Data Protection Appliance In-Line Deduplication
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data replication systems face inefficiencies due to the need for post-processing compression and decompression, which burdens CPU resources and introduces latency, especially during data replication across distances.
Innovation Solution
Implementing in-line deduplication and compression using XIO arrays and Quick Assist Technology (QAT) within a 'friendly zone' of storage arrays, where the Data Protection Appliance (DPA) offloads data processing to specialized hardware, optimizing data access and reducing resource consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If post-processing compression and decompression are used in data replication systems, then data can be stored and transmitted, but CPU resources are burdened and latency is introduced
Solution Approach 1:
The patent extracts the compression and decompression functions from the main data replication path by using a separate compression engine and dedicated hardware modules. This allows compression to occur in parallel or independently, preventing CPU bottlenecks during data replication operations.
Solution Approach 2:
The patent introduces a compression engine as an intermediary component between the data source and storage system. This intermediary handles all compression and decompression operations, shielding the main replication system from CPU-intensive operations and reducing overall system latency.
2Productivity
If post-processing compression and decompression are used in data replication systems, then data can be stored and transmitted, but latency is introduced
Solution Approach 1:
The patent implements preliminary compression of data before replication operations begin. By pre-compressing data and preparing compression buffers in advance, the system eliminates time-consuming compression operations from the critical replication path, thereby reducing overall latency.
Solution Approach 2:
The patent replaces software-based compression with hardware-based compression modules and dedicated compression engines. This substitution moves compression operations from the software CPU layer to specialized hardware, significantly reducing processing time and replication latency.
3Productivity
If hardware-based compression and decompression are implemented, then CPU load is reduced and throughput is improved, but device complexity increases
Solution Approach 1:
The patent designs the compression engine and hardware modules to serve multiple functions: compression, decompression, data validation, and replication coordination. By making these components multi-functional, the patent reduces the need for separate dedicated hardware for each function, thereby managing system complexity while maintaining high throughput.
Data Source
AI summary
A storage system comprises a storage array in operable communication with and responsive to instructions from a host. The storage array comprises a logical unit (LU), a privileged zone, a data protection appliance (DPA), and an intermediary device. The privileged zone is configured within the storage array and permits at least one predetermined process to have access to the LU. The DPA is configured to operate within the privileged zone. The intermediary device is in operable communication with the host, LU, and DPA and is configured to receive read and write instructions from the DPA and to ensure that I/O's passing through the intermediary device to at least one of the LU and the DPA, in response to the reads and writes, are formatted to a first predetermined standard, for at least one of the LU and the DPA.