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
|
# test_performance.py
# Copyright (C) 2008, 2009 Michael Trier (mtrier@gmail.com) and contributors
#
# This module is part of GitPython and is released under
# the BSD License: http://www.opensource.org/licenses/bsd-license.php
from io import BytesIO
from time import time
import sys
from .lib import TestBigRepoRW
from git import Commit
from gitdb import IStream
from test.test_commit import TestCommitSerialization
class TestPerformance(TestBigRepoRW, TestCommitSerialization):
def tearDown(self):
import gc
gc.collect()
# ref with about 100 commits in its history
ref_100 = "0.1.6"
def _query_commit_info(self, c):
c.author
c.authored_date
c.author_tz_offset
c.committer
c.committed_date
c.committer_tz_offset
c.message
c.parents
def test_iteration(self):
no = 0
nc = 0
# find the first commit containing the given path - always do a full
# iteration ( restricted to the path in question ), but in fact it should
# return quite a lot of commits, we just take one and hence abort the operation
st = time()
for c in self.rorepo.iter_commits(self.ref_100):
nc += 1
self._query_commit_info(c)
for obj in c.tree.traverse():
obj.size
no += 1
# END for each object
# END for each commit
elapsed_time = time() - st
print(
"Traversed %i Trees and a total of %i uncached objects in %s [s] ( %f objs/s )"
% (nc, no, elapsed_time, no / elapsed_time),
file=sys.stderr,
)
def test_commit_traversal(self):
# bound to cat-file parsing performance
nc = 0
st = time()
for c in self.gitrorepo.commit().traverse(branch_first=False):
nc += 1
self._query_commit_info(c)
# END for each traversed commit
elapsed_time = time() - st
print(
"Traversed %i Commits in %s [s] ( %f commits/s )" % (nc, elapsed_time, nc / elapsed_time),
file=sys.stderr,
)
def test_commit_iteration(self):
# bound to stream parsing performance
nc = 0
st = time()
for c in Commit.iter_items(self.gitrorepo, self.gitrorepo.head):
nc += 1
self._query_commit_info(c)
# END for each traversed commit
elapsed_time = time() - st
print(
"Iterated %i Commits in %s [s] ( %f commits/s )" % (nc, elapsed_time, nc / elapsed_time),
file=sys.stderr,
)
def test_commit_serialization(self):
self.assert_commit_serialization(self.gitrwrepo, "58c78e6", True)
rwrepo = self.gitrwrepo
make_object = rwrepo.odb.store
# direct serialization - deserialization can be tested afterwards
# serialization is probably limited on IO
hc = rwrepo.commit(rwrepo.head)
nc = 5000
st = time()
for i in range(nc):
cm = Commit(
rwrepo,
Commit.NULL_BIN_SHA,
hc.tree,
hc.author,
hc.authored_date,
hc.author_tz_offset,
hc.committer,
hc.committed_date,
hc.committer_tz_offset,
str(i),
parents=hc.parents,
encoding=hc.encoding,
)
stream = BytesIO()
cm._serialize(stream)
slen = stream.tell()
stream.seek(0)
cm.binsha = make_object(IStream(Commit.type, slen, stream)).binsha
# END commit creation
elapsed = time() - st
print(
"Serialized %i commits to loose objects in %f s ( %f commits / s )" % (nc, elapsed, nc / elapsed),
file=sys.stderr,
)
|
