aboutsummaryrefslogtreecommitdiff
path: root/tests/test_sftp_big.py
blob: c182762411f28f6422cdfc0fe73d04ea89a27e66 (plain)
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
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
# Copyright (C) 2003-2007  Robey Pointer <robey@lag.net>
#
# This file is part of paramiko.
#
# Paramiko is free software; you can redistribute it and/or modify it under the
# terms of the GNU Lesser General Public License as published by the Free
# Software Foundation; either version 2.1 of the License, or (at your option)
# any later version.
#
# Paramiko is distrubuted in the hope that it will be useful, but WITHOUT ANY
# WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR
# A PARTICULAR PURPOSE.  See the GNU Lesser General Public License for more
# details.
#
# You should have received a copy of the GNU Lesser General Public License
# along with Paramiko; if not, write to the Free Software Foundation, Inc.,
# 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA.

"""
some unit tests to make sure sftp works well with large files.

a real actual sftp server is contacted, and a new folder is created there to
do test file operations in (so no existing files will be harmed).
"""

import logging
import os
import random
import struct
import sys
import threading
import time
import unittest

import paramiko
from stub_sftp import StubServer, StubSFTPServer
from loop import LoopSocket
from test_sftp import get_sftp

FOLDER = os.environ.get('TEST_FOLDER', 'temp-testing000')


class BigSFTPTest (unittest.TestCase):

    def setUp(self):
        global FOLDER
        sftp = get_sftp()
        for i in xrange(1000):
            FOLDER = FOLDER[:-3] + '%03d' % i
            try:
                sftp.mkdir(FOLDER)
                break
            except (IOError, OSError):
                pass

    def tearDown(self):
        sftp = get_sftp()
        sftp.rmdir(FOLDER)

    def test_1_lots_of_files(self):
        """
        create a bunch of files over the same session.
        """
        sftp = get_sftp()
        numfiles = 100
        try:
            for i in range(numfiles):
                f = sftp.open('%s/file%d.txt' % (FOLDER, i), 'w', 1)
                f.write('this is file #%d.\n' % i)
                f.close()
                sftp.chmod('%s/file%d.txt' % (FOLDER, i), 0660)

            # now make sure every file is there, by creating a list of filenmes
            # and reading them in random order.
            numlist = range(numfiles)
            while len(numlist) > 0:
                r = numlist[random.randint(0, len(numlist) - 1)]
                f = sftp.open('%s/file%d.txt' % (FOLDER, r))
                self.assertEqual(f.readline(), 'this is file #%d.\n' % r)
                f.close()
                numlist.remove(r)
        finally:
            for i in range(numfiles):
                try:
                    sftp.remove('%s/file%d.txt' % (FOLDER, i))
                except:
                    pass

    def test_2_big_file(self):
        """
        write a 1MB file with no buffering.
        """
        sftp = get_sftp()
        kblob = (1024 * 'x')
        start = time.time()
        try:
            f = sftp.open('%s/hongry.txt' % FOLDER, 'w')
            for n in range(1024):
                f.write(kblob)
                if n % 128 == 0:
                    sys.stderr.write('.')
            f.close()
            sys.stderr.write(' ')

            self.assertEqual(sftp.stat('%s/hongry.txt' % FOLDER).st_size, 1024 * 1024)
            end = time.time()
            sys.stderr.write('%ds ' % round(end - start))
            
            start = time.time()
            f = sftp.open('%s/hongry.txt' % FOLDER, 'r')
            for n in range(1024):
                data = f.read(1024)
                self.assertEqual(data, kblob)
            f.close()

            end = time.time()
            sys.stderr.write('%ds ' % round(end - start))
        finally:
            sftp.remove('%s/hongry.txt' % FOLDER)

    def test_3_big_file_pipelined(self):
        """
        write a 1MB file, with no linefeeds, using pipelining.
        """
        sftp = get_sftp()
        kblob = ''.join([struct.pack('>H', n) for n in xrange(512)])
        start = time.time()
        try:
            f = sftp.open('%s/hongry.txt' % FOLDER, 'w')
            f.set_pipelined(True)
            for n in range(1024):
                f.write(kblob)
                if n % 128 == 0:
                    sys.stderr.write('.')
            f.close()
            sys.stderr.write(' ')

            self.assertEqual(sftp.stat('%s/hongry.txt' % FOLDER).st_size, 1024 * 1024)
            end = time.time()
            sys.stderr.write('%ds ' % round(end - start))
            
            start = time.time()
            f = sftp.open('%s/hongry.txt' % FOLDER, 'r')
            f.prefetch()

            # read on odd boundaries to make sure the bytes aren't getting scrambled
            n = 0
            k2blob = kblob + kblob
            chunk = 629
            size = 1024 * 1024
            while n < size:
                if n + chunk > size:
                    chunk = size - n
                data = f.read(chunk)
                offset = n % 1024
                self.assertEqual(data, k2blob[offset:offset + chunk])
                n += chunk
            f.close()

            end = time.time()
            sys.stderr.write('%ds ' % round(end - start))
        finally:
            sftp.remove('%s/hongry.txt' % FOLDER)

    def test_4_prefetch_seek(self):
        sftp = get_sftp()
        kblob = ''.join([struct.pack('>H', n) for n in xrange(512)])
        try:
            f = sftp.open('%s/hongry.txt' % FOLDER, 'w')
            f.set_pipelined(True)
            for n in range(1024):
                f.write(kblob)
                if n % 128 == 0:
                    sys.stderr.write('.')
            f.close()
            sys.stderr.write(' ')
            
            self.assertEqual(sftp.stat('%s/hongry.txt' % FOLDER).st_size, 1024 * 1024)
            
            start = time.time()
            k2blob = kblob + kblob
            chunk = 793
            for i in xrange(10):
                f = sftp.open('%s/hongry.txt' % FOLDER, 'r')
                f.prefetch()
                base_offset = (512 * 1024) + 17 * random.randint(1000, 2000)
                offsets = [base_offset + j * chunk for j in xrange(100)]
                # randomly seek around and read them out
                for j in xrange(100):
                    offset = offsets[random.randint(0, len(offsets) - 1)]
                    offsets.remove(offset)
                    f.seek(offset)
                    data = f.read(chunk)
                    n_offset = offset % 1024
                    self.assertEqual(data, k2blob[n_offset:n_offset + chunk])
                    offset += chunk
                f.close()
            end = time.time()
            sys.stderr.write('%ds ' % round(end - start))
        finally:
            sftp.remove('%s/hongry.txt' % FOLDER)

    def test_5_readv_seek(self):
        sftp = get_sftp()
        kblob = ''.join([struct.pack('>H', n) for n in xrange(512)])
        try:
            f = sftp.open('%s/hongry.txt' % FOLDER, 'w')
            f.set_pipelined(True)
            for n in range(1024):
                f.write(kblob)
                if n % 128 == 0:
                    sys.stderr.write('.')
            f.close()
            sys.stderr.write(' ')

            self.assertEqual(sftp.stat('%s/hongry.txt' % FOLDER).st_size, 1024 * 1024)

            start = time.time()
            k2blob = kblob + kblob
            chunk = 793
            for i in xrange(10):
                f = sftp.open('%s/hongry.txt' % FOLDER, 'r')
                base_offset = (512 * 1024) + 17 * random.randint(1000, 2000)
                # make a bunch of offsets and put them in random order
                offsets = [base_offset + j * chunk for j in xrange(100)]
                readv_list = []
                for j in xrange(100):
                    o = offsets[random.randint(0, len(offsets) - 1)]
                    offsets.remove(o)
                    readv_list.append((o, chunk))
                ret = f.readv(readv_list)
                for i in xrange(len(readv_list)):
                    offset = readv_list[i][0]
                    n_offset = offset % 1024
                    self.assertEqual(ret.next(), k2blob[n_offset:n_offset + chunk])
                f.close()
            end = time.time()
            sys.stderr.write('%ds ' % round(end - start))
        finally:
            sftp.remove('%s/hongry.txt' % FOLDER)

    def test_6_lots_of_prefetching(self):
        """
        prefetch a 1MB file a bunch of times, discarding the file object
        without using it, to verify that paramiko doesn't get confused.
        """
        sftp = get_sftp()
        kblob = (1024 * 'x')
        try:
            f = sftp.open('%s/hongry.txt' % FOLDER, 'w')
            f.set_pipelined(True)
            for n in range(1024):
                f.write(kblob)
                if n % 128 == 0:
                    sys.stderr.write('.')
            f.close()
            sys.stderr.write(' ')

            self.assertEqual(sftp.stat('%s/hongry.txt' % FOLDER).st_size, 1024 * 1024)

            for i in range(10):
                f = sftp.open('%s/hongry.txt' % FOLDER, 'r')
                f.prefetch()
            f = sftp.open('%s/hongry.txt' % FOLDER, 'r')
            f.prefetch()
            for n in range(1024):
                data = f.read(1024)
                self.assertEqual(data, kblob)
                if n % 128 == 0:
                    sys.stderr.write('.')
            f.close()
            sys.stderr.write(' ')
        finally:
            sftp.remove('%s/hongry.txt' % FOLDER)
    
    def test_7_prefetch_readv(self):
        """
        verify that prefetch and readv don't conflict with each other.
        """
        sftp = get_sftp()
        kblob = ''.join([struct.pack('>H', n) for n in xrange(512)])
        try:
            f = sftp.open('%s/hongry.txt' % FOLDER, 'w')
            f.set_pipelined(True)
            for n in range(1024):
                f.write(kblob)
                if n % 128 == 0:
                    sys.stderr.write('.')
            f.close()
            sys.stderr.write(' ')
            
            self.assertEqual(sftp.stat('%s/hongry.txt' % FOLDER).st_size, 1024 * 1024)

            f = sftp.open('%s/hongry.txt' % FOLDER, 'r')
            f.prefetch()
            data = f.read(1024)
            self.assertEqual(data, kblob)
            
            chunk_size = 793
            base_offset = 512 * 1024
            k2blob = kblob + kblob
            chunks = [(base_offset + (chunk_size * i), chunk_size) for i in range(20)]
            for data in f.readv(chunks):
                offset = base_offset % 1024
                self.assertEqual(chunk_size, len(data))
                self.assertEqual(k2blob[offset:offset + chunk_size], data)
                base_offset += chunk_size

            f.close()
            sys.stderr.write(' ')
        finally:
            sftp.remove('%s/hongry.txt' % FOLDER)
    
    def test_8_large_readv(self):
        """
        verify that a very large readv is broken up correctly and still
        returned as a single blob.
        """
        sftp = get_sftp()
        kblob = ''.join([struct.pack('>H', n) for n in xrange(512)])
        try:
            f = sftp.open('%s/hongry.txt' % FOLDER, 'w')
            f.set_pipelined(True)
            for n in range(1024):
                f.write(kblob)
                if n % 128 == 0:
                    sys.stderr.write('.')
            f.close()
            sys.stderr.write(' ')

            self.assertEqual(sftp.stat('%s/hongry.txt' % FOLDER).st_size, 1024 * 1024)
            
            f = sftp.open('%s/hongry.txt' % FOLDER, 'r')
            data = list(f.readv([(23 * 1024, 128 * 1024)]))
            self.assertEqual(1, len(data))
            data = data[0]
            self.assertEqual(128 * 1024, len(data))
            
            f.close()
            sys.stderr.write(' ')
        finally:
            sftp.remove('%s/hongry.txt' % FOLDER)
    
    def test_9_big_file_big_buffer(self):
        """
        write a 1MB file, with no linefeeds, and a big buffer.
        """
        sftp = get_sftp()
        mblob = (1024 * 1024 * 'x')
        try:
            f = sftp.open('%s/hongry.txt' % FOLDER, 'w', 128 * 1024)
            f.write(mblob)
            f.close()

            self.assertEqual(sftp.stat('%s/hongry.txt' % FOLDER).st_size, 1024 * 1024)
        finally:
            sftp.remove('%s/hongry.txt' % FOLDER)
    
    def test_A_big_file_renegotiate(self):
        """
        write a 1MB file, forcing key renegotiation in the middle.
        """
        sftp = get_sftp()
        t = sftp.sock.get_transport()
        t.packetizer.REKEY_BYTES = 512 * 1024
        k32blob = (32 * 1024 * 'x')
        try:
            f = sftp.open('%s/hongry.txt' % FOLDER, 'w', 128 * 1024)
            for i in xrange(32):
                f.write(k32blob)
            f.close()
            
            self.assertEqual(sftp.stat('%s/hongry.txt' % FOLDER).st_size, 1024 * 1024)
            self.assertNotEquals(t.H, t.session_id)
            
            # try to read it too.
            f = sftp.open('%s/hongry.txt' % FOLDER, 'r', 128 * 1024)
            f.prefetch()
            total = 0
            while total < 1024 * 1024:
                total += len(f.read(32 * 1024))
            f.close()
        finally:
            sftp.remove('%s/hongry.txt' % FOLDER)
            t.packetizer.REKEY_BYTES = pow(2, 30)