如何更改内核I / O缓冲区大小 [英] How to change kernel i/o buffer size

问题描述

我运行一些实验与I / O密集​​型应用程序，我试图了解不同内核的影响I / O缓冲的大小，不同的电梯算法，等等。

I am running some experiments with I/O intensive applications and am trying to understand the effects of varying the kernel i/o buffer size, different elevator algorithms, and so on.

我怎么能知道在内核中的I / O缓冲的当前大小？确实内核使用一个以上的缓冲液作为需要时？我怎样才能改变这个缓冲区的大小？是否有一个配置文件的地方存储此信息？

How can I know the current size of the i/o buffer in the kernel? Does the kernel use more than one buffer as need arises? How can I change the size of this buffer? Is there a config file somewhere that stores this info?

（很明显，我不是在谈论处理器或磁盘缓存，我说的是通过内部的缓冲区中读取/不时冲洗出来到磁盘之前写入内核使用的缓冲区）。

(To be clear, I am not talking about processor or disk caches, I am talking about the buffer used by the kernel internally that buffers reads/writes before flushing them out to disk from time to time).

先谢谢了。

推荐答案

内核不缓存​​读取和写入你的思考方式......它保持一个页面缓存保存在磁盘页。你没有得到操纵它的大小（当然，不是直接的，反正）;内核将始终使用的所有的的页面缓存的可用内存。

The kernel does not buffer reads and writes the way you think... It maintains a "page cache" that holds pages from the disk. You do not get to manipulate its size (well, not directly, anyway); the kernel will always use all available free memory for the page cache.

您需要解释你真正要做的。如果要对多少数据从磁盘内核pre-取一些控制，尝试预读的Linux的搜索。 （提示： blockdev看看-setra XXX ）

You need to explain what you are really trying to do. If you want some control over how much data the kernel pre-fetches from disk, try a search for "linux readahead". (Hint: blockdev --setra XXX)

如果你想在内核多久他们刷新到磁盘之前举行脏页一些控制，尝试Linux的dirty_ratio的搜索。

If you want some control over how long the kernel will hold dirty pages before flushing them to disk, try a search for "linux dirty_ratio".

一个特定的应用程序也可以使用完全绕过页面缓存 O_DIRECT ，并且它可以使用实行某种控制权 FSYNC ， sync_file_range ， posix_fadvise 和 posix_madvise 。 （ O_DIRECT 和 sync_file_range 是Linux的专用;其余的是POSIX）

A specific application can also bypass the page cache completely by using O_DIRECT, and it can exercise some control over it using fsync, sync_file_range, posix_fadvise, and posix_madvise. (O_DIRECT and sync_file_range are Linux-specific; the rest are POSIX.)

您可以问一个更好的问题，如果你先教育自己有关Linux VM子系统，尤其是页面缓存。

You will be able to ask a better question if you first educate yourself about the Linux VM subsystem, especially the page cache.

这篇关于如何更改内核I / O缓冲区大小的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！