Process migration method, computing device and storage medium

Abstract

The invention discloses a process migration method, a computing device and a storage medium, and the process migration method comprises the following steps of calculating the predicted running time of each process in a processor according to the running information of the processes; according to the predicted running time of the processes, determining the process with the predicted running time smaller than a running time threshold value as a short running process; acquiring the running information of the processor, and determining whether the short running process is used as a to-be-migrated process according to the running information of the processor; if the short running process is the to-be-migrated process, determining a target processor for migrating the to-be-migrated process according to the running information of other processors; and migrating the to-be-migrated process to the target processor for operation. According to the present invention, the migration of all the short running processes can be avoided, the migration frequency of the short running processes is reduced, the problem of invalidation of cache and memory affinity caused by migration is reduced, and it is guaranteed that when the short running processes are migrated, the system performance can be improved, and the use efficiency of the processor is improved.

Description

technical field [0001] The invention relates to the field of processors, in particular to a process migration method, computing equipment and storage media. Background technique [0002] With the development of computer technology, in order to further improve the working efficiency of the processor in the computer equipment and the processing speed of the computer to the task, a multi-core load balancing mechanism will be adopted in the process of executing many tasks. The multi-core load balancing mechanism refers to migrating processes between processors. Specifically, a scheduling algorithm (such as the PELT algorithm) is periodically used to calculate the load of each process in the processor scheduling queue to obtain the processor load. The load of a processor is the sum of the loads of all processes in the scheduling queue of the processor. When the kernel finds that the load distribution on each processor is significantly different, it will migrate the process from ...

AI Technical Summary

Problems solved by technology

In the existing technology, the load of each process is calculated by the method of time decay, and the running time of the short execution cycle process is very short, and the CPU is reselected according to the load when waking up, which will cause frequent migration of processes between CPUs.

Frequent migration of processes will increase the load of the system, invalidate the cache of the process, increase the probability of accessing memory across NUMA nodes, increase the number of memory pages migrated by the NUMA automatic balancing mechanism, and reduce system performance

Images