Commit d3575156 authored by Naohiro Aota's avatar Naohiro Aota Committed by David Sterba
Browse files

btrfs: zoned: redirty released extent buffers 



Tree manipulating operations like merging nodes often release
once-allocated tree nodes. Such nodes are cleaned so that pages in the
node are not uselessly written out. On zoned volumes, however, such
optimization blocks the following IOs as the cancellation of the write
out of the freed blocks breaks the sequential write sequence expected by
the device.

Introduce a list of clean and unwritten extent buffers that have been
released in a transaction. Redirty the buffers so that
btree_write_cache_pages() can send proper bios to the devices.

Besides it clears the entire content of the extent buffer not to confuse
raw block scanners e.g. 'btrfs check'. By clearing the content,
csum_dirty_buffer() complains about bytenr mismatch, so avoid the
checking and checksum using newly introduced buffer flag
EXTENT_BUFFER_NO_CHECK.

Reviewed-by: default avatarJosef Bacik <josef@toxicpanda.com>
Signed-off-by: default avatarNaohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: default avatarDavid Sterba <dsterba@suse.com>
parent 2eda5708

fs/btrfs/disk-io.c

+8 −0
Original line number Diff line number Diff line
@@ -459,6 +459,12 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct bio_vec *bvec 
		return 0;



	found_start = btrfs_header_bytenr(eb);



	if (test_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags)) {

		WARN_ON(found_start != 0);

		return 0;

	}



	/*

	 * Please do not consolidate these warnings into a single if.

	 * It is useful to know what went wrong.
@@ -4774,6 +4780,8 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, 
				     EXTENT_DIRTY);

	btrfs_destroy_pinned_extent(fs_info, &cur_trans->pinned_extents);



	btrfs_free_redirty_list(cur_trans);



	cur_trans->state =TRANS_STATE_COMPLETED;

	wake_up(&cur_trans->commit_wait);

}

fs/btrfs/extent-tree.c

+11 −1
Original line number Diff line number Diff line
@@ -3292,9 +3292,11 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, 


		if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {

			ret = check_ref_cleanup(trans, buf->start);

			if (!ret)

			if (!ret) {

				btrfs_redirty_list_add(trans->transaction, buf);

				goto out;

			}

		}



		cache = btrfs_lookup_block_group(fs_info, buf->start);
@@ -3304,6 +3306,13 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, 
			goto out;

		}



		if (btrfs_is_zoned(fs_info)) {

			btrfs_redirty_list_add(trans->transaction, buf);

			pin_down_extent(trans, cache, buf->start, buf->len, 1);

			btrfs_put_block_group(cache);

			goto out;

		}



		WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags));



		btrfs_add_free_space(cache, buf->start, buf->len);
@@ -4635,6 +4644,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, 
	__btrfs_tree_lock(buf, nest);

	btrfs_clean_tree_block(buf);

	clear_bit(EXTENT_BUFFER_STALE, &buf->bflags);

	clear_bit(EXTENT_BUFFER_NO_CHECK, &buf->bflags);



	set_extent_buffer_uptodate(buf);

fs/btrfs/extent_io.c

+4 −0
Original line number Diff line number Diff line
@@ -25,6 +25,7 @@ 
#include "backref.h"

#include "disk-io.h"

#include "subpage.h"

#include "zoned.h"



static struct kmem_cache *extent_state_cache;

static struct kmem_cache *extent_buffer_cache;
@@ -5182,6 +5183,7 @@ __alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start, 


	btrfs_leak_debug_add(&fs_info->eb_leak_lock, &eb->leak_list,

			     &fs_info->allocated_ebs);

	INIT_LIST_HEAD(&eb->release_list);



	spin_lock_init(&eb->refs_lock);

	atomic_set(&eb->refs, 1);
@@ -6111,6 +6113,8 @@ void write_extent_buffer(const struct extent_buffer *eb, const void *srcv, 
	char *src = (char *)srcv;

	unsigned long i = get_eb_page_index(start);



	WARN_ON(test_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags));



	if (check_eb_range(eb, start, len))

		return;

fs/btrfs/extent_io.h

+2 −0
Original line number Diff line number Diff line
@@ -31,6 +31,7 @@ enum { 
	EXTENT_BUFFER_IN_TREE,

	/* write IO error */

	EXTENT_BUFFER_WRITE_ERR,

	EXTENT_BUFFER_NO_CHECK,

};



/* these are flags for __process_pages_contig */
@@ -93,6 +94,7 @@ struct extent_buffer { 
	struct rw_semaphore lock;



	struct page *pages[INLINE_EXTENT_BUFFER_PAGES];

	struct list_head release_list;

#ifdef CONFIG_BTRFS_DEBUG

	struct list_head leak_list;

#endif

fs/btrfs/transaction.c

+10 −0
Original line number Diff line number Diff line
@@ -21,6 +21,7 @@ 
#include "qgroup.h"

#include "block-group.h"

#include "space-info.h"

#include "zoned.h"



#define BTRFS_ROOT_TRANS_TAG 0
@@ -380,6 +381,8 @@ static noinline int join_transaction(struct btrfs_fs_info *fs_info, 
	spin_lock_init(&cur_trans->dirty_bgs_lock);

	INIT_LIST_HEAD(&cur_trans->deleted_bgs);

	spin_lock_init(&cur_trans->dropped_roots_lock);

	INIT_LIST_HEAD(&cur_trans->releasing_ebs);

	spin_lock_init(&cur_trans->releasing_ebs_lock);

	list_add_tail(&cur_trans->list, &fs_info->trans_list);

	extent_io_tree_init(fs_info, &cur_trans->dirty_pages,

			IO_TREE_TRANS_DIRTY_PAGES, fs_info->btree_inode);
@@ -2350,6 +2353,13 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) 
		goto scrub_continue;

	}



	/*

	 * At this point, we should have written all the tree blocks allocated

	 * in this transaction. So it's now safe to free the redirtyied extent

	 * buffers.

	 */

	btrfs_free_redirty_list(cur_trans);



	ret = write_all_supers(fs_info, 0);

	/*

	 * the super is written, we can safely allow the tree-loggers