DRBD源码分析（三）——块设备驱动和IO队列处理函数

STATIC void drbd_connector_callback(struct cn_msg *req, struct netlink_skb_parms *nsp)

方法。在该方法中有一处调用：

mdev = ensure_mdev(nlp); 

drbd_thread_init(mdev, &mdev->receiver, drbdd_init); 
drbd_thread_init(mdev, &mdev->worker, drbd_worker); 
drbd_thread_init(mdev, &mdev->asender, drbd_asender);

struct drbd_conf* drbd_new_device(unsigned int minor)
{
    struct drbd_conf* mdev;
    struct gendisk* disk;
    struct request_queue* q;

    /* GFP_KERNEL, we are outside of all write-out paths */
    mdev = kzalloc(sizeof(struct drbd_conf), GFP_KERNEL);
    if (!mdev)
        return NULL;
    if (!zalloc_cpumask_var(&mdev->cpu_mask, GFP_KERNEL))
        goto out_no_cpumask;

    mdev->minor = minor;

    drbd_init_set_defaults(mdev);

    q = blk_alloc_queue(GFP_KERNEL);
    if (!q)
        goto out_no_q;
    mdev->rq_queue = q;
    q->queuedata = mdev;
    blk_queue_max_segment_size(q, DRBD_MAX_SEGMENT_SIZE);

    disk = alloc_disk(1);
    if (!disk)
        goto out_no_disk;
    mdev->vdisk = disk;

    set_disk_ro(disk, TRUE);

    disk->queue = q;
    disk->major = DRBD_MAJOR;
    disk->first_minor = minor;
    disk->fops = &drbd_ops;
    sprintf(disk->disk_name, "drbd%d", minor);
    disk->private_data = mdev;

    mdev->this_bdev = bdget(MKDEV(DRBD_MAJOR, minor));
    /* we have no partitions. we contain only ourselves. */
    mdev->this_bdev->bd_contains = mdev->this_bdev;

    q->backing_dev_info.congested_fn = drbd_congested;
    q->backing_dev_info.congested_data = mdev;

    blk_queue_make_request(q, drbd_make_request_26);
    blk_queue_bounce_limit(q, BLK_BOUNCE_ANY);
    blk_queue_merge_bvec(q, drbd_merge_bvec);
    q->queue_lock = &mdev->req_lock; /* needed since we use */
    /* plugging on a queue, that actually has no requests! */
    q->unplug_fn = drbd_unplug_fn;

    mdev->md_io_page = alloc_page(GFP_KERNEL);
    if (!mdev->md_io_page)
        goto out_no_io_page;

    if (drbd_bm_init(mdev))
        goto out_no_bitmap;
    /* no need to lock access, we are still initializing this minor device. */
    if (!tl_init(mdev))
        goto out_no_tl;

    mdev->app_reads_hash = kzalloc(APP_R_HSIZE * sizeof(void *), GFP_KERNEL);
    if (!mdev->app_reads_hash)
        goto out_no_app_reads;

    mdev->current_epoch = kzalloc(sizeof(struct drbd_epoch), GFP_KERNEL);
    if (!mdev->current_epoch)
        goto out_no_epoch;

    INIT_LIST_HEAD(&mdev->current_epoch->list);
    mdev->epochs = 1;

    return mdev;

    /* out_whatever_else:
        kfree(mdev->current_epoch); */
    out_no_epoch:
    kfree(mdev->app_reads_hash);
    out_no_app_reads:
    tl_cleanup(mdev);
    out_no_tl:
    drbd_bm_cleanup(mdev);
    out_no_bitmap:
    __free_page(mdev->md_io_page);
    out_no_io_page:
    put_disk(disk);
    out_no_disk:
    blk_cleanup_queue(q);
    out_no_q:
    free_cpumask_var(mdev->cpu_mask);
    out_no_cpumask:
    kfree(mdev);
    return NULL;
}

/* to make some things easier, force alignment of requests within the
 * granularity of our hash tables */
s_enr = bio->bi_sector >> HT_SHIFT;
e_enr = (bio->bi_sector + (bio->bi_size >> 9) - 1) >> HT_SHIFT;

if (likely(s_enr == e_enr))
{
    dev_err(DEV, "drbd_make_request_26 2\n");
    inc_ap_bio(mdev, 1);
    return drbd_make_request_common(mdev, bio);
}

对于bio落在32个扇区以内的bio，直接当作一个普通的IO处理即可，走drbd_make_request_common方法，否则，需要对IO进行拆分，调试的时候发现所有的IO都在32扇区以内，并没有跨度超过这个值的bio。

在drbd_make_request_common中，会对IO进行本地的存盘，然后发送到对端。发送到对端的过程是想worker线程监听的任务队列中放入任务。由worker线程负责发送。

比较重要的两个方法：

__req_mod和drbd_make_request_common，把这两个方法弄清楚了，主节点的业务流程也就清晰了。