A weight-based application resource scheduling device and method

Abstract

The invention discloses a weight-based application resource scheduling device and method, belonging to the technical field of big data application processing. The resource scheduling device of the present invention includes an application request receiving module, a resource prediction module, a process acquisition module, a resource scheduling module and a recovery module. The resource prediction module is used to obtain the load characteristics of the I / O application request and calculate the I / O application load. Read and write operation threshold, a process acquisition module, used to obtain the processed read and write operation value of process n to obtain the nth process read and write operation value (n≥1); resource scheduling module, used for according to the I / O application load The read and write operation threshold and the acquired read and write operation value of the nth process are used for process resource scheduling. The scheduling device and method of the present invention determine the weights and resources that need to be allocated to each process by comparing the read and write operation thresholds of different I / O application loads and the obtained read and write operation values ​​processed by the process, so that the application load requests can be processed efficiently and reasonably , improve disk resource utilization.

Description

technical field [0001] The invention relates to a weight-based application resource scheduling device and method, and belongs to the technical field of big data application processing. Background technique [0002] Generally speaking, since the data center carries a large number of cloud computing applications, its performance not only affects the application performance and user experience, but also greatly affects the application service capability of the data center. For various applications in the data center, one of the most common applications is the access of a large number of random small files, such as e-commerce transactions, social media applications, etc. This type of application is characterized by a large number of accesses and high concurrency. Generates a lot of random I / O and mostly small file transfers. For example, most of the user pictures on Facebook and product pictures on e-commerce applications such as Taobao are small files of tens of KB. Not only ...

AI Technical Summary

Problems solved by technology

However, the virtual machines that host various applications in cloud computing data centers are generally defined by users themselves, and there is no special treatment for resource characteristics. As a result, limited disk resources cannot be fully utilized when specific applications access the data center.

Images