Job tracking method, device, computer equipment and storage medium

Abstract

The invention relates to a job tracking method, a device, computer equipment and a storage medium. The method comprises the steps that the job scheduling system obtains basic information of a target job in the job scheduling system, inputs the basic information of the target job into a preset analysis algorithm, determines a process identifier corresponding to the target job, determines process information corresponding to the target job based on the process identifier, and sends the process information to the target job. and the basic information of the target job and the process information of the target job are sent to a database. In the method, the job scheduling system can determine the process identifier corresponding to the job according to the preset analytical algorithm based on the collected basic information of the job, so that the detailed information of the process corresponding to the job is determined based on the process identifier, and the purpose of monitoring and tracking the detailed information of the process of the job in the job scheduling system is achieved; The further data mining and analysis are carried out based on the basic information and the process information of the job, so that data support is provided for optimizing job scheduling.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a job tracking method, device, computer equipment and storage medium. Background technique [0002] As an open source, fault-tolerant, and highly scalable cluster job scheduling system, SLURM can implement job scheduling for computer equipment and monitor jobs. Specifically, in the existing technology, the specified field attribute is marked in the command and script for submitting the job, such as the comment attribute, and the application name of the job in the running state is obtained through the SLURMscontrol show job command carrying the field attribute, and obtained through the linux command carrying the field attribute The process information corresponding to the job in the running state, so as to monitor the job according to the application name and process information of the job. [0003] However, if the above-mentioned prior art does not add the comment at...

AI Technical Summary

Problems solved by technology

[0003] However, if the above-mentioned existing technology does not add the comment attribute parameter in the command and script for submitting the job, the complete information of the job will not be obtained, and job monitoring is limited.

Images