Btrfs: qgroup, Account data space in more proper timings.

Currenly, in data writing, ->reserved is accounted in
fill_delalloc(), but ->may_use is released in clear_bit_hook()
which is called by btrfs_finish_ordered_io(). That's too late,
that said, between fill_delalloc() and btrfs_finish_ordered_io(),
the data is doublely accounted by qgroup. It will cause some
unexpected -EDQUOT.

Example:
	# btrfs quota enable /root/btrfs-auto-test/
	# btrfs subvolume create /root/btrfs-auto-test//sub
	Create subvolume '/root/btrfs-auto-test/sub'
	# btrfs qgroup limit 1G /root/btrfs-auto-test//sub
	dd if=/dev/zero of=/root/btrfs-auto-test//sub/file bs=1024 count=1500000
	dd: error writing '/root/btrfs-auto-test//sub/file': Disk quota exceeded
	681353+0 records in
	681352+0 records out
	697704448 bytes (698 MB) copied, 8.15563 s, 85.5 MB/s
It's (698 MB) when we got an -EDQUOT, but we limit it by 1G.

This patch move the btrfs_qgroup_reserve/free() for data from
btrfs_delalloc_reserve/release_metadata() to btrfs_check_data_free_space()
and btrfs_free_reserved_data_space(). Then the accounter in qgroup
will be updated at the same time with the accounter in space_info updated.
In this way, the unexpected -EDQUOT will be killed.

Reported-by: Satoru Takeuchi <takeuchi_satoru@jp.fujitsu.com>
Signed-off-by: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 3113e0b..4d37746 100644 (file)
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3969,12 +3969,16 @@ commit_trans:
                                              data_sinfo->flags, bytes, 1);
                return -ENOSPC;
        }
+       ret = btrfs_qgroup_reserve(root, bytes);
+       if (ret)
+               goto out;
        data_sinfo->bytes_may_use += bytes;
        trace_btrfs_space_reservation(root->fs_info, "space_info",
                                      data_sinfo->flags, bytes, 1);
+out:
        spin_unlock(&data_sinfo->lock);
 
-       return 0;
+       return ret;
 }
 
 /*
@@ -3991,6 +3995,7 @@ void btrfs_free_reserved_data_space(struct inode *inode, u64 bytes)
        data_sinfo = root->fs_info->data_sinfo;
        spin_lock(&data_sinfo->lock);
        WARN_ON(data_sinfo->bytes_may_use < bytes);
+       btrfs_qgroup_free(root, bytes);
        data_sinfo->bytes_may_use -= bytes;
        trace_btrfs_space_reservation(root->fs_info, "space_info",
                                      data_sinfo->flags, bytes, 0);
@@ -5391,8 +5396,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
        spin_unlock(&BTRFS_I(inode)->lock);
 
        if (root->fs_info->quota_enabled) {
-               ret = btrfs_qgroup_reserve(root, num_bytes +
-                                          nr_extents * root->nodesize);
+               ret = btrfs_qgroup_reserve(root, nr_extents * root->nodesize);
                if (ret)
                        goto out_fail;
        }
@@ -5400,8 +5404,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
        ret = reserve_metadata_bytes(root, block_rsv, to_reserve, flush);
        if (unlikely(ret)) {
                if (root->fs_info->quota_enabled)
-                       btrfs_qgroup_free(root, num_bytes +
-                                               nr_extents * root->nodesize);
+                       btrfs_qgroup_free(root, nr_extents * root->nodesize);
                goto out_fail;
        }
 
@@ -5522,8 +5525,7 @@ void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes)
        trace_btrfs_space_reservation(root->fs_info, "delalloc",
                                      btrfs_ino(inode), to_free, 0);
        if (root->fs_info->quota_enabled) {
-               btrfs_qgroup_free(root, num_bytes +
-                                       dropped * root->nodesize);
+               btrfs_qgroup_free(root, dropped * root->nodesize);
        }
 
        btrfs_block_rsv_release(root, &root->fs_info->delalloc_block_rsv,

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index fd105c1..faef1d6 100644 (file)
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2549,7 +2549,6 @@ static long btrfs_fallocate(struct file *file, int mode,
 {
        struct inode *inode = file_inode(file);
        struct extent_state *cached_state = NULL;
-       struct btrfs_root *root = BTRFS_I(inode)->root;
        u64 cur_offset;
        u64 last_byte;
        u64 alloc_start;
@@ -2577,11 +2576,6 @@ static long btrfs_fallocate(struct file *file, int mode,
        ret = btrfs_check_data_free_space(inode, alloc_end - alloc_start);
        if (ret)
                return ret;
-       if (root->fs_info->quota_enabled) {
-               ret = btrfs_qgroup_reserve(root, alloc_end - alloc_start);
-               if (ret)
-                       goto out_reserve_fail;
-       }
 
        mutex_lock(&inode->i_mutex);
        ret = inode_newsize_ok(inode, alloc_end);
@@ -2674,6 +2668,7 @@ static long btrfs_fallocate(struct file *file, int mode,
                } else if (actual_end > inode->i_size &&
                           !(mode & FALLOC_FL_KEEP_SIZE)) {
                        struct btrfs_trans_handle *trans;
+                       struct btrfs_root *root = BTRFS_I(inode)->root;
 
                        /*
                         * We didn't need to allocate any more space, but we
@@ -2710,9 +2705,6 @@ static long btrfs_fallocate(struct file *file, int mode,
                             &cached_state, GFP_NOFS);
 out:
        mutex_unlock(&inode->i_mutex);
-       if (root->fs_info->quota_enabled)
-               btrfs_qgroup_free(root, alloc_end - alloc_start);
-out_reserve_fail:
        /* Let go of our reservation. */
        btrfs_free_reserved_data_space(inode, alloc_end - alloc_start);
        return ret;