Storage System Partial Data Decompression for Write Requests

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing storage systems with compression functions face performance degradation due to unnecessary decompression processing, as they often decompress entire compression units even for partial read or write requests, leading to inefficiencies in data access.

Innovation Solution

The solution involves optimizing the storage system to only decompress the specific portions of compressed data corresponding to the range of the read or write request, using advanced compression algorithms and management tables to determine the necessary decompression range, thereby reducing overhead and enhancing performance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If the entire compression unit is decompressed for partial read or write requests, then the data can be accessed, but unnecessary decompression processing is performed leading to performance degradation

Engineering Contradiction:

Improvedata access performanceVSAvoiddecompression processing time

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The compression unit is divided into multiple sub-compression units based on the request range. Only the specific sub-compression unit containing the requested data is decompressed, rather than decompressing the entire compression unit. This segmentation allows selective decompression of only the necessary portion, improving access performance while reducing unnecessary processing time.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The requested data is extracted and processed separately from the rest of the compression unit. By identifying the specific range requested and extracting only that portion for decompression, the system avoids the overhead of decompressing unrelated data, thereby reducing processing time while maintaining data access capability.

Inventive Principle:

Principle #2Taking out (Extraction)

2Quantity of substance

If the compression function divides data into given lengths, then the compression capacity is reduced, but the access performance deteriorates due to overhead of decompression processing

Engineering Contradiction:

Improvestored data capacityVSAvoidaccess performance

Core Design Contradiction:

Quantity of substanceVSProductivity

Solution Approach 1:

The compression unit is segmented into smaller sub-compression units based on the actual request range. This allows the system to maintain the benefits of compression for the entire data set while enabling selective decompression of only the relevant segments, thus preserving storage efficiency while improving access performance.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Instead of decompressing the entire compression unit (excessive action), the system performs partial decompression only on the sub-compression unit containing the requested data. This partial action reduces the decompression overhead while still providing full access to the needed information.

Inventive Principle:

Principle #16Partial or excessive action

3Ease of operation

If the whole data is decompressed for update requests, then the update data can be overwritten, but the update performance deteriorates due to overhead of decompression and compression processing

Engineering Contradiction:

Improveupdate capabilityVSAvoidupdate performance

Core Design Contradiction:

Ease of operationVSProductivity

Solution Approach 1:

The update operation is segmented to affect only the specific sub-compression unit containing the update data. The system decompresses only the relevant sub-compression unit, applies the update, and recompresses only that segment, rather than processing the entire compression unit. This segmentation dramatically reduces the overhead of decompression and compression processing while maintaining full update capability.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The update data is extracted and applied to the specific location within the decompressed sub-compression unit. After the update is applied, only the modified portion is recompressed and written back, rather than recompressing the entire data set. This extraction approach minimizes the processing overhead while ensuring data integrity.

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentUS9183217B2Method for decompressing data in storage system for write requests that cross compressed data boundaries

Publication Date: 2015.11.10 HITACHI VANTARA LTD

AI summary

The present invention aims at improving the performance of a compression function in a storage system, and solves the prior art problem of having to decompress a whole compression unit even if a read request or a write request targets only a portion smaller than the compression unit, causing increase of overhead of decompression processing and elongation of processing time, and deteriorating performance. The present invention prevents unnecessary decompression processing and reduces the overhead of processing by suppressing the range of decompression processing to a minimum portion according to the relationship between the read/write request range and the compression unit.