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
Otherwise need additional analize
Signed-off-by: Timofey Titovets <nefelim...@gmail.com>
---
fs/btrfs/compression.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 48 insertions(+)
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 1cb4df023d5e..83daf2f9d051 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -1201,6 +1201,48 @@ int btrfs_decompress_buf2page(const char *buf, unsigned
long buf_start,
}
+/*
+ * Count byte types in bucket
+ * That heuristic can detect text like data (configs, xml, json, html & etc)
+ * Because in most text like data byte set are restricted to limit number
+ * of possible characters, and that restriction in most cases
+ * make data easy compressible.
+ *
+ * @BYTE_SET_THRESHOLD - assume that all data with that byte set size:
+ * less - compressible
+ * more - need additional analize
+ */
+
+#define BYTE_SET_THRESHOLD 64
+
+static u32 byte_set_size(const struct heuristic_ws *ws)
+{
+ u32 i;
+ u32 byte_set_size = 0;
+
+ for (i = 0; i < BYTE_SET_THRESHOLD; i++) {
+ if (ws->bucket[i].count > 0)
+ byte_set_size++;
+ }
+
+ /*
+ * Continue collecting count of byte types in bucket
+ * If byte set size bigger then threshold
+ * That useless to continue, because for that data type
+ * detection technique fail
+ */
+ for (; i < BUCKET_SIZE; i++) {
+ if (ws->bucket[i].count > 0) {
+ byte_set_size++;
+ if (byte_set_size > BYTE_SET_THRESHOLD)
+ return byte_set_size;
+ }
+ }
+
+ return byte_set_size;
+}
+
+
static bool sample_repeated_patterns(struct heuristic_ws *ws)
{
u32 half_of_sample = ws->sample_size / 2;
@@ -1300,6 +1342,12 @@ int btrfs_compress_heuristic(struct inode *inode, u64
start, u64 end)
ws->bucket[byte].count++;
}
+ i = byte_set_size(ws);
+ if (i < BYTE_SET_THRESHOLD) {
+ ret = 2;
+ goto out;
+ }
+
out:
__free_workspace(0, ws_list, true);
return ret;
--
2.14.2
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
