A method for fault-tolerant management of a multi-core operating system
A technology of operating system and management method, applied in the field of operating system management of multi-core processors of embedded systems, can solve the problem that the system cannot perform fault-tolerant management, avoid the uncertainty of asynchronous events and data access conflicts, and reduce algorithm overhead , the effect of good versatility
Active Publication Date: 2018-03-09
BEIJING INST OF CONTROL ENG
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
To avoid the problem that the system cannot perform fault-tolerant management due to the failure of the processor core where the monitoring thread is located in the prior art, and improve the fault-tolerant capability of the system
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0019] The invention provides a fault-tolerant management method for a multi-core operating system based on shared memory. The method enables the processor cores to monitor each other's states through an inter-core fault detection matrix. Work (including tasks and interrupts) is migrated to the healthy processor core and continues to run. The method can quickly detect a failed processor core, and can also ensure the normal operation of the system in extreme cases where only one core can work normally. The steps are as follows:
[0020] (1) Construct a global task list and an n×n inter-core fault detection matrix (n is the number of processor cores) in the system.
[0021] (2) Make a scheduler instance run on each processor core. The basic function of each scheduler instance is to start the global task from the global task according to the task scheduling algorithm when an interrupt occurs or the local (the processor core) has a task status change. Pick a ready task from the ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The present invention provides a fault-tolerant management method for a multi-core operating system, which mainly includes constructing an n×n inter-core fault detection matrix, and each processor core periodically detects whether other processor cores in the system fail by using the inter-core fault detection matrix; wherein , the fault detection of each processor core includes: at the beginning of each timing monitoring cycle, the elements in the corresponding column k of each processor core in the inter-core fault detection matrix are set to TRUE; at the end of each timing monitoring cycle , each processor core checks the elements in the corresponding row j in the matrix, if one of the elements ejk is not TRUE, it is considered that the processor core k corresponding to the column may have failed, and finally the element in row j All cleared. Each processor core of the system of the present invention has the ability to perform fault detection on other cores in the processor, which greatly improves the system fault tolerance.
Description
technical field [0001] The invention relates to the field of operating system management methods for embedded system multi-core processors, in particular to a multi-core operating system fault-tolerant management method. Background technique [0002] Using multi-core processors in embedded systems is an effective way to improve system computing power and reliability. By dividing the computing task into multiple threads that can be executed in parallel and distributing them to run on different processor cores, the computing speed can be greatly improved. The reliability of the system can be improved by enabling multiple processor cores to execute the same task synchronously and output the operation results after voting. [0003] During the operation of a multi-core system, when a processor core has a non-transient failure, the system needs to be able to sense the failure and reschedule the threads on the failed core to run on other processor cores. Among them, how to make t...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F11/07
Inventor 王婧彭飞龚健吴一帆华更新刘鸿瑾许娜徐建
Owner BEIJING INST OF CONTROL ENG