Commit 08635bae authored by Chris Mason's avatar Chris Mason Committed by David Sterba
Browse files

Btrfs: stop using btrfs_schedule_bio() 



btrfs_schedule_bio() hands IO off to a helper thread to do the actual
submit_bio() call.  This has been used to make sure async crc and
compression helpers don't get stuck on IO submission.  To maintain good
performance, over time the IO submission threads duplicated some IO
scheduler characteristics such as high and low priority IOs and they
also made some ugly assumptions about request allocation batch sizes.

All of this cost at least one extra context switch during IO submission,
and doesn't fit well with the modern blkmq IO stack.  So, this commit stops
using btrfs_schedule_bio().  We may need to adjust the number of async
helper threads for crcs and compression, but long term it's a better
path.

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 e1f60a65

fs/btrfs/compression.c

+4 −4
Original line number Diff line number Diff line
@@ -378,7 +378,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, 
				BUG_ON(ret); /* -ENOMEM */

			}



			ret = btrfs_map_bio(fs_info, bio, 0, 1);

			ret = btrfs_map_bio(fs_info, bio, 0);

			if (ret) {

				bio->bi_status = ret;

				bio_endio(bio);
@@ -409,7 +409,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, 
		BUG_ON(ret); /* -ENOMEM */

	}



	ret = btrfs_map_bio(fs_info, bio, 0, 1);

	ret = btrfs_map_bio(fs_info, bio, 0);

	if (ret) {

		bio->bi_status = ret;

		bio_endio(bio);
@@ -668,7 +668,7 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, 
						  fs_info->sectorsize);

			sums += csum_size * nr_sectors;



			ret = btrfs_map_bio(fs_info, comp_bio, mirror_num, 0);

			ret = btrfs_map_bio(fs_info, comp_bio, mirror_num);

			if (ret) {

				comp_bio->bi_status = ret;

				bio_endio(comp_bio);
@@ -693,7 +693,7 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, 
		BUG_ON(ret); /* -ENOMEM */

	}



	ret = btrfs_map_bio(fs_info, comp_bio, mirror_num, 0);

	ret = btrfs_map_bio(fs_info, comp_bio, mirror_num);

	if (ret) {

		comp_bio->bi_status = ret;

		bio_endio(comp_bio);

fs/btrfs/disk-io.c

+3 −4
Original line number Diff line number Diff line
@@ -791,8 +791,7 @@ static void run_one_async_done(struct btrfs_work *work) 
		return;

	}



	ret = btrfs_map_bio(btrfs_sb(inode->i_sb), async->bio,

			async->mirror_num, 1);

	ret = btrfs_map_bio(btrfs_sb(inode->i_sb), async->bio, async->mirror_num);

	if (ret) {

		async->bio->bi_status = ret;

		bio_endio(async->bio);
@@ -892,12 +891,12 @@ static blk_status_t btree_submit_bio_hook(struct inode *inode, struct bio *bio, 
					  BTRFS_WQ_ENDIO_METADATA);

		if (ret)

			goto out_w_error;

		ret = btrfs_map_bio(fs_info, bio, mirror_num, 0);

		ret = btrfs_map_bio(fs_info, bio, mirror_num);

	} else if (!async) {

		ret = btree_csum_one_bio(bio);

		if (ret)

			goto out_w_error;

		ret = btrfs_map_bio(fs_info, bio, mirror_num, 0);

		ret = btrfs_map_bio(fs_info, bio, mirror_num);

	} else {

		/*

		 * kthread helpers are used to submit writes so that

fs/btrfs/inode.c

+3 −3
Original line number Diff line number Diff line
@@ -2108,7 +2108,7 @@ static blk_status_t btrfs_submit_bio_hook(struct inode *inode, struct bio *bio, 
	}



mapit:

	ret = btrfs_map_bio(fs_info, bio, mirror_num, 0);

	ret = btrfs_map_bio(fs_info, bio, mirror_num);



out:

	if (ret) {
@@ -7850,7 +7850,7 @@ static inline blk_status_t submit_dio_repair_bio(struct inode *inode, 
	if (ret)

		return ret;



	ret = btrfs_map_bio(fs_info, bio, mirror_num, 0);

	ret = btrfs_map_bio(fs_info, bio, mirror_num);



	return ret;

}
@@ -8376,7 +8376,7 @@ static inline blk_status_t btrfs_submit_dio_bio(struct bio *bio, 
			goto err;

	}

map:

	ret = btrfs_map_bio(fs_info, bio, 0, 0);

	ret = btrfs_map_bio(fs_info, bio, 0);

err:

	return ret;

}

fs/btrfs/volumes.c

+4 −51
Original line number Diff line number Diff line
@@ -6415,52 +6415,8 @@ static void btrfs_end_bio(struct bio *bio) 
	}

}



/*

 * see run_scheduled_bios for a description of why bios are collected for

 * async submit.

 *

 * This will add one bio to the pending list for a device and make sure

 * the work struct is scheduled.

 */

static noinline void btrfs_schedule_bio(struct btrfs_device *device,

					struct bio *bio)

{

	struct btrfs_fs_info *fs_info = device->fs_info;

	int should_queue = 1;

	struct btrfs_pending_bios *pending_bios;



	/* don't bother with additional async steps for reads, right now */

	if (bio_op(bio) == REQ_OP_READ) {

		btrfsic_submit_bio(bio);

		return;

	}



	WARN_ON(bio->bi_next);

	bio->bi_next = NULL;



	spin_lock(&device->io_lock);

	if (op_is_sync(bio->bi_opf))

		pending_bios = &device->pending_sync_bios;

	else

		pending_bios = &device->pending_bios;



	if (pending_bios->tail)

		pending_bios->tail->bi_next = bio;



	pending_bios->tail = bio;

	if (!pending_bios->head)

		pending_bios->head = bio;

	if (device->running_pending)

		should_queue = 0;



	spin_unlock(&device->io_lock);



	if (should_queue)

		btrfs_queue_work(fs_info->submit_workers, &device->work);

}



static void submit_stripe_bio(struct btrfs_bio *bbio, struct bio *bio,

			      u64 physical, int dev_nr, int async)

			      u64 physical, int dev_nr)

{

	struct btrfs_device *dev = bbio->stripes[dev_nr].dev;

	struct btrfs_fs_info *fs_info = bbio->fs_info;
@@ -6478,9 +6434,6 @@ static void submit_stripe_bio(struct btrfs_bio *bbio, struct bio *bio, 


	btrfs_bio_counter_inc_noblocked(fs_info);



	if (async)

		btrfs_schedule_bio(dev, bio);

	else

	btrfsic_submit_bio(bio);

}
@@ -6502,7 +6455,7 @@ static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical) 
}



blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,

			   int mirror_num, int async_submit)

			   int mirror_num)

{

	struct btrfs_device *dev;

	struct bio *first_bio = bio;
@@ -6571,7 +6524,7 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, 
			bio = first_bio;



		submit_stripe_bio(bbio, bio, bbio->stripes[dev_nr].physical,

				  dev_nr, async_submit);

				  dev_nr);

	}

	btrfs_bio_counter_dec(fs_info);

	return BLK_STS_OK;

fs/btrfs/volumes.h

+1 −1
Original line number Diff line number Diff line
@@ -436,7 +436,7 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info); 
int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type);

void btrfs_mapping_tree_free(struct extent_map_tree *tree);

blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,

			   int mirror_num, int async_submit);

			   int mirror_num);

int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,

		       fmode_t flags, void *holder);

struct btrfs_device *btrfs_scan_one_device(const char *path,

CRA Git | Maintained and supported by SUSTech CRA and CCSE