Compressed Data Replication Without Decompression Overhead
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional data replication processes consume significant computing resources and bandwidth due to the need to decompress and recompress data, as the size of compressed data is unknown, leading to failed read commands and inefficient data transmission.
Innovation Solution
Implementing a read compressed data command that specifies the uncompressed data size, allowing compressed data to be transmitted and stored in its original form, reducing the need for decompression and conserving resources and bandwidth.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If compressed data is decompressed before transmission, then read commands can successfully execute, but computing resources and bandwidth are significantly consumed
Solution Approach 1:
Instead of the conventional approach where compressed data is decompressed before transmission, the patent inverts the process by transmitting compressed data directly without decompression. The initiator sends a read command specifying the uncompressed data size, and the storage array returns the compressed data in its original compressed form, eliminating the need for decompression and recompression operations.
Solution Approach 2:
The patent changes the parameter specification in read commands from block size to uncompressed data size. This parameter change allows the system to correctly identify and retrieve the appropriate amount of compressed data without needing to decompress it first, enabling direct transmission of compressed data while maintaining read command success.
2Ease of operation
If compressed data is transmitted in uncompressed form, then data can be easily read and transmitted, but bandwidth consumption increases significantly
Solution Approach 1:
The patent inverts the conventional data transmission approach by sending compressed data directly without decompression. The storage array transmits data in its compressed form, and the initiator receives and processes it as compressed data, eliminating the bandwidth-wasting decompression step while maintaining operational simplicity through the modified read command protocol.
3Quantity of substance
If the size of compressed data is unknown, then data can be stored efficiently, but read commands fail because the amount of data does not correspond to the requested amount
Solution Approach 1:
The patent changes the read command parameter from block size to uncompressed data size. This allows the initiator to specify how much uncompressed data it expects, and the storage array can correctly identify and return the corresponding compressed data without needing to know its compressed size in advance, resolving the mismatch between requested and actual data amounts.
Solution Approach 2:
The patent introduces an intermediary mapping relationship between uncompressed data size and compressed data identification. The system uses the uncompressed size as a mediator to correctly identify and retrieve the corresponding compressed data, bridging the gap between the initiator's knowledge of uncompressed size and the storage array's storage of compressed data.
4Quantity of substance
If data is replicated in compressed form, then bandwidth is conserved during transmission, but conventional protocols cannot handle the unknown size of compressed data
Solution Approach 1:
The patent modifies the protocol parameter from block size to uncompressed data size in read commands. This simple parameter change enables conventional protocols to handle compressed data replication effectively, allowing the system to transmit and replicate compressed data while conserving bandwidth without requiring complex new protocols.
Data Source
AI summary
Systems and methods for replicating data are disclosed. Data stored in a compressed form on a source storage array or device can be read and transmitted to a destination storage array or device. The replication of data is achieved without having to decompress the data.