Linux3.10.0块IO子系统流程（2）-- 构造、排序、合并请求

Linux块设备可以分为三类。分别针对顺序访问物理设备、随机访问物理设备和逻辑设备（即“栈式设备”）

 

类型	make_request_fn	request_fn	备注
SCSI 设备等	从bio构造request（经过合并和排序），返回0	逐个处理request	调用blk_init_queue，使用默认的__make_request，提供策略例程
SSD等	直接处理bio，返回0	无	调用blk_alloc_queue，提供make_request_fn
RAID或Device Mapper设备	重定向bio，返回非零值	无	调用blk_alloc_queue，提供make_request_fn

 

blk_init_queue原型：

 struct request_queue *blk_init_queue(request_fn_proc *rfn, spinlock_t *lock)
 {
     return blk_init_queue_node(rfn, lock, NUMA_NO_NODE);
 }
 EXPORT_SYMBOL(blk_init_queue);
 
 struct request_queue *
 blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
 {
     struct request_queue *uninit_q, *q;
     uninit_q = blk_alloc_queue_node(GFP_KERNEL, node_id);
     if (!uninit_q)
         return NULL;
     q = blk_init_allocated_queue(uninit_q, rfn, lock);
     if (!q)
         blk_cleanup_queue(uninit_q);
     return q;
 }
 EXPORT_SYMBOL(blk_init_queue_node);
 
 struct request_queue *
 blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
              spinlock_t *lock)
 {
     if (!q)
         return NULL;
     if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
         return NULL;
     q->request_fn        = rfn;
     q->prep_rq_fn        = NULL;
     q->unprep_rq_fn        = NULL;
     q->queue_flags        |= QUEUE_FLAG_DEFAULT;
     /* Override internal queue lock with supplied lock pointer */
     if (lock)
         q->queue_lock        = lock;
     /*
      * This also sets hw/phys segments, boundary and size
      */
     blk_queue_make_request(q, blk_queue_bio);　　//使用blk_init_queue会默认绑定blk_queue_bio来处理IO
     q->sg_reserved_size = INT_MAX;
     /* init elevator */
     if (elevator_init(q, NULL))    // 初始化IO调度
         return NULL;
     return q;
 }
 EXPORT_SYMBOL(blk_init_allocated_queue);

下面来跟踪blk_queue_bio函数：

 void blk_queue_bio(struct request_queue *q, struct bio *bio)
 {
     const bool sync = !!(bio->bi_rw & REQ_SYNC);
     struct blk_plug *plug;
     int el_ret, rw_flags, where = ELEVATOR_INSERT_SORT;
     struct request *req;
     unsigned int request_count = ;
     /*
      * low level driver can indicate that it wants pages above a
      * certain limit bounced to low memory (ie for highmem, or even
      * ISA dma in theory)
      */
     blk_queue_bounce(q, &bio);    // 如果需要，创建反弹缓冲区
     if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
         bio_endio(bio, -EIO);
         return;
     }
     if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) {
         spin_lock_irq(q->queue_lock);
         where = ELEVATOR_INSERT_FLUSH;
         goto get_rq;
     }
     /*
      * Check if we can merge with the plugged list before grabbing any locks
      * 首先尝试请求合并
      */
     if (attempt_plug_merge(q, bio, &request_count))
         return;
     spin_lock_irq(q->queue_lock);
     el_ret = elv_merge(q, &req, bio);    // 判断是否bio是否可以合并
     // 如果可以合并的话，分为向前和向后合并
     if (el_ret == ELEVATOR_BACK_MERGE) {
         if (bio_attempt_back_merge(q, req, bio)) {
             elv_bio_merged(q, req, bio);    // 请求如果在硬件上允许，则进行合并
             if (!attempt_back_merge(q, req))    // 合并之后可能两个request可以合并
                 elv_merged_request(q, req, el_ret);
             goto out_unlock;
         }
     } else if (el_ret == ELEVATOR_FRONT_MERGE) {
         if (bio_attempt_front_merge(q, req, bio)) {
             elv_bio_merged(q, req, bio);
             if (!attempt_front_merge(q, req))
                 elv_merged_request(q, req, el_ret);
             goto out_unlock;
         }
     }
 // 不能合并就根据bio构造request
 get_rq:
     /*
      * This sync check and mask will be re-done in init_request_from_bio(),
      * but we need to set it earlier to expose the sync flag to the
      * rq allocator and io schedulers.
      */
     rw_flags = bio_data_dir(bio);
     if (sync)
         rw_flags |= REQ_SYNC;
     /*
      * Grab a free request. This is might sleep but can not fail.
      * Returns with the queue unlocked.
      */
     req = get_request(q, rw_flags, bio, GFP_NOIO);    // 获取一个request
     if (unlikely(!req)) {
         bio_endio(bio, -ENODEV);    /* @q is dead */
         goto out_unlock;
     }
     /*
      * After dropping the lock and possibly sleeping here, our request
      * may now be mergeable after it had proven unmergeable (above).
      * We don't worry about that case for efficiency. It won't happen
      * often, and the elevators are able to handle it.
      */
     init_request_from_bio(req, bio);    // 根据bio构造一个request，并添加到IO调度器队列
     if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags))
         req->cpu = raw_smp_processor_id();
     plug = current->plug;
     // 接下来是蓄流/泄流策略
     if (plug) {
         /*
          * If this is the first request added after a plug, fire
          * of a plug trace. If others have been added before, check
          * if we have multiple devices in this plug. If so, make a
          * note to sort the list before dispatch.
          */
         if (list_empty(&plug->list))
             trace_block_plug(q);
         else {
             if (request_count >= BLK_MAX_REQUEST_COUNT) {
                 blk_flush_plug_list(plug, false);
                 trace_block_plug(q);
             }
         }
         list_add_tail(&req->queuelist, &plug->list);
         drive_stat_acct(req, );
     } else {
         spin_lock_irq(q->queue_lock);
         add_acct_request(q, req, where);　　// 将请求添加到IO调度队列或请求队列，主要被用来处理屏障请求
         __blk_run_queue(q);
 out_unlock:
         spin_unlock_irq(q->queue_lock);
     }
 }
 EXPORT_SYMBOL_GPL(blk_queue_bio);    /* for device mapper only */

第13行，blk_queue_bounce创建一个反弹缓冲区。通常是在驱动尝试在外围设备不可达到的地址。例如高端内存上执行DMA等。创建反弹缓冲区后，数据要在原缓冲区和反弹缓冲区之间进行与读写方向对应的复制。毫无疑问，使用反弹缓冲区会降低性能，但也没有其他办法。

所谓反弹，实际上是分配一个新的bio描述符，它和原始bio的segment一一对应。如果原始bio的segment使用的页面在DMA内存范围外，则分配一个在DMA范围内的页面，赋给新的bio对应的segment。对于写操作，需要将旧bio页面的内容复制到新的bio中。如果原始的bio的segment使用的页面在DMA范围内，则将新的bio指向同一地方。

最后将原始bio保存在新的bio的bi_private域中，并设置新bio的完成回调函数。

接下来交给IO调度器，由它负责合并和排序请求。合并是指将对磁盘上连续位置的请求合并为一个，通过一次SCSI命令完成。排序是将多个请求对磁盘上的访问位置顺序重新排列，使得磁头尽可能向一个方向移动。请求的合并和排序是在SCSI设备的请求队列描述符上进行的。

 int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 {
     struct elevator_queue *e = q->elevator;
     struct request *__rq;
     int ret;
 
     /*
      * Levels of merges:
      *     nomerges:  No merges at all attempted
      *     noxmerges: Only simple one-hit cache try
      *     merges:       All merge tries attempted
      */
     if (blk_queue_nomerges(q))    // 如果设置了QUEUE_FLAG_NOMERGES的标志位，就直接返回不合并
         return ELEVATOR_NO_MERGE;
 
     /*
      * First try one-hit cache.
      */
     // 如果请求队列的last_merge有缓存下来的request，调用blk_try_merge来进行尝试和它进行合并，如果可以合并，通过参数输出这个req
     if (q->last_merge && elv_rq_merge_ok(q->last_merge, bio)) {
         ret = blk_try_merge(q->last_merge, bio);
         if (ret != ELEVATOR_NO_MERGE) {
             *req = q->last_merge;
             return ret;
         }
     }
 
      // 如果设置了QUEUE_FLAG_NOXMERGES的标志位，表明不要进行“扩展”的合并尝试
     if (blk_queue_noxmerges(q))
         return ELEVATOR_NO_MERGE;
 
     /*
      * See if our hash lookup can find a potential backmerge.
      * 后面的代码就是所谓的“扩展”合并尝试，它包含两方面的内容：
      * 第一部分是各种IO调度算法全都适用的，而第二部分则是各种IO调度算法特定的
      */
     __rq = elv_rqhash_find(q, bio->bi_sector);
     if (__rq && elv_rq_merge_ok(__rq, bio)) {
         *req = __rq;
         return ELEVATOR_BACK_MERGE;
     }
 
     /*
      * IO调度特定的合并算法是通过电梯队列操作表的elevator_merge_fn回调实现的
      */
     if (e->type->ops.elevator_merge_fn)
         return e->type->ops.elevator_merge_fn(q, req, bio);
 
     return ELEVATOR_NO_MERGE;
 }

如果我们的请求不能合并到现有的request中，那么就要新申请request描述符了，根据bio对它初始化，并添加到IO调度器队列

最后Linux块设备层采用蓄流/泄流技术来改进吞吐量，蓄流是为了将请求合并和排序，然后一起泄流，泄流函数为__blk_run_queue(q)

/**
* __blk_run_queue - run a single device queue
* @q:    The queue to run
*
* Description:
*    See @blk_run_queue. This variant must be called with the queue lock
*    held and interrupts disabled.
*/
void __blk_run_queue(struct request_queue *q)
{
    if (unlikely(blk_queue_stopped(q)))
        return;
    __blk_run_queue_uncond(q);
}
 
/**
* __blk_run_queue_uncond - run a queue whether or not it has been stopped
* @q:    The queue to run
*
* Description:
*    Invoke request handling on a queue if there are any pending requests.
*    May be used to restart request handling after a request has completed.
*    This variant runs the queue whether or not the queue has been
*    stopped. Must be called with the queue lock held and interrupts
*    disabled. See also @blk_run_queue.
*/
inline void __blk_run_queue_uncond(struct request_queue *q)
{
    if (unlikely(blk_queue_dead(q)))
        return;
    /*
     * Some request_fn implementations, e.g. scsi_request_fn(), unlock
     * the queue lock internally. As a result multiple threads may be
     * running such a request function concurrently. Keep track of the
     * number of active request_fn invocations such that blk_drain_queue()
     * can wait until all these request_fn calls have finished.
     */
    q->request_fn_active++;
    q->request_fn(q);    // 回调函数实例化为scsi_request_fn，也就是通常所说的SCSI策略例程
    q->request_fn_active--;
}

__blk_run_queue

对于SCSI设备，在为它分配请求队列时，将请求队列的request_fn回调函数实例化为scsi_request_fn，也就是通常所说的SCSI策略例程。