Attribute-Only Data Reads to Avoid Retrieval and Decompression Delays
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data storage systems experience significant delays in processing read requests due to the need to retrieve and decompress data, which is not always necessary for operations like deduplication, replication, or ransomware detection, as attributes of the data are often more relevant.
Innovation Solution
Implementing attribute-only read requests that access metadata structures to retrieve attributes associated with specified data elements without retrieving the data itself, utilizing cache storage for faster access to metadata.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If a customary read request is issued to obtain data from backend storage, then the requested data can be retrieved, but significant processing delays occur due to data retrieval and decompression time
Solution Approach 1:
The patent extracts only the necessary attributes (metadata) from the data storage system without retrieving the actual data. The attribute-only read request selectively obtains information such as data length, compression ratio, or other attributes while leaving the bulk data untouched in storage, thereby eliminating the time-consuming data retrieval and decompression steps.
Solution Approach 2:
Instead of performing a complete data retrieval action, the system performs a partial action by retrieving only the attributes needed for the operation. This partial retrieval is sufficient for operations like deduplication, replication, or ransomware detection where full data access is not required, thus reducing processing time while maintaining operational effectiveness.
2Ease of operation
If data is decompressed to obtain full access, then complete data availability is achieved, but additional processing time is required for decompression
Solution Approach 1:
The patent extracts only the essential attributes needed for the storage operation without extracting or decompressing the actual data. By obtaining attributes such as compression metadata, data length, or content identifiers directly from the stored format, the system avoids the time-consuming decompression process entirely while still gathering sufficient information for operations like deduplication or replication.
3Reliability
If full data retrieval is performed for storage operations, then complete data is available for processing, but system efficiency decreases due to unnecessary data overhead
Solution Approach 1:
The patent extracts only the necessary attributes for reliable storage operations without retrieving the full data. For operations like deduplication, the system extracts attributes such as content identifiers or hash values; for replication, it extracts metadata about data characteristics. This selective extraction maintains operational reliability while dramatically improving processing efficiency by avoiding unnecessary data movement.
Solution Approach 2:
The system performs exactly the amount of data retrieval needed for each operation - no more, no less. For attribute-only operations, it retrieves only attributes; for operations requiring some data, it retrieves only the necessary portions. This precise partial action maintains reliability by getting sufficient information while maximizing productivity by minimizing unnecessary data processing.
Data Source
Figure 1
Figure 2
Figure 3~5
AI summary
A technique of obtaining attributes associated with data includes providing an attribute-only read request directed to a specified data element, accessing metadata structures that store one or more attributes associated with the specified data element, and returning the attribute (or attributes) but not the data itself in response to the request.