SSD Background Operation Scheduling for Read Latency

Solution Overview

Problem

Solid state storage devices (SSDs) experience varying read latencies due to background operations like erase and garbage collection, leading to inconsistent performance and increased latency for read requests, which can negatively impact dependent applications and consume system resources.

Innovation Solution

A background operations manager component in the storage server I/O controller generates a schedule for SSD background operations, allowing for proactive management of these operations to minimize read latency by reconstructing data from available SSDs when necessary, reducing the time SSDs are unavailable for read requests.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If background operations (erase and garbage collection) are performed on SSDs, then storage maintenance and data reliability are improved, but read latency increases and becomes inconsistent

Engineering Contradiction:

Improvestorage maintenanceVSAvoidread latency

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by scheduling background operations during specific time windows and proactively migrating data before these operations occur. The storage server anticipates when background operations will affect data availability and pre-migrates data to unaffected SSDs, eliminating the need for hosts to wait for background operations to complete.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The storage server acts as an intermediary between hosts and SSDs. It receives read requests from hosts, checks whether affected SSDs will be unavailable due to scheduled background operations, and proactively migrates data to unaffected SSDs before the background operations begin, thereby mediating the conflict between background maintenance and read access.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If background operations are performed on SSDs, then data maintenance is improved, but latency consistency deteriorates

Engineering Contradiction:

Improvedata maintenanceVSAvoidlatency consistency

Core Design Contradiction:

ReliabilityVSStability of the object's composition

Solution Approach 1:

The system performs preliminary actions by scheduling background operations during specific time windows and proactively migrating data before these operations occur. The storage server anticipates when background operations will affect data availability and pre-migrates data to unaffected SSDs, eliminating the need for hosts to wait for background operations to complete.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The storage server continuously monitors the status of SSDs and their scheduled background operations. When a read request is received, the server checks whether the target SSD will be unavailable due to background operations and takes appropriate action, creating a feedback loop that maintains latency consistency.

Inventive Principle:

Principle #23Feedback

3Loss of time

If hosts use large buffers to accommodate slow SSD responses, then read latency variability is accommodated, but system resource utilization deteriorates

Engineering Contradiction:

Improveread latency variabilityVSAvoidsystem resource utilization

Core Design Contradiction:

Loss of timeVSProductivity

Solution Approach 1:

The system performs preliminary actions by scheduling background operations during specific time windows and proactively migrating data before these operations occur. The storage server anticipates when background operations will affect data availability and pre-migrates data to unaffected SSDs, eliminating the need for hosts to wait for background operations to complete.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS10241722B1Proactive scheduling of background operations for solid state drives

Publication Date: 2019.03.26 PAVILION DATA SYST

AI summary

A processing device of a storage server that manages a plurality of SSDs receives to read data. The processing device determines a first SSD of the plurality of SSDs on which the data is stored, and determines that the first SSD is performing a background operation. The processing device determines whether the data is located on a block of the first SSD that will be unavailable during the background operation. Responsive to determining that the data is located on the block of the first SSD, the processing device reconstructs the data based on additional data on one or more remaining SSDs of the plurality of SSDs. The processing device then generates a response to the request that includes the data.