Easy extending page architecture based on Linux large page memory

Abstract

The invention discloses an easy extending page architecture based on a Linux large page memory. The easy extending page architecture comprises the large page memory and an interface function for calling the large page memory, wherein the large page memory is divided into a plurality of nodes; each node is divided into a plurality of partitions; each partition consists of a plurality of 2M large pages connected into a whole in a double linked list form; and the interface function comprises an application function used for obtaining a single large page, a release function used for releasing the large page, a locking function used for occupying the large page and preventing other processes from accessing, and an unlocking function used for recovering the freedom of the large page. The architecture does not share a buddy system with a small page file system, is independently managed and can carry out decoupling with a Linux kernel, and the independence of memory storage calling is improved.

Description

technical field [0001] The invention belongs to the technical field of communication, and in particular relates to an easily expandable page architecture based on Linux large page memory. Background technique [0002] Memory management is the most important part of the Linux kernel. The memory adopts a "paging mechanism" to support fast and efficient management of large address spaces. Although the memory page size is configurable in principle, the default 4KB (4096 bytes) pages, or small pages, are used in the Linux kernel. When an application program with a large memory requirement is run on the Linux operating system, because the default page size is 4KB, it will generate many TLB Miss and page fault interrupts, which will greatly affect the performance of the application program. Therefore, the Linux kernel Huge page support was also introduced in . When the operating system uses 2MB or more as the paging unit, this will greatly reduce the number of TLB Miss and page ...

AI Technical Summary

Problems solved by technology

However, in essence, the implementation of hugetlbfs is only a means of "patching" to support flexible memory page sizes, which is limited by the Linux kernel

The large page file system and the small page still share the partner system, which makes the development and design on the large page inevitably affect the small page, which is not conducive to further development and expansion

Images