diff options
| author | Chris Mason <chris.mason@oracle.com> | 2009-02-12 09:41:38 -0500 |
|---|---|---|
| committer | Chris Mason <chris.mason@oracle.com> | 2009-02-12 09:41:38 -0500 |
| commit | 536ac8ae86e68bb5574d7cc81c7d229a86b82601 (patch) | |
| tree | 2ec565edbbe3cf91e864b83f3fbd0a5bf8c088c4 /fs | |
| parent | b288052e1779261ae80138074989ef50358c4e58 (diff) | |
| download | linux-536ac8ae86e68bb5574d7cc81c7d229a86b82601.tar.gz linux-536ac8ae86e68bb5574d7cc81c7d229a86b82601.tar.bz2 linux-536ac8ae86e68bb5574d7cc81c7d229a86b82601.zip | |
Btrfs: use larger metadata clusters in ssd mode
Larger metadata clusters can significantly improve writeback performance
on ssd drives with large erasure blocks. The larger clusters make it
more likely a given IO will completely overwrite the ssd block, so it
doesn't have to do an internal rwm cycle.
On spinning media, lager metadata clusters end up spreading out the
metadata more over time, which makes fsck slower, so we don't want this
to be the default.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Diffstat (limited to 'fs')
| -rw-r--r-- | fs/btrfs/extent-tree.c | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 376656f65b33..c59e12036e20 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2872,7 +2872,8 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans, if (data & BTRFS_BLOCK_GROUP_METADATA) { last_ptr = &root->fs_info->last_alloc; - empty_cluster = 64 * 1024; + if (!btrfs_test_opt(root, SSD)) + empty_cluster = 64 * 1024; } if ((data & BTRFS_BLOCK_GROUP_DATA) && btrfs_test_opt(root, SSD)) |