linux内核函数之 blk_plug

分析：

/*

* blk_plug permits building a queue of related requests by holding the I/O

* fragments for a short period. This allows merging of sequential requests

* into single larger request. As the requests are moved from a per-task list to

* the device's request_queue in a batch, this results in improved scalability

* as the lock contention for request_queue lock is reduced.

*

* It is ok not to disable preemption when adding the request to the plug list

* or when attempting a merge, because blk_schedule_flush_list() will only flush

* the plug list when the task sleeps by itself. For details, please see

* schedule() where blk_schedule_flush_plug() is called.

*/

struct blk_plug {

     unsigned long magic; /* detect uninitialized use-cases */

     struct list_head list; /* requests */

     struct list_head cb_list; /* md requires an unplug callback */

     unsigned int should_sort; /* list to be sorted before flushing? */

};

#define BLK_MAX_REQUEST_COUNT 16



struct blk_plug_cb;

typedef void (*blk_plug_cb_fn)(struct blk_plug_cb *, bool);

struct blk_plug_cb {

     struct list_head list;

     blk_plug_cb_fn callback;

     void *data;

};

blk_plug构建了一个缓存碎片IO的请求队列。用于将顺序请求合并成一个大的请求。

合并后请求批量从per-task链表移动到设备请求队列，减少了设备请求队列锁竞争，

从而提高了效率。

blk_plug的使用很简单：

1、设置该线程开启请求合并模式  blk_start_plug

2、关闭线程请求合并  blk_finish_plug

至于如何合并、如何下发请求，这些工作都是由内核来完成的。

那么blk_plug适用于什么情况呢？由于是专门优化请求合并的，所以适合于连续的小块请求。

下面是一个测试的结果：

测试环境：

SATA控制器：intel 82801JI

OS: linux3.6, redhat 

raid5: 4个ST31000524NS盘

没有blk_plug:

Total (8,16):

 Reads Queued:      309811,     1239MiB  Writes Queued:           0,        0KiB

 Read Dispatches:   283583,     1189MiB  Write Dispatches:        0,        0KiB

 Reads Requeued:         0               Writes Requeued:         0

 Reads Completed:   273351,     1149MiB  Writes Completed:        0,        0KiB

 Read Merges:        23533,    94132KiB  Write Merges:            0,        0KiB

 IO unplugs:             0               Timer unplugs:           0



添加了 blk_plug:

Total (8,16):

 Reads Queued:      428697,     1714MiB  Writes Queued:           0,        0KiB

 Read Dispatches:     3954,     1714MiB  Write Dispatches:        0,        0KiB

 Reads Requeued:         0               Writes Requeued:         0

 Reads Completed:     3956,     1715MiB  Writes Completed:        0,        0KiB

 Read Merges:       424743,     1698MiB  Write Merges:            0,        0KiB

 IO unplugs:             0               Timer unplugs:        3384

可以看出，读请求大量被合并下发了。

blk_plug其他域说明：

magic：用于判断blk_plug是否有效

list：用于缓存请求的队列

cb_list：回调函数的链表，下发请求时会调用到

should_sort：下发之前是否对请求进行排序