Btrfs: add new defrag-range ioctl.
The btrfs defrag ioctl was limited to doing the entire file. This commit adds a new interface that can defrag a specific range inside the file. It can also force compression on the file, allowing you to selectively compress individual files after they were created, even when mount -o compress isn't turned on. Signed-off-by: Chris Mason <chris.mason@oracle.com>
This commit is contained in:
parent
940100a4a7
commit
1e701a3292
|
@ -153,6 +153,11 @@ struct btrfs_inode {
|
|||
unsigned ordered_data_close:1;
|
||||
unsigned dummy_inode:1;
|
||||
|
||||
/*
|
||||
* always compress this one file
|
||||
*/
|
||||
unsigned force_compress:1;
|
||||
|
||||
struct inode vfs_inode;
|
||||
};
|
||||
|
||||
|
|
|
@ -1184,7 +1184,6 @@ struct btrfs_root {
|
|||
#define BTRFS_INODE_NOATIME (1 << 9)
|
||||
#define BTRFS_INODE_DIRSYNC (1 << 10)
|
||||
|
||||
|
||||
/* some macros to generate set/get funcs for the struct fields. This
|
||||
* assumes there is a lefoo_to_cpu for every type, so lets make a simple
|
||||
* one for u8:
|
||||
|
|
|
@ -379,7 +379,8 @@ again:
|
|||
* change at any time if we discover bad compression ratios.
|
||||
*/
|
||||
if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS) &&
|
||||
btrfs_test_opt(root, COMPRESS)) {
|
||||
(btrfs_test_opt(root, COMPRESS) ||
|
||||
(BTRFS_I(inode)->force_compress))) {
|
||||
WARN_ON(pages);
|
||||
pages = kzalloc(sizeof(struct page *) * nr_pages, GFP_NOFS);
|
||||
|
||||
|
@ -483,8 +484,10 @@ again:
|
|||
nr_pages_ret = 0;
|
||||
|
||||
/* flag the file so we don't compress in the future */
|
||||
if (!btrfs_test_opt(root, FORCE_COMPRESS))
|
||||
if (!btrfs_test_opt(root, FORCE_COMPRESS) &&
|
||||
!(BTRFS_I(inode)->force_compress)) {
|
||||
BTRFS_I(inode)->flags |= BTRFS_INODE_NOCOMPRESS;
|
||||
}
|
||||
}
|
||||
if (will_compress) {
|
||||
*num_added += 1;
|
||||
|
@ -1211,7 +1214,8 @@ static int run_delalloc_range(struct inode *inode, struct page *locked_page,
|
|||
else if (BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC)
|
||||
ret = run_delalloc_nocow(inode, locked_page, start, end,
|
||||
page_started, 0, nr_written);
|
||||
else if (!btrfs_test_opt(root, COMPRESS))
|
||||
else if (!btrfs_test_opt(root, COMPRESS) &&
|
||||
!(BTRFS_I(inode)->force_compress))
|
||||
ret = cow_file_range(inode, locked_page, start, end,
|
||||
page_started, nr_written, 1);
|
||||
else
|
||||
|
@ -3639,6 +3643,7 @@ static noinline void init_btrfs_i(struct inode *inode)
|
|||
bi->index_cnt = (u64)-1;
|
||||
bi->last_unlink_trans = 0;
|
||||
bi->ordered_data_close = 0;
|
||||
bi->force_compress = 0;
|
||||
extent_map_tree_init(&BTRFS_I(inode)->extent_tree, GFP_NOFS);
|
||||
extent_io_tree_init(&BTRFS_I(inode)->io_tree,
|
||||
inode->i_mapping, GFP_NOFS);
|
||||
|
|
|
@ -476,13 +476,18 @@ out_unlock:
|
|||
}
|
||||
|
||||
static int should_defrag_range(struct inode *inode, u64 start, u64 len,
|
||||
u64 *last_len, u64 *skip, u64 *defrag_end)
|
||||
int thresh, u64 *last_len, u64 *skip,
|
||||
u64 *defrag_end)
|
||||
{
|
||||
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
|
||||
struct extent_map *em = NULL;
|
||||
struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
|
||||
int ret = 1;
|
||||
|
||||
|
||||
if (thresh == 0)
|
||||
thresh = 256 * 1024;
|
||||
|
||||
/*
|
||||
* make sure that once we start defragging and extent, we keep on
|
||||
* defragging it
|
||||
|
@ -517,8 +522,7 @@ static int should_defrag_range(struct inode *inode, u64 start, u64 len,
|
|||
/*
|
||||
* we hit a real extent, if it is big don't bother defragging it again
|
||||
*/
|
||||
if ((*last_len == 0 || *last_len >= 256 * 1024) &&
|
||||
em->len >= 256 * 1024)
|
||||
if ((*last_len == 0 || *last_len >= thresh) && em->len >= thresh)
|
||||
ret = 0;
|
||||
|
||||
/*
|
||||
|
@ -542,7 +546,8 @@ static int should_defrag_range(struct inode *inode, u64 start, u64 len,
|
|||
return ret;
|
||||
}
|
||||
|
||||
static int btrfs_defrag_file(struct file *file)
|
||||
static int btrfs_defrag_file(struct file *file,
|
||||
struct btrfs_ioctl_defrag_range_args *range)
|
||||
{
|
||||
struct inode *inode = fdentry(file)->d_inode;
|
||||
struct btrfs_root *root = BTRFS_I(inode)->root;
|
||||
|
@ -563,11 +568,19 @@ static int btrfs_defrag_file(struct file *file)
|
|||
if (inode->i_size == 0)
|
||||
return 0;
|
||||
|
||||
last_index = (inode->i_size - 1) >> PAGE_CACHE_SHIFT;
|
||||
i = 0;
|
||||
if (range->start + range->len > range->start) {
|
||||
last_index = min_t(u64, inode->i_size - 1,
|
||||
range->start + range->len - 1) >> PAGE_CACHE_SHIFT;
|
||||
} else {
|
||||
last_index = (inode->i_size - 1) >> PAGE_CACHE_SHIFT;
|
||||
}
|
||||
|
||||
i = range->start >> PAGE_CACHE_SHIFT;
|
||||
while (i <= last_index) {
|
||||
if (!should_defrag_range(inode, (u64)i << PAGE_CACHE_SHIFT,
|
||||
PAGE_CACHE_SIZE, &last_len, &skip,
|
||||
PAGE_CACHE_SIZE,
|
||||
range->extent_thresh,
|
||||
&last_len, &skip,
|
||||
&defrag_end)) {
|
||||
unsigned long next;
|
||||
/*
|
||||
|
@ -585,6 +598,8 @@ static int btrfs_defrag_file(struct file *file)
|
|||
}
|
||||
total_read++;
|
||||
mutex_lock(&inode->i_mutex);
|
||||
if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)
|
||||
BTRFS_I(inode)->force_compress = 1;
|
||||
|
||||
ret = btrfs_check_data_free_space(root, inode, PAGE_CACHE_SIZE);
|
||||
if (ret) {
|
||||
|
@ -673,6 +688,28 @@ loop_unlock:
|
|||
i++;
|
||||
}
|
||||
|
||||
if ((range->flags & BTRFS_DEFRAG_RANGE_START_IO))
|
||||
filemap_flush(inode->i_mapping);
|
||||
|
||||
if ((range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)) {
|
||||
/* the filemap_flush will queue IO into the worker threads, but
|
||||
* we have to make sure the IO is actually started and that
|
||||
* ordered extents get created before we return
|
||||
*/
|
||||
atomic_inc(&root->fs_info->async_submit_draining);
|
||||
while (atomic_read(&root->fs_info->nr_async_submits) ||
|
||||
atomic_read(&root->fs_info->async_delalloc_pages)) {
|
||||
wait_event(root->fs_info->async_submit_wait,
|
||||
(atomic_read(&root->fs_info->nr_async_submits) == 0 &&
|
||||
atomic_read(&root->fs_info->async_delalloc_pages) == 0));
|
||||
}
|
||||
atomic_dec(&root->fs_info->async_submit_draining);
|
||||
|
||||
mutex_lock(&inode->i_mutex);
|
||||
BTRFS_I(inode)->force_compress = 0;
|
||||
mutex_unlock(&inode->i_mutex);
|
||||
}
|
||||
|
||||
return 0;
|
||||
|
||||
err_reservations:
|
||||
|
@ -1284,10 +1321,11 @@ out:
|
|||
return err;
|
||||
}
|
||||
|
||||
static int btrfs_ioctl_defrag(struct file *file)
|
||||
static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
|
||||
{
|
||||
struct inode *inode = fdentry(file)->d_inode;
|
||||
struct btrfs_root *root = BTRFS_I(inode)->root;
|
||||
struct btrfs_ioctl_defrag_range_args *range;
|
||||
int ret;
|
||||
|
||||
ret = mnt_want_write(file->f_path.mnt);
|
||||
|
@ -1308,7 +1346,30 @@ static int btrfs_ioctl_defrag(struct file *file)
|
|||
ret = -EINVAL;
|
||||
goto out;
|
||||
}
|
||||
btrfs_defrag_file(file);
|
||||
|
||||
range = kzalloc(sizeof(*range), GFP_KERNEL);
|
||||
if (!range) {
|
||||
ret = -ENOMEM;
|
||||
goto out;
|
||||
}
|
||||
|
||||
if (argp) {
|
||||
if (copy_from_user(range, argp,
|
||||
sizeof(*range))) {
|
||||
ret = -EFAULT;
|
||||
kfree(range);
|
||||
}
|
||||
/* compression requires us to start the IO */
|
||||
if ((range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)) {
|
||||
range->flags |= BTRFS_DEFRAG_RANGE_START_IO;
|
||||
range->extent_thresh = (u32)-1;
|
||||
}
|
||||
} else {
|
||||
/* the rest are all set to zero by kzalloc */
|
||||
range->len = (u64)-1;
|
||||
}
|
||||
btrfs_defrag_file(file, range);
|
||||
kfree(range);
|
||||
break;
|
||||
}
|
||||
out:
|
||||
|
@ -1831,7 +1892,9 @@ long btrfs_ioctl(struct file *file, unsigned int
|
|||
case BTRFS_IOC_DEFAULT_SUBVOL:
|
||||
return btrfs_ioctl_default_subvol(file, argp);
|
||||
case BTRFS_IOC_DEFRAG:
|
||||
return btrfs_ioctl_defrag(file);
|
||||
return btrfs_ioctl_defrag(file, NULL);
|
||||
case BTRFS_IOC_DEFRAG_RANGE:
|
||||
return btrfs_ioctl_defrag(file, argp);
|
||||
case BTRFS_IOC_RESIZE:
|
||||
return btrfs_ioctl_resize(root, argp);
|
||||
case BTRFS_IOC_ADD_DEV:
|
||||
|
|
|
@ -99,6 +99,35 @@ struct btrfs_ioctl_clone_range_args {
|
|||
__u64 dest_offset;
|
||||
};
|
||||
|
||||
/* flags for the defrag range ioctl */
|
||||
#define BTRFS_DEFRAG_RANGE_COMPRESS 1
|
||||
#define BTRFS_DEFRAG_RANGE_START_IO 2
|
||||
|
||||
struct btrfs_ioctl_defrag_range_args {
|
||||
/* start of the defrag operation */
|
||||
__u64 start;
|
||||
|
||||
/* number of bytes to defrag, use (u64)-1 to say all */
|
||||
__u64 len;
|
||||
|
||||
/*
|
||||
* flags for the operation, which can include turning
|
||||
* on compression for this one defrag
|
||||
*/
|
||||
__u64 flags;
|
||||
|
||||
/*
|
||||
* any extent bigger than this will be considered
|
||||
* already defragged. Use 0 to take the kernel default
|
||||
* Use 1 to say every single extent must be rewritten
|
||||
*/
|
||||
__u32 extent_thresh;
|
||||
|
||||
/* spare for later */
|
||||
__u32 unused[5];
|
||||
};
|
||||
|
||||
|
||||
#define BTRFS_IOC_SNAP_CREATE _IOW(BTRFS_IOCTL_MAGIC, 1, \
|
||||
struct btrfs_ioctl_vol_args)
|
||||
#define BTRFS_IOC_DEFRAG _IOW(BTRFS_IOCTL_MAGIC, 2, \
|
||||
|
@ -130,6 +159,8 @@ struct btrfs_ioctl_clone_range_args {
|
|||
struct btrfs_ioctl_vol_args)
|
||||
#define BTRFS_IOC_SNAP_DESTROY _IOW(BTRFS_IOCTL_MAGIC, 15, \
|
||||
struct btrfs_ioctl_vol_args)
|
||||
#define BTRFS_IOC_DEFRAG_RANGE _IOW(BTRFS_IOCTL_MAGIC, 16, \
|
||||
struct btrfs_ioctl_defrag_range_args)
|
||||
#define BTRFS_IOC_TREE_SEARCH _IOWR(BTRFS_IOCTL_MAGIC, 17, \
|
||||
struct btrfs_ioctl_search_args)
|
||||
#define BTRFS_IOC_INO_LOOKUP _IOWR(BTRFS_IOCTL_MAGIC, 18, \
|
||||
|
|
Loading…
Reference in New Issue