a storage volume. One or more processors determine at least one operational characteristic of each storage volume of a storage volume group associated with an application. One or more labels are assigned for each storage volume, based on the operational characteristics of each storage volume. At least one template is received that includes labels of storage volume characteristics of known application types. One or more processors infer a type of application associated with the storage volume group, based on a best-fit match of the aggregate labels of the storage volumes of the storage volume group to the labels included in the templates of storage volume characteristics of known application types.