Network Socket Sub-Sampling for Storage I/O Workload Capture

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current storage server technologies face challenges in efficiently collecting and analyzing workload data without disrupting the primary storage operations, requiring a mechanism that minimizes resource consumption and supports real-time analytics while maintaining high data integrity.

Innovation Solution

A method and system for selectively collecting and sub-sampling I/O request and response data from storage servers, allowing for real-time data capture and transmission over a network connection without interfering with standard I/O operations, using a data collection module that interfaces with a management console to analyze the data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If comprehensive workload data is collected from storage servers, then data integrity and analytics quality are improved, but storage server resource consumption and overhead increase

Engineering Contradiction:
Improveworkload data integrityVSAvoidstorage server resource consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

A network socket acts as an intermediary between the storage server and the data collection system. The storage server sends workload data through the network socket without requiring direct integration or additional processing resources on the storage server itself, thereby maintaining data integrity while minimizing server overhead

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The data collection functionality is extracted from the storage server's core processing path. By using network sockets for data transmission, the workload monitoring is separated from the primary storage operations, allowing comprehensive data collection without impacting storage server performance

Inventive Principle:
Principle #2Taking out (Extraction)

2Speed

If real-time workload data is captured continuously, then analytics responsiveness is improved, but resource overhead and system impact increase

Engineering Contradiction:
Improveanalytics responsivenessVSAvoiddata collection system complexity
Core Design Contradiction:
SpeedVSDevice complexity

Solution Approach 1:

The system uses periodic sub-sampling of workload data instead of continuous capture. Network sockets enable periodic data transmission at optimized intervals, providing responsive analytics while reducing the complexity and resource demands of continuous monitoring

Inventive Principle:
Principle #19Periodic action

3Productivity

If selective data collection is implemented, then resource efficiency is improved, but data completeness may be compromised

Engineering Contradiction:
Improvedata collection efficiencyVSAvoidworkload data completeness
Core Design Contradiction:
ProductivityVSLoss of information

Solution Approach 1:

The system implements sub-sampling of workload data, collecting a representative partial set of I/O requests and responses. This partial action approach provides sufficient data for effective analytics and tuning while maintaining high collection efficiency, avoiding the need to capture every single data point

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP3274810B1Methods and systems for real-time activity tracing in a storage environment
Publication Date: 2021.01.13 NETAPP INC
  • EP3274810B1 patent drawingFigure 1
  • EP3274810B1 patent drawingFigure 2A
  • EP3274810B1 patent drawingFigure 2B

AI summary

Systems and. methods for: efficient input/output (I/O) workload, capture are provided. For example, in one aspect, a machine implemented method includes: opening a network socket for listening to a connection request from a computing device; accepting the connection request from the computing device over the network, socket; enabling selective data collection based on network connection with the computing device over the network socket, where the network connection based selective data collection includes obtaining information regarding a plurality of input/output (I/O) requests and responses and performance information of a storage server for processing the I/O requests sub-sampling the network connection based collected data; and sending at least a portion of the network connection based collected data over the network socket connection to : the computing device.