[PATCH v5 5/6] Btrfs: heuristic add byte set calculation
From: Timofey Titovets <hidden>
Date: 2017-08-23 00:27:13
Subsystem:
btrfs file system, filesystems (vfs and infrastructure), the rest · Maintainers:
Chris Mason, David Sterba, Alexander Viro, Christian Brauner, Linus Torvalds
Calculate byte set size for data sample: Calculate how many unique bytes has been in sample By count all bytes in bucket with count > 0 If byte set low (~25%), data are easily compressible Signed-off-by: Timofey Titovets <redacted> --- fs/btrfs/heuristic.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+)
diff --git a/fs/btrfs/heuristic.c b/fs/btrfs/heuristic.c
index 4557ea1db373..953428fde305 100644
--- a/fs/btrfs/heuristic.c
+++ b/fs/btrfs/heuristic.c@@ -31,6 +31,7 @@ */ #define MAX_INPUT_PAGES ((BTRFS_MAX_UNCOMPRESSED >> PAGE_SHIFT)+1) #define MAX_SAMPLE_SIZE (MAX_INPUT_PAGES*PAGE_SIZE*READ_SIZE/ITER_SHIFT) +#define BYTE_SET_THRESHOLD 64 struct bucket_item { u32 count;
@@ -73,6 +74,27 @@ static struct list_head *heuristic_alloc_workspace(void) return ERR_PTR(-ENOMEM); } +static int byte_set_size(const struct workspace *workspace) +{ + int a = 0; + int byte_set_size = 0; + + for (; a < BYTE_SET_THRESHOLD; a++) { + if (workspace->bucket[a].count > 0) + byte_set_size++; + } + + for (; a < BUCKET_SIZE; a++) { + if (workspace->bucket[a].count > 0) { + byte_set_size++; + if (byte_set_size > BYTE_SET_THRESHOLD) + return byte_set_size; + } + } + + return byte_set_size; +} + static bool sample_zeroed(struct workspace *workspace) { u32 i;
@@ -135,6 +157,10 @@ static int heuristic(struct list_head *ws, struct inode *inode, workspace->bucket[byte].count++; } + a = byte_set_size(workspace); + if (a > BYTE_SET_THRESHOLD) + return 2; + return 1; } --
2.14.1