Distributed storage system parameter adjusting method and device, electronic equipment and medium

Abstract

The invention discloses a distributed storage system parameter adjusting method and device, equipment and a medium. The distributed storage system parameter adjusting method comprises the steps of: acquiring a neural network model which is created in advance according to data obtained by interaction between a vdbench client and a storage cluster and is used for evaluating a time delay size; determining actual internal state data of the current storage cluster, wherein the actual internal state data comprises interface time delay data of ganesha; and searching a target parameter enabling an output value to be maximum according to the actual internal state data by utilizing the neural network model, and adjusting parameters of the current storage cluster according to the target parameter, wherein the output value is in negative correlation with the time delay of a client. According to the distributed storage system parameter adjusting method and the device, the neural network model for evaluating the time delay can be created, the actual internal state data of the storage cluster can be obtained, the target parameter capable of maximizing the output value can be searched based on thecreated neural network model, the target parameter capable of minimizing the time delay can be obtained so as to adjust and optimize the storage cluster, and the automatic adjustment and optimizationof the storage cluster can be realized.

Description

technical field [0001] The present application relates to the technical field of distributed storage, and more specifically, to a parameter adjustment method and device of a distributed storage system, an electronic device, and a computer-readable storage medium. Background technique [0002] There are a large number of adjustable parameters in the current storage system, and the adjustable range of each parameter is very large, and modifying these parameters will often have different effects on the performance of the system. Usually the default parameter configuration is provided by the supplier, and the combination of these parameter values ​​is generally not the optimal parameter set. Even adjusting a small number of parameter values ​​can increase the energy consumption and performance efficiency of the system by more than several times. [0003] Traditional parameter adjustment is done by system administrators based on their professional knowledge and experience. Due t...

AI Technical Summary

Problems solved by technology

[0003] Traditional parameter adjustment is done by system administrators based on their professional knowledge and experience. Due to the increasing complexity of storage systems, manual parameter adjustment cannot adapt to large-scale storage systems, and manual parameter adjustment cannot be monitored around the clock As well as high labor costs and other shortcomings, there is an urgent need to study automatic tuning methods for storage systems

Images