Method for improving real-time performance of Linux operating system application program based on multi-core CPU

By reallocating tasks on a multi-core CPU and optimizing the Linux kernel, the real-time performance of traditional Linux systems in industrial control scenarios has been addressed, achieving low-latency interrupt response and system stability, thus meeting the real-time requirements of power distribution automation.

CN122132148AActive Publication Date: 2026-06-02ZHUHAI FEISEN POWER TECH CO LTD
4 Cites 0 Cited by

Patent Information

Application Number
CN202610591671.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-04-30
Publication Date
2026-06-02
Estimated Expiration
2046-04-30

AI Technical Summary

Technical Problem

Traditional Linux operating systems lack real-time performance in industrial control scenarios, especially in power distribution automation applications where they cannot meet the minimum interrupt response latency requirement of less than 10 microseconds. They suffer from problems such as kernel non-preemption, interrupt masking, spinlock blocking, scheduler design nondeterminism, priority inversion, and memory allocation blocking.

Method used

By reallocating tasks across a multi-core CPU, non-real-time critical tasks, real-time critical tasks, and sub-real-time critical tasks are assigned to different cores. The interrupt priority and kernel preemption mode of each core are configured, and the Linux kernel is optimized using boot parameters and driver modules to achieve physical isolation and deterministic scheduling of tasks.

Benefits of technology

It significantly reduced system costs, simplified the development process, improved system real-time performance and stability, met the application scenarios with extreme real-time requirements such as distribution network automation, and ensured strict priority guarantee and predictable delay of critical tasks.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a method for improving the real-time performance of an application program of a Linux operating system based on a multi-core CPU (Central Processing Unit), which comprises the following steps of: in a system starting stage, redistributing each core task in the multi-core CPU by modifying starting parameters of a Linux core, and centrally distributing a basic running task of the Linux system to a zeroth core for running; when a target application program creates a task, the task affinity is set by calling a system function according to the real-time requirement of the task; distributing the non-real-time key task to the first core for operation; distributing the real-time key task to a second core for operation; and distributing the secondary real-time key task to the third core for operation. According to the method, different tasks are distributed by utilizing different cores of the multi-core CPU, so that the response delay time for specific interruption with strict real-time requirements in the Linux system is effectively shortened, the real-time performance of equipment is improved, and the real-time requirements in the fields of distribution network automation and the like are met.
Need to check novelty before this filing date? Find Prior Art