Understanding the Linux Kernel

Chapter 14. Disk Caches

This chapter deals with disk caches. It shows how Linux makes use of sophisticated techniques to improve system performances by reducing disk accesses as much as possible.

As mentioned in Section 12.1.1 in Chapter 12, a disk cache is a software mechanism that allows the system to keep in RAM some data normally stored on a disk, so that further accesses to that data can be satisfied quickly without accessing the disk.

Besides the dentry cache, which is used by the VFS to speed up the translation of a file pathname to the corresponding inode, two main disk caches—the buffer cache and the page cache—are used by Linux. Most of this chapter describes the buffer cache, and a short section near the end covers the page cache.

We learned in Section 13.5.1 in Chapter 13, that a buffer is a memory area containing the data of a disk block. Each block refers to physically adjacent bytes on the disk surface; the block size depends on the type of the filesystem it comes from. As suggested by its name, the buffer cache is a disk cache that stores buffers.

Conversely, the page cache is a disk cache storing page frames that contain data belonging to regular files. It is inherently different from the buffer cache, since page frames in the page cache do not necessarily correspond to physically adjacent disk blocks.

Buffer I/O operations (see Section 13.5 in Chapter 13) make use of the buffer cache only. Page I/O operations use the page cache and optionally the buffer cache ...