summaryrefslogtreecommitdiff
path: root/git/test/performance/test_streams.py
diff options
context:
space:
mode:
authorAntoine Musso <hashar@free.fr>2014-11-16 20:15:50 +0100
committerAntoine Musso <hashar@free.fr>2014-11-16 20:46:41 +0100
commitf5d11b750ecc982541d1f936488248f0b42d75d3 (patch)
tree8be522510315f5adc32c0c55acd45dc1074294da /git/test/performance/test_streams.py
parent7aba59a2609ec768d5d495dafd23a4bce8179741 (diff)
downloadgitpython-f5d11b750ecc982541d1f936488248f0b42d75d3.tar.gz
pep8 linting (whitespaces)
W191 indentation contains tabs E221 multiple spaces before operator E222 multiple spaces after operator E225 missing whitespace around operator E271 multiple spaces after keyword W292 no newline at end of file W293 blank line contains whitespace W391 blank line at end of file
Diffstat (limited to 'git/test/performance/test_streams.py')
-rw-r--r--git/test/performance/test_streams.py44
1 files changed, 22 insertions, 22 deletions
diff --git a/git/test/performance/test_streams.py b/git/test/performance/test_streams.py
index 93e88841..cac53a06 100644
--- a/git/test/performance/test_streams.py
+++ b/git/test/performance/test_streams.py
@@ -18,16 +18,16 @@ from lib import (
class TestObjDBPerformance(TestBigRepoR):
-
+
large_data_size_bytes = 1000*1000*10 # some MiB should do it
moderate_data_size_bytes = 1000*1000*1 # just 1 MiB
-
+
@with_rw_repo('HEAD', bare=True)
def test_large_data_streaming(self, rwrepo):
# TODO: This part overlaps with the same file in gitdb.test.performance.test_stream
# It should be shared if possible
ldb = LooseObjectDB(os.path.join(rwrepo.git_dir, 'objects'))
-
+
for randomize in range(2):
desc = (randomize and 'random ') or ''
print >> sys.stderr, "Creating %s data ..." % desc
@@ -35,7 +35,7 @@ class TestObjDBPerformance(TestBigRepoR):
size, stream = make_memory_file(self.large_data_size_bytes, randomize)
elapsed = time() - st
print >> sys.stderr, "Done (in %f s)" % elapsed
-
+
# writing - due to the compression it will seem faster than it is
st = time()
binsha = ldb.store(IStream('blob', size, stream)).binsha
@@ -43,22 +43,22 @@ class TestObjDBPerformance(TestBigRepoR):
assert ldb.has_object(binsha)
db_file = ldb.readable_db_object_path(bin_to_hex(binsha))
fsize_kib = os.path.getsize(db_file) / 1000
-
-
+
+
size_kib = size / 1000
print >> sys.stderr, "Added %i KiB (filesize = %i KiB) of %s data to loose odb in %f s ( %f Write KiB / s)" % (size_kib, fsize_kib, desc, elapsed_add, size_kib / elapsed_add)
-
+
# reading all at once
st = time()
ostream = ldb.stream(binsha)
shadata = ostream.read()
elapsed_readall = time() - st
-
+
stream.seek(0)
assert shadata == stream.getvalue()
print >> sys.stderr, "Read %i KiB of %s data at once from loose odb in %f s ( %f Read KiB / s)" % (size_kib, desc, elapsed_readall, size_kib / elapsed_readall)
-
-
+
+
# reading in chunks of 1 MiB
cs = 512*1000
chunks = list()
@@ -71,21 +71,21 @@ class TestObjDBPerformance(TestBigRepoR):
break
# END read in chunks
elapsed_readchunks = time() - st
-
+
stream.seek(0)
assert ''.join(chunks) == stream.getvalue()
-
+
cs_kib = cs / 1000
print >> sys.stderr, "Read %i KiB of %s data in %i KiB chunks from loose odb in %f s ( %f Read KiB / s)" % (size_kib, desc, cs_kib, elapsed_readchunks, size_kib / elapsed_readchunks)
-
+
# del db file so git has something to do
os.remove(db_file)
-
+
# VS. CGIT
##########
# CGIT ! Can using the cgit programs be faster ?
proc = rwrepo.git.hash_object('-w', '--stdin', as_process=True, istream=subprocess.PIPE)
-
+
# write file - pump everything in at once to be a fast as possible
data = stream.getvalue() # cache it
st = time()
@@ -96,15 +96,15 @@ class TestObjDBPerformance(TestBigRepoR):
gelapsed_add = time() - st
del(data)
assert gitsha == bin_to_hex(binsha) # we do it the same way, right ?
-
+
# as its the same sha, we reuse our path
fsize_kib = os.path.getsize(db_file) / 1000
print >> sys.stderr, "Added %i KiB (filesize = %i KiB) of %s data to using git-hash-object in %f s ( %f Write KiB / s)" % (size_kib, fsize_kib, desc, gelapsed_add, size_kib / gelapsed_add)
-
+
# compare ...
print >> sys.stderr, "Git-Python is %f %% faster than git when adding big %s files" % (100.0 - (elapsed_add / gelapsed_add) * 100, desc)
-
-
+
+
# read all
st = time()
s, t, size, data = rwrepo.git.get_object_data(gitsha)
@@ -113,8 +113,8 @@ class TestObjDBPerformance(TestBigRepoR):
# compare
print >> sys.stderr, "Git-Python is %f %% faster than git when reading big %sfiles" % (100.0 - (elapsed_readall / gelapsed_readall) * 100, desc)
-
-
+
+
# read chunks
st = time()
s, t, size, stream = rwrepo.git.stream_object_data(gitsha)
@@ -125,7 +125,7 @@ class TestObjDBPerformance(TestBigRepoR):
# END read stream
gelapsed_readchunks = time() - st
print >> sys.stderr, "Read %i KiB of %s data in %i KiB chunks from git-cat-file in %f s ( %f Read KiB / s)" % (size_kib, desc, cs_kib, gelapsed_readchunks, size_kib / gelapsed_readchunks)
-
+
# compare
print >> sys.stderr, "Git-Python is %f %% faster than git when reading big %s files in chunks" % (100.0 - (elapsed_readchunks / gelapsed_readchunks) * 100, desc)
# END for each randomization factor