1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
|
import gzip
import pytest
import cramjam
import pathlib
import numpy as np
from memory_profiler import profile
FILES = [
f
for f in pathlib.Path("benchmarks/data").iterdir()
if f.is_file() and f.name != "COPYING"
]
class FiftyFourMbRepeating:
"""
54mb of data, where the first 54bytes are repeated 1000000 times.
"""
name = "fifty-four-mb-repeating"
def read_bytes(self):
return b"oh what a beautiful morning, oh what a beautiful day!!" * 1000000
class FiftyFourMbRandom:
"""
54mb of data, all random
"""
name = "fifty-four-mb-random"
def read_bytes(self):
return np.random.randint(0, 255, size=54000000, dtype=np.uint8).tobytes()
FILES.extend([FiftyFourMbRepeating(), FiftyFourMbRandom()])
def round_trip(compress, decompress, data, **kwargs):
return decompress(compress(data, **kwargs))
@pytest.mark.parametrize(
"use_cramjam", (True, False), ids=lambda val: "cramjam" if val else "snappy"
)
@pytest.mark.parametrize("file", FILES, ids=lambda val: val.name)
def test_snappy_raw(benchmark, file, use_cramjam: bool):
"""
Uses snappy compression raw
"""
import snappy
data = file.read_bytes()
if use_cramjam:
benchmark(
round_trip,
compress=cramjam.snappy.compress_raw,
decompress=cramjam.snappy.decompress_raw,
data=data,
)
else:
benchmark(
round_trip,
compress=snappy.compress,
decompress=snappy.decompress,
data=data,
)
@pytest.mark.parametrize(
"use_cramjam", (True, False), ids=lambda val: "cramjam" if val else "snappy"
)
@pytest.mark.parametrize("file", FILES, ids=lambda val: val.name)
def test_snappy_framed(benchmark, file, use_cramjam: bool):
"""
Uses snappy compression framed
"""
import snappy
data = bytearray(file.read_bytes())
if use_cramjam:
benchmark(
round_trip,
compress=cramjam.snappy.compress,
decompress=cramjam.snappy.decompress,
data=data,
)
else:
compressor = snappy.StreamCompressor()
decompressor = snappy.StreamDecompressor()
benchmark(
round_trip,
compress=compressor.compress,
decompress=decompressor.decompress,
data=data,
)
@pytest.mark.parametrize("op", ("decompress_into", "compress_into"))
@pytest.mark.parametrize("file", FILES, ids=lambda val: val.name)
def test_cramjam_snappy_de_compress_into(benchmark, op, file):
"""
Uses decompress_into for snappy compression
"""
from cramjam import snappy
data = file.read_bytes()
compressed_data = bytes(cramjam.snappy.compress(data))
operation = getattr(snappy, op)
buffer = np.zeros(
len(data) if op == "decompress_into" else len(compressed_data),
dtype=np.uint8,
)
benchmark(
lambda data, buffer: operation(data, buffer),
data=compressed_data if op == "decompress_into" else data,
buffer=buffer,
)
@pytest.mark.parametrize("lib", ("gzip", "cramjam", "isal"), ids=lambda val: val)
@pytest.mark.parametrize("file", FILES, ids=lambda val: val.name)
def test_gzip(benchmark, file, lib):
from isal import igzip
data = file.read_bytes()
if lib == "cramjam":
benchmark(
round_trip,
compress=cramjam.gzip.compress,
decompress=cramjam.gzip.decompress,
data=data,
level=3,
)
elif lib == "gzip":
benchmark(
round_trip,
compress=gzip.compress,
decompress=gzip.decompress,
data=data,
compresslevel=3,
)
else:
benchmark(
round_trip,
compress=igzip.compress,
decompress=igzip.decompress,
data=data,
compresslevel=igzip._COMPRESS_LEVEL_BEST, # 3
)
@pytest.mark.parametrize(
"use_cramjam", (True, False), ids=lambda val: "cramjam" if val else "python-lz4"
)
@pytest.mark.parametrize("file", FILES, ids=lambda val: val.name)
def test_lz4(benchmark, file, use_cramjam: bool):
from lz4 import frame
data = file.read_bytes()
if use_cramjam:
benchmark(
round_trip,
compress=cramjam.lz4.compress,
decompress=cramjam.lz4.decompress,
data=data,
level=4,
)
else:
benchmark(
round_trip,
compress=frame.compress,
decompress=frame.decompress,
data=data,
compression_level=4,
)
@pytest.mark.parametrize(
"use_cramjam", (True, False), ids=lambda val: "cramjam" if val else "python-lz4"
)
@pytest.mark.parametrize("file", FILES, ids=lambda val: val.name)
def test_lz4_block(benchmark, file, use_cramjam: bool):
from lz4 import block
data = file.read_bytes()
if use_cramjam:
benchmark(
round_trip,
compress=cramjam.lz4.compress_block,
decompress=cramjam.lz4.decompress_block,
data=data,
)
else:
benchmark(
round_trip,
compress=block.compress,
decompress=block.decompress,
data=data,
)
@pytest.mark.parametrize(
"use_cramjam", (True, False), ids=lambda val: "cramjam" if val else "brotli"
)
@pytest.mark.parametrize(
"file",
[
f
for f in FILES
if not (isinstance(f, (FiftyFourMbRandom, FiftyFourMbRepeating))
],
ids=lambda val: val.name,
)
def test_brotli(benchmark, file, use_cramjam: bool):
import brotli
data = file.read_bytes()
if use_cramjam:
benchmark(
round_trip,
compress=cramjam.brotli.compress,
decompress=cramjam.brotli.decompress,
data=data,
)
else:
benchmark(
round_trip,
compress=brotli.compress,
decompress=brotli.decompress,
data=data,
)
@pytest.mark.parametrize(
"use_cramjam", (True, False), ids=lambda val: "cramjam" if val else "zstd"
)
@pytest.mark.parametrize("file", FILES, ids=lambda val: val.name)
def test_zstd(benchmark, file, use_cramjam: bool):
import zstd
data = file.read_bytes()
if use_cramjam:
benchmark(
round_trip,
compress=cramjam.zstd.compress,
decompress=cramjam.zstd.decompress,
data=data,
)
else:
benchmark(
round_trip,
compress=zstd.compress,
decompress=zstd.decompress,
data=data,
)
@pytest.mark.parametrize(
"use_cramjam", (True, False), ids=lambda val: "cramjam" if val else "bzip2"
)
@pytest.mark.parametrize("file", FILES, ids=lambda val: val.name)
def test_bzip2(benchmark, file, use_cramjam: bool):
import bz2
data = file.read_bytes()
if use_cramjam:
benchmark(
round_trip,
compress=cramjam.bzip2.compress,
decompress=cramjam.bzip2.decompress,
data=data,
)
else:
benchmark(
round_trip,
compress=bz2.compress,
decompress=bz2.decompress,
data=data,
)
@profile
def memory_profile():
import snappy
data = bytearray(FILES[-1].read_bytes())
out1 = bytes(cramjam.snappy.compress_raw(data))
_out1 = bytes(cramjam.snappy.decompress_raw(out1))
out2 = snappy.compress(data)
_ou2 = snappy.decompress(out2)
if __name__ == "__main__":
memory_profile()
|
