A dynamically reconfigurable hash computing architecture and its method, key-value storage system

Abstract

The present application discloses a dynamically reconfigurable Hash computing architecture and a method thereof, and a Key-Value storage system. The Hash computing architecture includes: a CPU module,an FPGA module and a memory; the CPU module is configured to divide a calculation task according to the number of processing units of the FPGA module and dynamically reconstruct an operation mode ofthe FPGA module according to different parts of the load, send the calculation task data to the FPGA module, store the calculation task data to a memory, monitor a task state of the FPGA module and obtain a task result at the end of the task; the memory is configured as a shared memory unit of the CPU module and the FPGA module. The FPGA module is configured to dynamically reconstruct according tothe received operation mode, obtain the calculation task data stored in the memory according to the received calculation task, perform hash calculation processing according to the calculation task data to obtain the task result, and return the task state and the task result to the CPU module at the same time. The method and a key-Value storage system are based on the dynamically reconfigurable Hash computing architecture.

Description

technical field [0001] The disclosure belongs to the technical field of Key-Value storage systems, and in particular relates to a dynamically reconfigurable Hash computing architecture and method thereof, and a Key-Value storage system. Background technique [0002] Key-Value storage systems are widely used in large data centers, such as e-commerce, social networking, and online search. Compared with traditional SQL databases, the Key-Value storage system has the advantages of fast speed, strong scalability, and easy portability. The Key-Value database is mainly used as a cache layer in the data center to solve the problem of slow permanent storage at the back end of the data center. As the scale of the data center continues to expand and the access frequency of the required data continues to increase, the Key-Value storage system used as the data center to manage data access has a more important impact on the performance of the data center to provide services. [0003] Th...

AI Technical Summary

Problems solved by technology

[0008] Aiming at the deficiencies in the prior art and solving the problem of how to implement a high-efficiency Hash acceleration computing unit in the prior art so as to further improve the performance of the Key-Value storage system, the present invention proposes a dynamically reconfigurable Hash computing architecture Its method and Key-Value storage system effectively improve the overall performance of the Key-Value storage system and enhance the scalability of the Key-Value storage system through the designed high-efficiency and dynamically reconfigurable Hash computing architecture

Images