Storage Device Write Command Ordering for Data Pre-fetching

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In SATA systems and similar storage interfaces, write commands are executed in a random order, leading to inefficiencies as devices connected to storage devices cannot pre-fetch data effectively without using extensive memory resources, which is costly and does not necessarily improve performance.

Innovation Solution

A system, method, and computer program product that identify and order a plurality of write commands associated with a storage device, allowing the device to pre-fetch data in a determined order known to the device, thereby optimizing data access and reducing resource usage.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If write commands are executed in random order in SATA systems, then device complexity is reduced, but data access efficiency deteriorates and memory resources are wasted

Engineering Contradiction:

Improvedata access efficiencyVSAvoidcommand ordering complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by determining and communicating the execution order of write commands to the device before the commands are actually executed. This allows the device to pre-fetch data in advance according to the known command sequence, improving data access efficiency without requiring complex real-time coordination during command execution.

Inventive Principle:

Principle #10Preliminary action

2Reliability

If devices pre-fetch data for all write commands, then data availability is improved, but memory resource consumption increases significantly

Engineering Contradiction:

Improvedata availabilityVSAvoidmemory resource consumption

Core Design Contradiction:

ReliabilityVSQuantity of substance

Solution Approach 1:

The patent applies partial action by having devices pre-fetch data only for the next needed command rather than all commands. The device receives information about the ordered sequence of write commands and pre-fetches data selectively based on this knowledge, avoiding the excessive memory consumption of pre-fetching all data while ensuring data availability for upcoming operations.

Inventive Principle:

Principle #16Partial or excessive action

3Productivity

If write commands are executed in random order, then ease of operation is improved, but performance is not improved due to mismatched data pre-fetching

Engineering Contradiction:

Improvewrite operation performanceVSAvoidcommand execution control

Core Design Contradiction:

ProductivityVSEase of operation

Solution Approach 1:

The patent introduces an intermediary mechanism where the storage device receives and processes command order information from the host system. This intermediary layer allows the device to understand the execution sequence without requiring the host to directly control command execution, maintaining ease of operation while enabling performance optimization through ordered data pre-fetching.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS10019200B2Ordering a plurality of write commands associated with a storage device

Publication Date: 2018.07.10 SEAGATE TECH LLC

AI summary

Methods, systems, and computer-readable storage media for identifying randomly ordered write commands by a storage device enabled to communicate with a drive compatible with a storage protocol enabling command execution in random order. The storage device may determined a particular order of the identified write commands. The write commands in the determined particular order may be arranged by the storage device. The storage device may send the ordered write commands to the drive. The ordered write commands may allow for pre-fetching of data associated with the write commands by the drive.