Show More
@@ -1,139 +1,146 b'' | |||||
1 | # -*- coding: utf-8 -*- |
|
1 | # -*- coding: utf-8 -*- | |
2 | """ |
|
2 | """ | |
3 | rhodecode.tests.test_crawer |
|
3 | rhodecode.tests.test_crawer | |
4 | ~~~~~~~~~~~~~~~~~~~~~~~~~~~ |
|
4 | ~~~~~~~~~~~~~~~~~~~~~~~~~~~ | |
5 |
|
5 | |||
6 | Test for crawling a project for memory usage |
|
6 | Test for crawling a project for memory usage | |
7 |
|
7 | |||
8 | watch -n1 ./rhodecode/tests/mem_watch |
|
8 | watch -n1 ./rhodecode/tests/mem_watch | |
9 |
|
9 | |||
10 | :created_on: Apr 21, 2010 |
|
10 | :created_on: Apr 21, 2010 | |
11 | :author: marcink |
|
11 | :author: marcink | |
12 | :copyright: (C) 2009-2011 Marcin Kuzminski <marcin@python-works.com> |
|
12 | :copyright: (C) 2009-2011 Marcin Kuzminski <marcin@python-works.com> | |
13 | :license: GPLv3, see COPYING for more details. |
|
13 | :license: GPLv3, see COPYING for more details. | |
14 | """ |
|
14 | """ | |
15 | # This program is free software: you can redistribute it and/or modify |
|
15 | # This program is free software: you can redistribute it and/or modify | |
16 | # it under the terms of the GNU General Public License as published by |
|
16 | # it under the terms of the GNU General Public License as published by | |
17 | # the Free Software Foundation, either version 3 of the License, or |
|
17 | # the Free Software Foundation, either version 3 of the License, or | |
18 | # (at your option) any later version. |
|
18 | # (at your option) any later version. | |
19 | # |
|
19 | # | |
20 | # This program is distributed in the hope that it will be useful, |
|
20 | # This program is distributed in the hope that it will be useful, | |
21 | # but WITHOUT ANY WARRANTY; without even the implied warranty of |
|
21 | # but WITHOUT ANY WARRANTY; without even the implied warranty of | |
22 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
|
22 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
23 | # GNU General Public License for more details. |
|
23 | # GNU General Public License for more details. | |
24 | # |
|
24 | # | |
25 | # You should have received a copy of the GNU General Public License |
|
25 | # You should have received a copy of the GNU General Public License | |
26 | # along with this program. If not, see <http://www.gnu.org/licenses/>. |
|
26 | # along with this program. If not, see <http://www.gnu.org/licenses/>. | |
27 |
|
27 | |||
28 |
|
28 | |||
29 | import cookielib |
|
29 | import cookielib | |
30 | import urllib |
|
30 | import urllib | |
31 | import urllib2 |
|
31 | import urllib2 | |
32 | import vcs |
|
32 | import vcs | |
33 | import time |
|
33 | import time | |
34 |
|
34 | |||
35 | from os.path import join as jn |
|
35 | from os.path import join as jn | |
36 |
|
36 | |||
37 |
|
37 | |||
38 | BASE_URI = 'http://127.0.0.1:5000/%s' |
|
38 | BASE_URI = 'http://127.0.0.1:5000/%s' | |
39 | PROJECT = 'CPython' |
|
39 | PROJECT = 'CPython' | |
40 | PROJECT_PATH = jn('/', 'home', 'marcink', 'hg_repos') |
|
40 | PROJECT_PATH = jn('/', 'home', 'marcink', 'hg_repos') | |
41 |
|
41 | |||
42 |
|
42 | |||
43 | cj = cookielib.FileCookieJar('/tmp/rc_test_cookie.txt') |
|
43 | cj = cookielib.FileCookieJar('/tmp/rc_test_cookie.txt') | |
44 | o = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj)) |
|
44 | o = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj)) | |
45 | o.addheaders = [ |
|
45 | o.addheaders = [ | |
46 | ('User-agent', 'rhodecode-crawler'), |
|
46 | ('User-agent', 'rhodecode-crawler'), | |
47 | ('Accept-Language', 'en - us, en;q = 0.5') |
|
47 | ('Accept-Language', 'en - us, en;q = 0.5') | |
48 | ] |
|
48 | ] | |
49 |
|
49 | |||
50 | urllib2.install_opener(o) |
|
50 | urllib2.install_opener(o) | |
51 |
|
51 | |||
52 |
|
52 | |||
53 |
|
53 | |||
54 | def test_changelog_walk(pages=100): |
|
54 | def test_changelog_walk(pages=100): | |
55 | total_time = 0 |
|
55 | total_time = 0 | |
56 | for i in range(1, pages): |
|
56 | for i in range(1, pages): | |
57 |
|
57 | |||
58 | page = '/'.join((PROJECT, 'changelog',)) |
|
58 | page = '/'.join((PROJECT, 'changelog',)) | |
59 |
|
59 | |||
60 | full_uri = (BASE_URI % page) + '?' + urllib.urlencode({'page':i}) |
|
60 | full_uri = (BASE_URI % page) + '?' + urllib.urlencode({'page':i}) | |
61 | s = time.time() |
|
61 | s = time.time() | |
62 | f = o.open(full_uri) |
|
62 | f = o.open(full_uri) | |
63 | size = len(f.read()) |
|
63 | size = len(f.read()) | |
64 | e = time.time() - s |
|
64 | e = time.time() - s | |
65 | total_time += e |
|
65 | total_time += e | |
66 | print 'visited %s size:%s req:%s ms' % (full_uri, size, e) |
|
66 | print 'visited %s size:%s req:%s ms' % (full_uri, size, e) | |
67 |
|
67 | |||
68 |
|
68 | |||
69 | print 'total_time', total_time |
|
69 | print 'total_time', total_time | |
70 | print 'average on req', total_time / float(pages) |
|
70 | print 'average on req', total_time / float(pages) | |
71 |
|
71 | |||
72 |
|
72 | |||
73 | def test_changeset_walk(limit=None): |
|
73 | def test_changeset_walk(limit=None): | |
74 | print 'processing', jn(PROJECT_PATH, PROJECT) |
|
74 | print 'processing', jn(PROJECT_PATH, PROJECT) | |
75 | total_time = 0 |
|
75 | total_time = 0 | |
76 |
|
76 | |||
77 | repo = vcs.get_repo(jn(PROJECT_PATH, PROJECT)) |
|
77 | repo = vcs.get_repo(jn(PROJECT_PATH, PROJECT)) | |
78 | cnt = 0 |
|
78 | cnt = 0 | |
79 | for i in repo: |
|
79 | for i in repo: | |
80 | cnt += 1 |
|
80 | cnt += 1 | |
81 | raw_cs = '/'.join((PROJECT, 'changeset', i.raw_id)) |
|
81 | raw_cs = '/'.join((PROJECT, 'changeset', i.raw_id)) | |
82 | if limit and limit == cnt: |
|
82 | if limit and limit == cnt: | |
83 | break |
|
83 | break | |
84 |
|
84 | |||
85 | full_uri = (BASE_URI % raw_cs) |
|
85 | full_uri = (BASE_URI % raw_cs) | |
86 | s = time.time() |
|
86 | s = time.time() | |
87 | f = o.open(full_uri) |
|
87 | f = o.open(full_uri) | |
88 | size = len(f.read()) |
|
88 | size = len(f.read()) | |
89 | e = time.time() - s |
|
89 | e = time.time() - s | |
90 | total_time += e |
|
90 | total_time += e | |
91 | print 'visited %s\%s size:%s req:%s ms' % (full_uri, i, size, e) |
|
91 | print '%s visited %s\%s size:%s req:%s ms' % (cnt, full_uri, i, size, e) | |
92 |
|
92 | |||
93 | print 'total_time', total_time |
|
93 | print 'total_time', total_time | |
94 | print 'average on req', total_time / float(cnt) |
|
94 | print 'average on req', total_time / float(cnt) | |
95 |
|
95 | |||
96 |
|
96 | |||
97 | def test_files_walk(): |
|
97 | def test_files_walk(limit=100): | |
98 | print 'processing', jn(PROJECT_PATH, PROJECT) |
|
98 | print 'processing', jn(PROJECT_PATH, PROJECT) | |
99 | total_time = 0 |
|
99 | total_time = 0 | |
100 |
|
100 | |||
101 | repo = vcs.get_repo(jn(PROJECT_PATH, PROJECT)) |
|
101 | repo = vcs.get_repo(jn(PROJECT_PATH, PROJECT)) | |
102 |
|
102 | |||
103 | from rhodecode.lib.oset import OrderedSet |
|
103 | from rhodecode.lib.oset import OrderedSet | |
104 |
|
104 | |||
105 | paths_ = OrderedSet(['']) |
|
105 | paths_ = OrderedSet(['']) | |
106 | try: |
|
106 | try: | |
107 | tip = repo.get_changeset('tip') |
|
107 | tip = repo.get_changeset('tip') | |
108 | for topnode, dirs, files in tip.walk('/'): |
|
108 | for topnode, dirs, files in tip.walk('/'): | |
109 |
|
109 | |||
110 | for dir in dirs: |
|
110 | for dir in dirs: | |
111 | paths_.add(dir.path) |
|
111 | paths_.add(dir.path) | |
112 | for f in dir: |
|
112 | for f in dir: | |
113 | paths_.add(f.path) |
|
113 | paths_.add(f.path) | |
114 |
|
114 | |||
115 | for f in files: |
|
115 | for f in files: | |
116 | paths_.add(f.path) |
|
116 | paths_.add(f.path) | |
117 |
|
117 | |||
118 | except vcs.exception.RepositoryError, e: |
|
118 | except vcs.exception.RepositoryError, e: | |
119 | pass |
|
119 | pass | |
120 |
|
120 | |||
|
121 | cnt = 0 | |||
121 | for f in paths_: |
|
122 | for f in paths_: | |
|
123 | cnt += 1 | |||
|
124 | if limit and limit == cnt: | |||
|
125 | break | |||
|
126 | ||||
122 | file_path = '/'.join((PROJECT, 'files', 'tip', f)) |
|
127 | file_path = '/'.join((PROJECT, 'files', 'tip', f)) | |
123 |
|
128 | |||
124 | full_uri = (BASE_URI % file_path) |
|
129 | full_uri = (BASE_URI % file_path) | |
125 | s = time.time() |
|
130 | s = time.time() | |
126 | f = o.open(full_uri) |
|
131 | f = o.open(full_uri) | |
127 | size = len(f.read()) |
|
132 | size = len(f.read()) | |
128 | e = time.time() - s |
|
133 | e = time.time() - s | |
129 | total_time += e |
|
134 | total_time += e | |
130 | print 'visited %s size:%s req:%s ms' % (full_uri, size, e) |
|
135 | print '%s visited %s size:%s req:%s ms' % (cnt, full_uri, size, e) | |
131 |
|
136 | |||
132 | print 'total_time', total_time |
|
137 | print 'total_time', total_time | |
133 |
print 'average on req', total_time / float( |
|
138 | print 'average on req', total_time / float(cnt) | |
|
139 | ||||
134 |
|
140 | |||
135 |
|
141 | |||
136 | test_files_walk() |
|
|||
137 | test_changelog_walk(40) |
|
142 | test_changelog_walk(40) | |
|
143 | time.sleep(2) | |||
138 | test_changeset_walk(limit=100) |
|
144 | test_changeset_walk(limit=100) | |
139 |
|
145 | time.sleep(2) | ||
|
146 | test_files_walk(100) |
General Comments 0
You need to be logged in to leave comments.
Login now