Commit ba8a9d07 authored by Chris Mason's avatar Chris Mason Committed by David Sterba
Browse files

Btrfs: delete the entire async bio submission framework 



Now that we're not using btrfs_schedule_bio() anymore, delete all the
code that supported it.

Reviewed-by: default avatarJosef Bacik <josef@toxicpanda.com>
Reviewed-by: default avatarNikolay Borisov <nborisov@suse.com>
Signed-off-by: default avatarChris Mason <clm@fb.com>
Reviewed-by: default avatarDavid Sterba <dsterba@suse.com>
Signed-off-by: default avatarDavid Sterba <dsterba@suse.com>
parent 08635bae

fs/btrfs/ctree.h

+0 −1
Original line number Diff line number Diff line
@@ -723,7 +723,6 @@ struct btrfs_fs_info { 
	struct btrfs_workqueue *endio_meta_write_workers;

	struct btrfs_workqueue *endio_write_workers;

	struct btrfs_workqueue *endio_freespace_worker;

	struct btrfs_workqueue *submit_workers;

	struct btrfs_workqueue *caching_workers;

	struct btrfs_workqueue *readahead_workers;

fs/btrfs/disk-io.c

+1 −12
Original line number Diff line number Diff line
@@ -1989,7 +1989,6 @@ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info) 
	btrfs_destroy_workqueue(fs_info->rmw_workers);

	btrfs_destroy_workqueue(fs_info->endio_write_workers);

	btrfs_destroy_workqueue(fs_info->endio_freespace_worker);

	btrfs_destroy_workqueue(fs_info->submit_workers);

	btrfs_destroy_workqueue(fs_info->delayed_workers);

	btrfs_destroy_workqueue(fs_info->caching_workers);

	btrfs_destroy_workqueue(fs_info->readahead_workers);
@@ -2154,16 +2153,6 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info, 
	fs_info->caching_workers =

		btrfs_alloc_workqueue(fs_info, "cache", flags, max_active, 0);



	/*

	 * a higher idle thresh on the submit workers makes it much more

	 * likely that bios will be send down in a sane order to the

	 * devices

	 */

	fs_info->submit_workers =

		btrfs_alloc_workqueue(fs_info, "submit", flags,

				      min_t(u64, fs_devices->num_devices,

					    max_active), 64);



	fs_info->fixup_workers =

		btrfs_alloc_workqueue(fs_info, "fixup", flags, 1, 0);
@@ -2202,7 +2191,7 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info, 
		btrfs_alloc_workqueue(fs_info, "qgroup-rescan", flags, 1, 0);



	if (!(fs_info->workers && fs_info->delalloc_workers &&

	      fs_info->submit_workers && fs_info->flush_workers &&

	      fs_info->flush_workers &&

	      fs_info->endio_workers && fs_info->endio_meta_workers &&

	      fs_info->endio_meta_write_workers &&

	      fs_info->endio_repair_workers &&

fs/btrfs/super.c

+0 −1
Original line number Diff line number Diff line
@@ -1669,7 +1669,6 @@ static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info, 


	btrfs_workqueue_set_max(fs_info->workers, new_pool_size);

	btrfs_workqueue_set_max(fs_info->delalloc_workers, new_pool_size);

	btrfs_workqueue_set_max(fs_info->submit_workers, new_pool_size);

	btrfs_workqueue_set_max(fs_info->caching_workers, new_pool_size);

	btrfs_workqueue_set_max(fs_info->endio_workers, new_pool_size);

	btrfs_workqueue_set_max(fs_info->endio_meta_workers, new_pool_size);

fs/btrfs/volumes.c

+0 −210
Original line number Diff line number Diff line
@@ -397,8 +397,6 @@ static struct btrfs_device *__alloc_device(void) 
	INIT_LIST_HEAD(&dev->dev_alloc_list);

	INIT_LIST_HEAD(&dev->post_commit_list);



	spin_lock_init(&dev->io_lock);



	atomic_set(&dev->reada_in_flight, 0);

	atomic_set(&dev->dev_stats_ccnt, 0);

	btrfs_device_data_ordered_init(dev);
@@ -501,212 +499,6 @@ btrfs_get_bdev_and_sb(const char *device_path, fmode_t flags, void *holder, 
	return ret;

}



static void requeue_list(struct btrfs_pending_bios *pending_bios,

			struct bio *head, struct bio *tail)

{



	struct bio *old_head;



	old_head = pending_bios->head;

	pending_bios->head = head;

	if (pending_bios->tail)

		tail->bi_next = old_head;

	else

		pending_bios->tail = tail;

}



/*

 * we try to collect pending bios for a device so we don't get a large

 * number of procs sending bios down to the same device.  This greatly

 * improves the schedulers ability to collect and merge the bios.

 *

 * But, it also turns into a long list of bios to process and that is sure

 * to eventually make the worker thread block.  The solution here is to

 * make some progress and then put this work struct back at the end of

 * the list if the block device is congested.  This way, multiple devices

 * can make progress from a single worker thread.

 */

static noinline void run_scheduled_bios(struct btrfs_device *device)

{

	struct btrfs_fs_info *fs_info = device->fs_info;

	struct bio *pending;

	struct backing_dev_info *bdi;

	struct btrfs_pending_bios *pending_bios;

	struct bio *tail;

	struct bio *cur;

	int again = 0;

	unsigned long num_run;

	unsigned long batch_run = 0;

	unsigned long last_waited = 0;

	int force_reg = 0;

	int sync_pending = 0;

	struct blk_plug plug;



	/*

	 * this function runs all the bios we've collected for

	 * a particular device.  We don't want to wander off to

	 * another device without first sending all of these down.

	 * So, setup a plug here and finish it off before we return

	 */

	blk_start_plug(&plug);



	bdi = device->bdev->bd_bdi;



loop:

	spin_lock(&device->io_lock);



loop_lock:

	num_run = 0;



	/* take all the bios off the list at once and process them

	 * later on (without the lock held).  But, remember the

	 * tail and other pointers so the bios can be properly reinserted

	 * into the list if we hit congestion

	 */

	if (!force_reg && device->pending_sync_bios.head) {

		pending_bios = &device->pending_sync_bios;

		force_reg = 1;

	} else {

		pending_bios = &device->pending_bios;

		force_reg = 0;

	}



	pending = pending_bios->head;

	tail = pending_bios->tail;

	WARN_ON(pending && !tail);



	/*

	 * if pending was null this time around, no bios need processing

	 * at all and we can stop.  Otherwise it'll loop back up again

	 * and do an additional check so no bios are missed.

	 *

	 * device->running_pending is used to synchronize with the

	 * schedule_bio code.

	 */

	if (device->pending_sync_bios.head == NULL &&

	    device->pending_bios.head == NULL) {

		again = 0;

		device->running_pending = 0;

	} else {

		again = 1;

		device->running_pending = 1;

	}



	pending_bios->head = NULL;

	pending_bios->tail = NULL;



	spin_unlock(&device->io_lock);



	while (pending) {



		rmb();

		/* we want to work on both lists, but do more bios on the

		 * sync list than the regular list

		 */

		if ((num_run > 32 &&

		    pending_bios != &device->pending_sync_bios &&

		    device->pending_sync_bios.head) ||

		   (num_run > 64 && pending_bios == &device->pending_sync_bios &&

		    device->pending_bios.head)) {

			spin_lock(&device->io_lock);

			requeue_list(pending_bios, pending, tail);

			goto loop_lock;

		}



		cur = pending;

		pending = pending->bi_next;

		cur->bi_next = NULL;



		BUG_ON(atomic_read(&cur->__bi_cnt) == 0);



		/*

		 * if we're doing the sync list, record that our

		 * plug has some sync requests on it

		 *

		 * If we're doing the regular list and there are

		 * sync requests sitting around, unplug before

		 * we add more

		 */

		if (pending_bios == &device->pending_sync_bios) {

			sync_pending = 1;

		} else if (sync_pending) {

			blk_finish_plug(&plug);

			blk_start_plug(&plug);

			sync_pending = 0;

		}



		btrfsic_submit_bio(cur);

		num_run++;

		batch_run++;



		cond_resched();



		/*

		 * we made progress, there is more work to do and the bdi

		 * is now congested.  Back off and let other work structs

		 * run instead

		 */

		if (pending && bdi_write_congested(bdi) && batch_run > 8 &&

		    fs_info->fs_devices->open_devices > 1) {

			struct io_context *ioc;



			ioc = current->io_context;



			/*

			 * the main goal here is that we don't want to

			 * block if we're going to be able to submit

			 * more requests without blocking.

			 *

			 * This code does two great things, it pokes into

			 * the elevator code from a filesystem _and_

			 * it makes assumptions about how batching works.

			 */

			if (ioc && ioc->nr_batch_requests > 0 &&

			    time_before(jiffies, ioc->last_waited + HZ/50UL) &&

			    (last_waited == 0 ||

			     ioc->last_waited == last_waited)) {

				/*

				 * we want to go through our batch of

				 * requests and stop.  So, we copy out

				 * the ioc->last_waited time and test

				 * against it before looping

				 */

				last_waited = ioc->last_waited;

				cond_resched();

				continue;

			}

			spin_lock(&device->io_lock);

			requeue_list(pending_bios, pending, tail);

			device->running_pending = 1;



			spin_unlock(&device->io_lock);

			btrfs_queue_work(fs_info->submit_workers,

					 &device->work);

			goto done;

		}

	}



	cond_resched();

	if (again)

		goto loop;



	spin_lock(&device->io_lock);

	if (device->pending_bios.head || device->pending_sync_bios.head)

		goto loop_lock;

	spin_unlock(&device->io_lock);



done:

	blk_finish_plug(&plug);

}



static void pending_bios_fn(struct btrfs_work *work)

{

	struct btrfs_device *device;



	device = container_of(work, struct btrfs_device, work);

	run_scheduled_bios(device);

}



static bool device_path_matched(const char *path, struct btrfs_device *device)

{

	int found;
@@ -6628,8 +6420,6 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info, 
	else

		generate_random_uuid(dev->uuid);



	btrfs_init_work(&dev->work, pending_bios_fn, NULL, NULL);



	return dev;

}

fs/btrfs/volumes.h

+0 −11
Original line number Diff line number Diff line
@@ -18,10 +18,6 @@ extern struct mutex uuid_mutex; 
#define BTRFS_STRIPE_LEN	SZ_64K



struct buffer_head;

struct btrfs_pending_bios {

	struct bio *head;

	struct bio *tail;

};



struct btrfs_io_geometry {

	/* remaining bytes before crossing a stripe */
@@ -68,13 +64,6 @@ struct btrfs_device { 


	u64 generation;



	spinlock_t io_lock ____cacheline_aligned;

	int running_pending;

	/* regular prio bios */

	struct btrfs_pending_bios pending_bios;

	/* sync bios */

	struct btrfs_pending_bios pending_sync_bios;



	struct block_device *bdev;



	/* the mode sent to blkdev_get */