I/O service quality maintaining method for heterogeneous storage cluster system

Abstract

The invention discloses an I / O service quality maintaining method for a heterogeneous storage cluster system. The method comprises the following steps that firstly, storage resources in a quick storage partition of the heterogeneous storage cluster system are divided into a plurality of storage resource packets, correlation does not exist in the I / O process among the storage resource packets, and the performance of the different storage resource packets cannot be affected during the respective I / O process; secondly, when the heterogeneous storage cluster system receives jobs, a current job is allocated to a storage resource packet selected from the storage resource packets according to the output performance requirement level of I / O of the current job and the states of the storage resource packets, and the states of the storage resource packets are updated. The I / O service quality maintaining method has the advantages that the I / O service performance is high, the I / O bandwidth requirement is low, the I / O service quality is good, and the method is especially suitable for I / O intensive job.

Description

technical field [0001] The invention relates to the technical field of I / O service quality maintenance in a heterogeneous storage cluster system in a scene sensitive to I / O performance, in particular to an I / O service quality maintenance method for a heterogeneous storage cluster system. Background technique [0002] Storage system is an important part of parallel computer system. With the continuous expansion of the scale of parallel computer systems and the scale of application processing data, the performance of storage systems has become an important factor that affects and restricts the actual application performance of the system. In order to ensure the execution efficiency of I / O-intensive applications such as massive data analysis, heterogeneous storage architectures are often used in cluster systems, that is, storage systems are divided into fast storage partitions and slow storage partitions, and high-speed storage devices such as solid-state storage are deployed i...

AI Technical Summary

Problems solved by technology

At present, the real-time requirements of computing operations are gradually increasing. Whether the job can be completed within the predetermined time will have a serious impact on the effectiveness of job execution results, and the data input and output process is an important part of computing operations. If this process Performance requirements cannot be guaranteed, which can have a serious impact on the success or failure of computing jobs

Therefore, under the architecture of the existing heterogeneous storage cluster system, how to ensure the I / O performance of the job has become a key issue affecting the availability of the existing high-performance computing system

Images