Btrfs: inline csums if we're fsyncing
The tree logging stuff needs the csums to be on the ordered extents in order
to log them properly, so mark that we're sync and inline the csum creation
so we don't have to wait on the csumming to be done when logging extents
that are still in flight. Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 2411baf..2a8c242 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -91,6 +91,9 @@
unsigned long runtime_flags;
+ /* Keep track of who's O_SYNC/fsycing 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 71c2dc1..7f4654a 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1472,6 +1472,7 @@
ssize_t num_written = 0;
ssize_t err = 0;
size_t count, ocount;
+ bool sync = (file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host);
sb_start_write(inode->i_sb);
@@ -1529,6 +1530,9 @@
}
}
+ if (sync)
+ atomic_inc(&BTRFS_I(inode)->sync_writers);
+
if (unlikely(file->f_flags & O_DIRECT)) {
num_written = __btrfs_direct_write(iocb, iov, nr_segs,
pos, ppos, count, ocount);
@@ -1563,6 +1567,8 @@
num_written = err;
}
out:
+ if (sync)
+ atomic_dec(&BTRFS_I(inode)->sync_writers);
sb_end_write(inode->i_sb);
current->backing_dev_info = NULL;
return num_written ? num_written : err;
@@ -1613,7 +1619,9 @@
* out of the ->i_mutex. If so, we can flush the dirty pages by
* multi-task, and make the performance up.
*/
+ atomic_inc(&BTRFS_I(inode)->sync_writers);
ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
+ atomic_dec(&BTRFS_I(inode)->sync_writers);
if (ret)
return ret;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 123815f..7855aac 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1622,6 +1622,7 @@
int ret = 0;
int skip_sum;
int metadata = 0;
+ int async = !atomic_read(&BTRFS_I(inode)->sync_writers);
skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
@@ -1644,7 +1645,7 @@
goto out;
}
goto mapit;
- } else if (!skip_sum) {
+ } else if (async && !skip_sum) {
/* csum items have already been cloned */
if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID)
goto mapit;
@@ -1655,6 +1656,10 @@
__btrfs_submit_bio_start,
__btrfs_submit_bio_done);
goto out;
+ } else if (!skip_sum) {
+ ret = btrfs_csum_one_bio(root, inode, bio, 0, 0);
+ if (ret)
+ goto out;
}
mapit:
@@ -6333,6 +6338,9 @@
struct btrfs_root *root = BTRFS_I(inode)->root;
int ret;
+ if (async_submit)
+ async_submit = !atomic_read(&BTRFS_I(inode)->sync_writers);
+
bio_get(bio);
if (!write) {
@@ -7113,6 +7121,7 @@
extent_io_tree_init(&ei->io_failure_tree, &inode->i_data);
ei->io_tree.track_uptodate = 1;
ei->io_failure_tree.track_uptodate = 1;
+ atomic_set(&ei->sync_writers, 0);
mutex_init(&ei->log_mutex);
mutex_init(&ei->delalloc_mutex);
btrfs_ordered_inode_tree_init(&ei->ordered_tree);