SSD Controller Backup Power Management for Data Integrity

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Solid State Drives (SSDs) face challenges in persistently storing volatile data during sudden power outages, as capacitive backup power supplies can only provide power for a short time, and existing solutions may not ensure complete data integrity during error correction and write operations.

Innovation Solution

The SSD employs a controller with a backup power source and a management system that prepares erased free blocks in advance, allowing for immediate writing to nonvolatile memory during outages, interrupting error correction and garbage collection processes, and using a read-modify-write cycle to ensure data safety with a low-capacity backup power source.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a capacitive backup power supply is used, then the SSD can guard against data loss during outages, but the backup power can only be supplied for an extremely short time (10 ms to 0.1 sec)

Engineering Contradiction:
Improvedata integrity during outageVSAvoidbackup power supply time
Core Design Contradiction:
ReliabilityVSDuration of action of moving object

Solution Approach 1:

The system performs preliminary actions by pre-erasing free blocks and preparing them in advance before an outage occurs. When an outage happens, these pre-prepared blocks are immediately available for writing volatile data without requiring time-consuming erasure operations during the limited backup power window.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system skips time-consuming operations during outage recovery by interrupting error correction and garbage collection processes. It rushes through the essential data saving operation by directly writing volatile data to pre-prepared blocks, completing the critical function within the brief backup power availability.

Inventive Principle:
Principle #21Skipping (Rushing through)

2Reliability

If error correction and garbage collection processes are performed during normal operation, then data integrity is maintained, but these processes consume time that may not be available during sudden outages

Engineering Contradiction:
Improvedata integrityVSAvoidtime for data processing during outage
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system extracts and separates the critical data saving function from time-consuming auxiliary processes. During an outage, it takes out only the essential operation of writing volatile data to pre-prepared blocks, while leaving error correction and garbage collection to be performed later when full power is restored.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The system performs partial action by completing only the essential data persistence function during the limited outage window, rather than attempting to complete all maintenance tasks. It performs excessive preparation in advance by pre-erasing multiple free blocks so that sufficient blocks are available immediately when needed.

Inventive Principle:
Principle #16Partial or excessive action

3Reliability

If volatile data is written to nonvolatile memory during an outage, then data loss is prevented, but the write operation must be completed within a very short time window

Engineering Contradiction:
Improvedata persistenceVSAvoidwrite speed requirement
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system performs preliminary preparation by pre-erasing free blocks and maintaining a pool of ready-to-write blocks. This eliminates the time required for block erasure during the critical outage window, allowing immediate writing of volatile data to nonvolatile memory within the brief backup power availability.

Inventive Principle:
Principle #10Preliminary action

4Quantity of substance

If a small capacity backup power source is used, then the SSD design is more compact and cost-effective, but there is insufficient time to complete data writing operations

Engineering Contradiction:
Improvebackup power capacityVSAvoidcomplete data writing
Core Design Contradiction:
Quantity of substanceVSReliability

Solution Approach 1:

The system performs preliminary actions by pre-erasing free blocks and maintaining a ready pool of blocks before an outage occurs. This advance preparation ensures that when a small-capacity backup power source activates, immediately writable blocks are available, allowing complete data writing operations within the limited energy capacity.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system rushes through the data writing process by skipping time-consuming operations like block erasure and error correction during the outage. It focuses exclusively on the essential write operation to pre-prepared blocks, completing the critical data persistence function within the brief window provided by the small backup power source.

Inventive Principle:
Principle #21Skipping (Rushing through)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This solution enables the SSD to securely store volatile data and associated address conversion information during power outages, maintaining write performance and reducing recovery time even with a small backup power capacity, thus preventing data loss.

Implementation Method 1

the memory device is provided with a backup power source

Methodology Applied
Scientific EffectBattery (electricity): Battery (electricity)

Data Source

PatentUS9996278B2Memory device, control method for the memory device, and controller
Publication Date: 2018.06.12 KIOXIA CORP
  • US9996278B2 patent drawing
  • US9996278B2 patent drawing
  • US9996278B2 patent drawing

AI summary

During normal power operation, an erased free block is prepared in nonvolatile memory so that at least one erased free block is continuously available as a standby block. If a power failure occurs, volatile data and its address conversion information are written into the standby block in the nonvolatile memory.