Linux Kernel: buffers和cached的区别

      访问: 3,626 次      评论    

<p> The page cache caches pages of files to optimize file I/O. The buffer cache caches disk blocks to optimize block I/O. </p><p><span style="color: rgb(0, 112, 192);">Page Cache缓存文件内容以优化文件I/O,Buffer Cache缓存磁盘blocks以优化block I/O。 </span></p><p><span style="color: rgb(192, 0, 0);">注释:Block 块是用来管理磁盘空间的,而Page 页是针对内存管理,从磁盘读出的数据就缓存在内存页中。当一个块被调入到内存中,它要被存储在一个缓冲区中。 </span></p><p> Prior to Linux kernel version 2.4, the two caches were distinct: Files were in the page cache, disk blocks were in the buffer cache. Given that most files are represented by a filesystem on a disk, data was represented twice, once in each of the caches. Many Unix systems follow a similar pattern. </p><p><span style="color: rgb(0, 112, 192);">Linux kernel 2.4以前,这两个cache的使用是有明显区别的:文件的内容在Page Cache中缓冲,(管理基于磁盘的文件系统的VFS所访问的)blocks在Buffer Cache中缓冲。鉴于大多数的文件都是由基于磁盘的文件系统来存储和表示(represented )的,这样数据就被CACHE了两次,每个缓存(PageCache & BufferCache)中各表示一次。许多Unix系统都遵循此类的模式。 </span></p><p> This is simple to implement, but with an obvious ineleganceand inefficiency. Starting with Linux kernel version 2.4, the contents of the two caches were unified. The VM subsystem now drives I/O and it does so out of the page cache. If cached data has both a file and a block representation—as most data does—the buffer cache will simply point into the page cache; thus only one instance of the data is cached in memory. The page cache is what you picture when you think of a disk cache: It caches file data from a disk to make subsequent I/O faster. </p><p><span style="color: rgb(0, 112, 192);">这样易于实现,但存在明显的槽点(CACHE重复)和低效。从Linux kernel 2.4(2.4.10)开始,两个cache中的内容统一了(buffer cache不再真正的存在,实际上buffer cache不再独立分配,而是在page cache中用专门的buffer page来替代,buffer page在形式上就是缓冲区描述符,称为buffer_head)。现在由VM子系统来驱动I/O(并独立于Page Cache)。如果缓冲的数据既有文件表示(file representation)又有块表示(block representation)——大多数数据都是如此——那么buffer cache就简单的指向page cache;这样就仅有一份数据被缓冲在内存中了。当你想象一个磁盘缓存,page cache即是:它缓冲磁盘中的文件数据,以使后续的I/O操作更快。 </span></p><p><span style="color: rgb(192, 0, 0);">注释:每个缓冲区与一个块对应,它相当于磁盘块在内存中的表示。在内存页中,有一种叫专门用途的页面叫“缓冲区页”,用来存放块缓冲区。而每个块缓存区由两部分组成:缓冲区首部(用数据结构buffer_head表示)及真正的缓冲区内容(即所存储的数据,这些数据就放在刚刚说到的缓冲区页中)。而文件在内存中由file结构体表示,而磁盘块在内存中是由缓冲区来进行表示的。</span> </p><p> The buffer cache remains, however, as the kernel still needs to perform block I/O in terms of blocks, not pages. As most blocks represent file data, most of the buffer cache is represented by the page cache. But a small amount of block data isn't file backed—metadata and raw block I/O for example—and thus is solely represented by the buffer cache. </p><p><span style="color: rgb(0, 112, 192);">Buffer cache还被保留,因为内核还要以block为单位(而不是page)来进行block I/O操作。由于大多数情况下block就已经代表了文件数据,所以大多数的buffer cache由page cache来代替了。但还有少量block数据不是文件内容本身——例如文件系统的元数据(metadata)和裸设备(raw) block I/O——这些还是在buffer cache中缓冲的。</span> </p><p><span style="color: rgb(192, 0, 0);">注释:由于内核处理块时需要一些信息(比如将CACHE中的脏数据写入到磁盘中,而数据是被文件系统组织存储在block中的),如块属于哪个设备与块对应于哪个缓冲区。所以每个缓冲区都有一个缓冲区描述符,称为buffer_head。它包含了内核操作缓冲区所需要的全部信息。通过buffer_head 可以快速的定位page中独立的blocak在磁盘上的逻辑地址。</span> </p><p> See also my answer to What is the difference between Buffers and Cached columns in /proc/meminfo output?</p><p><br/></p><p></p><p style="text-align: center;">图1:page cache 和 buffer cache 的关系</p><p><br/></p><p></p><p style="text-align: center;">图2:the buffer cache</p><p><br/></p><p>原文链接:Linux Kernel: What is the major difference between the buffer cache and the page cache?</p><p>参考文章:block(块),page(页),buffer cache(块缓冲)区别与联系  </p><p><br/></p>

添加新评论