Merge pull request #3100 from ThomasWaldmann/compressed-not-larger-1.1

auto compression: make sure expensive compression is actually better

src/borg/compress.pyx

@@ -244,7 +244,7 @@ class Auto(CompressorBase):
         lz4_data = self.lz4.compress(data)
         ratio = len(lz4_data) / len(data)
         if ratio < 0.97:
-            return self.compressor, None
+            return self.compressor, lz4_data
         elif ratio < 1:
             return self.lz4, lz4_data
         else:
@@ -255,9 +255,24 @@ class Auto(CompressorBase):
 
     def compress(self, data):
         compressor, lz4_data = self._decide(data)
-        if lz4_data is None:
-            return compressor.compress(data)
+        if compressor is self.lz4:
+            # we know that trying to compress with expensive compressor is likely pointless,
+            # but lz4 managed to at least squeeze the data a bit.
+            return lz4_data
+        if compressor is self.none:
+            # we know that trying to compress with expensive compressor is likely pointless
+            # and also lz4 did not manage to squeeze the data (not even a bit).
+            uncompressed_data = compressor.compress(data)
+            return uncompressed_data
+        # if we get here, the decider decided to try the expensive compressor.
+        # we also know that lz4_data is smaller than uncompressed data.
+        exp_compressed_data = compressor.compress(data)
+        ratio = len(exp_compressed_data) / len(lz4_data)
+        if ratio < 0.99:
+            # the expensive compressor managed to squeeze the data significantly better than lz4.
+            return exp_compressed_data
         else:
+            # otherwise let's just store the lz4 data, which decompresses extremely fast.
             return lz4_data
 
     def decompress(self, data):

src/borg/testsuite/compress.py

@@ -110,12 +110,18 @@ def test_compressor():
 
 
 def test_auto():
-    compressor = CompressionSpec('auto,zlib,9').compressor
-
-    compressed = compressor.compress(bytes(500))
-    assert Compressor.detect(compressed) == ZLIB
-
-    compressed = compressor.compress(b'\x00\xb8\xa3\xa2-O\xe1i\xb6\x12\x03\xc21\xf3\x8a\xf78\\\x01\xa5b\x07\x95\xbeE\xf8\xa3\x9ahm\xb1~')
+    compressor_auto_zlib = CompressionSpec('auto,zlib,9').compressor
+    compressor_lz4 = CompressionSpec('lz4').compressor
+    compressor_zlib = CompressionSpec('zlib,9').compressor
+    data = bytes(500)
+    compressed_auto_zlib = compressor_auto_zlib.compress(data)
+    compressed_lz4 = compressor_lz4.compress(data)
+    compressed_zlib = compressor_zlib.compress(data)
+    ratio = len(compressed_zlib) / len(compressed_lz4)
+    assert Compressor.detect(compressed_auto_zlib) == ZLIB if ratio < 0.99 else LZ4
+
+    data = b'\x00\xb8\xa3\xa2-O\xe1i\xb6\x12\x03\xc21\xf3\x8a\xf78\\\x01\xa5b\x07\x95\xbeE\xf8\xa3\x9ahm\xb1~'
+    compressed = compressor_auto_zlib.compress(data)
     assert Compressor.detect(compressed) == CNONE