btrfs: determine synchronous writers from bio or writeback control

The writeback_control structure already passes down the information about
a writeback being synchronous from the core VM code, and thus information
is propagated into the bio REQ_SYNC flag through the wbc_to_write_flags
helper.

Use that information to decide if checksums calculation is offloaded to
a workqueue instead of btrfs_inode::sync_writers field that not only
bloats the inode but also has too wide scope, being inode wide instead
of limited to the actual writeback request.

The sync writes were set in:

- btrfs_do_write_iter - regular IO, sync status is set
- start_ordered_ops - ordered write start, writeback with WB_SYNC_ALL
  mode
- btrfs_write_marked_extents - write marked extents, writeback with
  WB_SYNC_ALL mode

Reviewed-by: Chris Mason <clm@fb.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: David Sterba <dsterba@suse.com>
[ update changelog ]
Signed-off-by: David Sterba <dsterba@suse.com>

diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c
index 67fb8f6a0eb9f8351ced7172f5f866ce4f5ebbc9..990a517c069be7e82e4d888b9303c15ff2b1bee0 100644 (file)
--- a/fs/btrfs/bio.c
+++ b/fs/btrfs/bio.c
@@ -579,11 +579,10 @@ static bool should_async_write(struct btrfs_bio *bbio)
                return false;
 
        /*
-        * If the I/O is not issued by fsync and friends, (->sync_writers != 0),
-        * then try to defer the submission to a workqueue to parallelize the
-        * checksum calculation.
+        * Try to defer the submission to a workqueue to parallelize the
+        * checksum calculation unless the I/O is issued synchronously.
         */
-       if (atomic_read(&bbio->inode->sync_writers))
+       if (op_is_sync(bbio->bio.bi_opf))
                return false;
 
        /* Zoned devices require I/O to be submitted in order. */

diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index ec2ae4406c16fe7adadd74adfac519fdf48ac4b2..0849b85b94fe964b044708eb2a98fad3a12495e6 100644 (file)
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -116,9 +116,6 @@ struct btrfs_inode {
 
        unsigned long runtime_flags;
 
-       /* Keep track of who's O_SYNC/fsyncing currently */
-       atomic_t sync_writers;
-
        /* full 64 bit generation number, struct vfs_inode doesn't have a big
         * enough field for this.
         */

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index f649647392e0e47c62f030d5c59c74cf633e4fac..f53b7b75092dbdf527145db8e9f4bbabdaed9943 100644 (file)
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1651,7 +1651,6 @@ ssize_t btrfs_do_write_iter(struct kiocb *iocb, struct iov_iter *from,
        struct file *file = iocb->ki_filp;
        struct btrfs_inode *inode = BTRFS_I(file_inode(file));
        ssize_t num_written, num_sync;
-       const bool sync = iocb_is_dsync(iocb);
 
        /*
         * If the fs flips readonly due to some impossible error, although we
@@ -1664,9 +1663,6 @@ ssize_t btrfs_do_write_iter(struct kiocb *iocb, struct iov_iter *from,
        if (encoded && (iocb->ki_flags & IOCB_NOWAIT))
                return -EOPNOTSUPP;
 
-       if (sync)
-               atomic_inc(&inode->sync_writers);
-
        if (encoded) {
                num_written = btrfs_encoded_write(iocb, from, encoded);
                num_sync = encoded->len;
@@ -1686,9 +1682,6 @@ ssize_t btrfs_do_write_iter(struct kiocb *iocb, struct iov_iter *from,
                        num_written = num_sync;
        }
 
-       if (sync)
-               atomic_dec(&inode->sync_writers);
-
        current->backing_dev_info = NULL;
        return num_written;
 }
@@ -1733,9 +1726,7 @@ static int start_ordered_ops(struct inode *inode, loff_t start, loff_t end)
         * several segments of stripe length (currently 64K).
         */
        blk_start_plug(&plug);
-       atomic_inc(&BTRFS_I(inode)->sync_writers);
        ret = btrfs_fdatawrite_range(inode, start, end);
-       atomic_dec(&BTRFS_I(inode)->sync_writers);
        blk_finish_plug(&plug);
 
        return ret;

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index e6a21bbf40f2b7fb698ccb3fd6e29207d676a32d..675b20c4d3c94f857b9f694f63db04b925b68832 100644 (file)
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -8468,7 +8468,6 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
        ei->io_tree.inode = ei;
        extent_io_tree_init(fs_info, &ei->file_extent_tree,
                            IO_TREE_INODE_FILE_EXTENT);
-       atomic_set(&ei->sync_writers, 0);
        mutex_init(&ei->log_mutex);
        btrfs_ordered_inode_tree_init(&ei->ordered_tree);
        INIT_LIST_HEAD(&ei->delalloc_inodes);

diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 8b6a99b8d7f6d3a6722299790e8208f613370320..27c616fdfae274908d9312ed0305086068e81ebf 100644 (file)
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1056,7 +1056,6 @@ int btrfs_write_marked_extents(struct btrfs_fs_info *fs_info,
        u64 start = 0;
        u64 end;
 
-       atomic_inc(&BTRFS_I(fs_info->btree_inode)->sync_writers);
        while (!find_first_extent_bit(dirty_pages, start, &start, &end,
                                      mark, &cached_state)) {
                bool wait_writeback = false;
@@ -1092,7 +1091,6 @@ int btrfs_write_marked_extents(struct btrfs_fs_info *fs_info,
                cond_resched();
                start = end + 1;
        }
-       atomic_dec(&BTRFS_I(fs_info->btree_inode)->sync_writers);
        return werr;
 }