A method to reduce data copying between multiple processes under linux

Abstract

The invention relates to the technical field of computer application, in particular to a method for reducing data copy among multiple processes under the linux. The method includes the following steps that firstly, a user applies for a shared storage organization; secondly, the shared storage organization is divided into multiple storage pools of different sizes and the storage pools are divided into multiple storage blocks; thirdly, a process A applies for a certain storage block, an application identification is an occupied identification and the count of the user in the head domain of the storage block a is 1; fourthly, the count of the user is added by one every time one more process applies the data in the storage block a; fifthly, the count of the user is subtracted by one every time the number of processes applying the data in the storage block a is reduced by one until the count of the user is zero, the application identification is an idle identification and the storage block a is returned to the corresponding storage pool. According to the method for reducing data copy among multiple processes under the linux, zero-copy data communication among the processes can be achieved, one-time data organization is achieved, multiple copying of the data is not needed and the data can be directly applied to the processes.

Description

technical field [0001] The invention relates to the field of computer application technology, in particular to a method for reducing data copying between multiple processes under linux. Background technique [0002] The Linux system is a system based on virtual memory. Its process spaces are independent and invisible to each other. Each process independently manages its own memory space. Data interaction between processes needs to be done through message queues, shared memory, pipes, files, etc. These methods either need to copy data such as message queues, pipes, etc., or even copy data multiple times to make the data organized in a process in a process. It can be seen in another process, and each additional process needs to copy the data once more, which is less efficient; or only two processes can share data, such as ordinary shared memory, which is usually used for each Two processes open up a memory segment as a shared memory space to complete the communication between...

AI Technical Summary

Problems solved by technology

Data interaction between processes needs to be done through message queues, shared memory, pipes, files, etc. These methods either need to copy data such as message queues, pipes, etc., or even copy data multiple times to make the data organized in a process in a process. It can be seen in another process, and each additional process needs to copy the data once more, which is less efficient; or only two processes can share data, such as ordinary shared memory, which is usually used for each Two processes open up a memory segment as a shared memory space to complete the communication between the two processes. This shared memory cannot be reused by multiple processes, which is a serious waste of resources.

Images