Performance pressure measurement method and system for distributed storage system and related components

Abstract

The invention discloses a performance pressure measurement method and system for a distributed storage system and related components, and the method comprises the steps: obtaining configuration information needed in a system environment, and initializing a test variable according to the configuration information; generating a plurality of test queues according to the test command, and executing the following steps on each test queue to obtain a performance pressure test result: transferring operation requests in the test queues to an operation queue; executing the operation request in the operation queue, and deleting the completed operation request from the operation queue; when the operation queue is empty, judging whether the test queue is empty or not; and if not, returning to execute the process of transferring the operation request in the test queue to the operation queue. The lightweight performance pressure measurement method is designed for engine characteristics of the local storage system, the method is easy to implement, the performance bottleneck of the storage system and the error position of the system can be quickly positioned, the high-performance value under the ultimate pressure of the system can be obtained, and a reference basis is provided for optimizing the engine of the storage system.

Description

technical field [0001] The invention relates to the field of system testing, in particular to a performance pressure testing method, system and related components of a distributed storage system. Background technique [0002] At present, distributed storage systems have been widely used in fields such as cloud computing and big data analysis. Distributed storage systems with different hardware specifications will appear in different scenarios and requirements, which can be roughly divided into: slow device storage, mixed slow and high speed Device storage and high-speed device storage. Under different hardware configurations, how to give full play to the optimal performance of the hardware is the goal of performance tuning of the distributed storage system. However, due to the stability, data security, and scalability requirements of the distributed storage system, the system processing logic is relatively complex, so that when analyzing the performance bottleneck of the sy...

AI Technical Summary

Problems solved by technology

However, due to the stability, data security, and scalability requirements of the distributed storage system, the system processing logic is relatively complex, so that when analyzing the performance bottleneck of the system, the system cannot be simply decoupled into different parts for performance testing. Conventional IO (Input / Output, input / output) testing tools, such as FIO, often fail to determine the best performance of the storage system when testing the performance of the storage system. At the same time, the amount of program engineering in the test is large, the error rate is high, and the problem is difficult to locate, resulting in performance testing. The efficiency is low, the effect is not ideal

Images