Storage Device Latency Monitoring via Hardware Timestamping

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing storage devices, such as solid-state drives (SSDs), face challenges in accurately measuring and troubleshooting latency issues without recreating the operating conditions that caused the delay, as traditional methods require user intervention and are not efficient for real-time detection and analysis.

Innovation Solution

A hardware controller in the storage device is configured to record timestamps associated with read and write commands, allowing it to detect delays and store operational characteristics for analysis, enabling real-time measurement and troubleshooting of latency issues.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional latency measurement methods are used, then user intervention and manual recreation of operating conditions are required, but this increases time consumption and reduces productivity

Engineering Contradiction:
Improvelatency measurement accuracyVSAvoidtroubleshooting efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The system performs preliminary actions by continuously recording timestamps and operational characteristics in the latency monitoring cache before latency issues need to be analyzed. This pre-capture of data eliminates the need for manual recreation of operating conditions, allowing immediate analysis when latency problems occur.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system creates copies of operational characteristics and timestamps in the latency monitoring cache, preserving the actual operating conditions without requiring users to manually recreate them. These cached copies enable accurate latency analysis under the exact conditions when issues occurred.

Inventive Principle:
Principle #26Copying

2Measurement precision

If manual recreation of operating conditions is required, then detailed latency analysis can be performed, but this increases complexity and reduces ease of operation

Engineering Contradiction:
Improvelatency cause analysis accuracyVSAvoidtroubleshooting simplicity
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system performs self-service by automatically capturing and storing operational characteristics and timestamps without requiring user intervention. The latency monitoring cache autonomously records the necessary data, eliminating the burden of manual condition recreation while maintaining analysis accuracy.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system takes preliminary action by pre-recording all necessary operational parameters and timestamps before latency issues manifest. This preparation eliminates the need for complex manual recreation procedures, making troubleshooting simple and straightforward.

Inventive Principle:
Principle #10Preliminary action

3Productivity

If real-time latency monitoring is implemented, then latency issues can be detected immediately, but this increases device complexity

Engineering Contradiction:
Improvelatency detection speedVSAvoidhardware controller complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The latency monitoring cache serves multiple functions: it stores timestamps for latency calculation, preserves operational characteristics for analysis, and enables both real-time detection and historical review. This multi-functionality reduces the need for separate dedicated components, managing complexity while enabling real-time monitoring.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS10379747B2Automated latency monitoring
Publication Date: 2019.08.13 WESTERN DIGITAL TECHNOLOGIES INC
  • US10379747B2 patent drawing
  • US10379747B2 patent drawing
  • US10379747B2 patent drawing

AI summary

A method includes receiving, by a hardware controller of a storage device and from a host device, a command to read data from or write data to a non-volatile memory device of the storage device. The method includes, responsive to receiving the command: initializing, by firmware executing at a processor of the hardware controller, a command to retrieve data from or write data to the non-volatile memory device; determining, by circuit logic of the hardware controller, a time indicative of when the firmware initialized the command; determining, by the circuit logic, a time indicative of when the command terminated; and storing, by the circuit logic and at a latency monitoring cache of the storage device, a timestamp associated with the time indicative of when the command was initialized and a timestamp associated with the time indicative of when the command terminated.