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
|
#!/usr/bin/env python
#
# benchmark.py - benchmark indexed_gzip
#
# Author: Paul McCarthy <pauldmccarthy@gmail.com>
#
from __future__ import print_function
import os
import os.path as op
import sys
import gzip
import time
import shutil
import hashlib
import tempfile
import argparse
import contextlib
import numpy as np
import indexed_gzip as igzip
@contextlib.contextmanager
def tempdir():
testdir = tempfile.mkdtemp()
prevdir = os.getcwd()
try:
os.chdir(testdir)
yield testdir
finally:
os.chdir(prevdir)
shutil.rmtree(testdir)
def size(filename):
with open(filename, 'rb') as f:
f.seek(-1, 2)
return f.tell()
def gen_file(fname, nbytes):
nelems = int(nbytes / 4)
data = np.random.randint(0, 2 ** 32, nelems, dtype=np.uint32)
# zero out 10% so there is something to compress
zeros = np.random.randint(0, nelems, int(nelems / 10.0))
data[zeros] = 0
data = data.tobytes()
# write 1GB max at a time - the gzip
# module doesn't like writing >= 4GB
# in one go.
chunksize = 1073741824
while len(data) > 0:
chunk = data[:chunksize]
data = data[chunksize:]
with gzip.open(fname, 'ab') as outf:
outf.write(chunk)
def benchmark_file(fobj, seeks, lens, update):
start = time.time()
hashobj = hashlib.md5()
for i, (s, l) in enumerate(zip(seeks, lens)):
fobj.seek(s)
data = fobj.read(l)
hashobj.update(data)
update(i)
update(len(seeks))
end = time.time()
elapsed = end - start
return str(hashobj.hexdigest()), elapsed
def benchmark(filename, nseeks):
nbytes = size(filename)
seeks = np.linspace(0, nbytes, nseeks, dtype=int)
lens = np.random.randint(1048576, 16777216, nseeks)
np.random.shuffle(seeks)
names = [
'GzipFile',
'IndexedGzipFile(drop_handles=True)',
'IndexedGzipFile(drop_handles=False)'
]
namelen = max([len(n) for n in names])
namefmt = '{{:<{}s}}'.format(namelen)
fobjs = [
lambda : gzip.GzipFile( filename, 'rb'),
lambda : igzip.IndexedGzipFile(filename, drop_handles=True),
lambda : igzip.IndexedGzipFile(filename, drop_handles=False),
]
for name, fobj in zip(names, fobjs):
def update(i):
print('\r{} {:6.2f}%'.format(
namefmt.format(name),
100.0 * i / len(seeks)), end='')
sys.stdout.flush()
with fobj() as f:
md5, time = benchmark_file(f, seeks, lens, update)
print(' {} {:0.0f}s'.format(md5, time))
if __name__ == '__main__':
parser = argparse.ArgumentParser('indexe_gzip benchmark')
parser.add_argument('-b',
'--bytes',
type=int,
help='Uncompressed size of test file in bytes. '
'Ignored if a --file is specified',
default=16777216)
parser.add_argument('-s',
'--seeks',
type=int,
help='Number of random seeks',
default=1000)
parser.add_argument('-f',
'--file',
type=str,
help='Test file (default: generate one)')
parser.add_argument('-r',
'--randomseed',
type=int,
help='Seed for random number generator')
namespace = parser.parse_args()
if namespace.randomseed is not None:
np.random.seed(namespace.seed)
if namespace.file is not None:
namespace.file = op.abspath(namespace.file)
with tempdir():
if namespace.file is None:
print('Generating test data ({:0.2f} MiB)...'.format(
namespace.bytes / (1024 * 1024)), end='')
sys.stdout.flush()
namespace.file = 'test.gz'
gen_file(namespace.file, namespace.bytes)
print(' {:0.2f} MiB compressed'.format(
size(namespace.file) / (1024 * 1024)))
if namespace.randomseed is not None:
np.random.seed(namespace.seed)
benchmark(namespace.file, namespace.seeks)
|