LFS（the Log-structured File System）系统详解

There was a large and growing gap between random I/O performance and sequential I/O performance:
Existing file systems perform poorly on many common workloads:

LFS文件系统的设计木主要是为了解决上面这以前文件系统所存在的两个问题：随机输入输出的性能和序列输入输出的性能相差很大；还有就是磁盘搜索和旋转延迟比较大。

LFS, short for the Log-structured File System. When writing to disk, LFS first buffers all updates (including metadata!) in an inmemory segment; when the segment is full, it is written to disk in one long, sequential transfer to an unused part of the disk. LFS never overwrites existing data, but ratheralwayswrites segments to free locations.

LFS文件系统的主要算法就是首先把所有的更新（包括元数据）缓存在内存中的成为segment的单位中。当segment填满之后，里面的数据就写入到磁盘中未使用的地方。 特别要注意的是：LFS并不会覆写已有的数据，而是把segment中的数据写入到磁盘中新的位置。（这样在磁盘中就会有old data和new data,在后面会详细讲到）

This basic idea, of simply writing all updates (such as data blocks, inodes, etc.) to the disk sequentially, sits at the heart of LFS. If you understand this, you get the basic idea. But as with all complicated systems, the devil is in the details.