summaryrefslogtreecommitdiffstats
path: root/tests/functional/arbiter/brick_cases/test_brickcases.py
blob: 51f89714c90921b7f9d24b5c0015badb8877b86c (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
386
387
388
389
390
391
392
393
394
395
#  Copyright (C) 2017-2018  Red Hat, Inc. <http://www.redhat.com>
#
#  This program is free software; you can redistribute it and/or modify
#  it under the terms of the GNU General Public License as published by
#  the Free Software Foundation; either version 2 of the License, or
#  any later version.
#
#  This program is distributed 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 General Public License for more details.
#
#  You should have received a copy of the GNU General Public License along
#  with this program; if not, write to the Free Software Foundation, Inc.,
#  51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.

""" Test Arbiter Specific Cases"""

import sys

from glusto.core import Glusto as g

from glustolibs.gluster.gluster_base_class import (GlusterBaseClass, runs_on)
from glustolibs.gluster.volume_libs import (
    log_volume_info_and_status, replace_brick_from_volume,
    expand_volume, wait_for_volume_process_to_be_online,
    verify_all_process_of_volume_are_online, shrink_volume)
from glustolibs.gluster.rebalance_ops import (
    rebalance_start, rebalance_status, wait_for_rebalance_to_complete)
from glustolibs.gluster.heal_libs import monitor_heal_completion
from glustolibs.gluster.exceptions import ExecutionError
from glustolibs.io.utils import (validate_io_procs,
                                 list_all_files_and_dirs_mounts,
                                 wait_for_io_to_complete)
from glustolibs.misc.misc_libs import upload_scripts


@runs_on([['replicated', 'distributed-replicated'],
          ['glusterfs', 'cifs', 'nfs']])
class GlusterArbiterVolumeTypeChangeClass(GlusterBaseClass):
    """Class for testing Volume Type Change from replicated to
        Arbitered volume
    """
    @classmethod
    def setUpClass(cls):
        # Calling GlusterBaseClass setUpClass
        cls.get_super_method(cls, 'setUpClass')()

        # Overriding the volume type to specifically test the volume type
        # change from replicated to arbiter
        if cls.volume_type == "replicated":
            cls.volume['voltype'] = {
                'type': 'replicated',
                'replica_count': 2,
                'dist_count': 1,
                'transport': 'tcp'}

        if cls.volume_type == "distributed-replicated":
            cls.volume['voltype'] = {
                'type': 'distributed-replicated',
                'dist_count': 2,
                'replica_count': 2,
                'transport': 'tcp'}

        # Upload io scripts for running IO on mounts
        g.log.info("Upload io scripts to clients %s for running IO on mounts",
                   cls.clients)
        script_local_path = ("/usr/share/glustolibs/io/scripts/"
                             "file_dir_ops.py")
        cls.script_upload_path = ("/usr/share/glustolibs/io/scripts/"
                                  "file_dir_ops.py")
        ret = upload_scripts(cls.clients, [script_local_path])
        if not ret:
            raise ExecutionError("Failed to upload IO scripts to clients %s"
                                 % cls.clients)
        g.log.info("Successfully uploaded IO scripts to clients %s",
                   cls.clients)

        cls.counter = 1
        # int: Value of counter is used for dirname-start-num argument for
        # file_dir_ops.py create_deep_dirs_with_files.

        # The --dir-length argument value for file_dir_ops.py
        # create_deep_dirs_with_files is set to 10 (refer to the cmd in setUp
        # method). This means every mount will create
        # 10 top level dirs. For every mountpoint/testcase to create new set of
        # dirs, we are incrementing the counter by --dir-length value i.e 10
        # in this test suite.

        # If we are changing the --dir-length to new value, ensure the counter
        # is also incremented by same value to create new set of files/dirs.

    def setUp(self):
        """
        - Setup Volume and Mount Volume
        """
        # Calling GlusterBaseClass setUp
        self.get_super_method(self, 'setUp')()

        self.all_mounts_procs = []
        self.io_validation_complete = False

        # Setup Volume and Mount Volume
        g.log.info("Starting to Setup Volume and Mount Volume")
        ret = self.setup_volume_and_mount_volume(mounts=self.mounts)
        if not ret:
            raise ExecutionError("Failed to Setup_Volume and Mount_Volume")
        g.log.info("Successful in Setup Volume and Mount Volume")

    def tearDown(self):
        """If test method failed before validating IO, tearDown waits for the
        IO's to complete and checks for the IO exit status

        Unmount Volume and Cleanup Volume
        """
        # Wait for IO to complete if io validation is not executed in the
        # test method
        if not self.io_validation_complete:
            g.log.info("Wait for IO to complete as IO validation did not "
                       "succeed in test method")
            ret = wait_for_io_to_complete(self.all_mounts_procs, self.mounts)
            if not ret:
                raise ExecutionError("IO failed on some of the clients")
            g.log.info("IO is successful on all mounts")

            # List all files and dirs created
            g.log.info("List all files and directories:")
            ret = list_all_files_and_dirs_mounts(self.mounts)
            if not ret:
                raise ExecutionError("Failed to list all files and dirs")
            g.log.info("Listing all files and directories is successful")

        # Unmount Volume and Cleanup Volume
        g.log.info("Starting to Unmount Volume and Cleanup Volume")
        ret = self.unmount_volume_and_cleanup_volume(mounts=self.mounts)
        if not ret:
            raise ExecutionError("Failed to Unmount Volume and Cleanup Volume")
        g.log.info("Successful in Unmount Volume and Cleanup Volume")

        # Calling GlusterBaseClass tearDown
        self.get_super_method(self, 'tearDown')()

    def test_replicated_to_arbiter_volume_change_with_volume_ops(self):
        """
        - Change the volume type from replicated to arbiter
        - Perform add-brick, rebalance on arbitered volume
        - Perform replace-brick on arbitered volume
        - Perform remove-brick on arbitered volume
        """
        # pylint: disable=too-many-statements

        # Start IO on mounts
        g.log.info("Starting IO on all mounts...")
        self.all_mounts_procs = []
        for mount_obj in self.mounts:
            g.log.info("Starting IO on %s:%s", mount_obj.client_system,
                       mount_obj.mountpoint)
            cmd = ("/usr/bin/env python%d %s create_deep_dirs_with_files "
                   "--dirname-start-num %d "
                   "--dir-depth 2 "
                   "--dir-length 15 "
                   "--max-num-of-dirs 5 "
                   "--num-of-files 5 %s" % (
                       sys.version_info.major, self.script_upload_path,
                       self.counter, mount_obj.mountpoint))
            proc = g.run_async(mount_obj.client_system, cmd,
                               user=mount_obj.user)
            self.all_mounts_procs.append(proc)
            self.counter = self.counter + 10
        self.io_validation_complete = False

        # Validate IO
        ret = validate_io_procs(self.all_mounts_procs, self.mounts)
        self.io_validation_complete = True
        self.assertTrue(ret, "IO failed on some of the clients")

        # Adding bricks to make an Arbiter Volume
        g.log.info("Adding bricks to convert to Arbiter Volume")
        ret = expand_volume(self.mnode, self.volname, self.servers[2:],
                            self.all_servers_info, replica_count=1,
                            arbiter_count=1)
        self.assertTrue(ret, ("Failed to expand the volume  %s", self.volname))
        g.log.info("Changing volume to arbiter volume is successful %s",
                   self.volname)

        # Log Volume Info and Status after changing the volume type from
        # replicated to arbitered
        g.log.info("Logging volume info and Status after changing to "
                   "arbitered volume")
        ret = log_volume_info_and_status(self.mnode, self.volname)
        self.assertTrue(ret, ("Logging volume info and status failed on "
                              "volume %s", self.volname))
        g.log.info("Successful in logging volume info and status of volume %s",
                   self.volname)

        # Wait for volume processes to be online
        g.log.info("Wait for volume processes to be online")
        ret = wait_for_volume_process_to_be_online(self.mnode, self.volname)
        self.assertTrue(ret, ("Failed to wait for volume %s processes to "
                              "be online", self.volname))
        g.log.info("Successful in waiting for volume %s processes to be "
                   "online", self.volname)

        # Verifying all bricks online
        g.log.info("Verifying volume's all process are online")
        ret = verify_all_process_of_volume_are_online(self.mnode, self.volname)
        self.assertTrue(ret, ("Volume %s : All process are not online",
                              self.volname))
        g.log.info("Volume %s : All process are online", self.volname)

        # Checking for heals to finish after changing the volume type
        # from replicated to arbitered volume
        g.log.info("Wait for self-heal to complete after changing the "
                   "volume type from replicated to arbitered volume")
        ret = monitor_heal_completion(self.mnode, self.volname)
        self.assertTrue(ret, ("Self heal didn't complete even after waiting "
                              "for 20 minutes."))
        g.log.info("self-heal is successful after changing the volume type "
                   "from replicated to arbitered volume")

        # Start IO on mounts
        g.log.info("Starting IO on all mounts...")
        self.all_mounts_procs = []
        for mount_obj in self.mounts:
            g.log.info("Starting IO on %s:%s", mount_obj.client_system,
                       mount_obj.mountpoint)
            cmd = ("/usr/bin/env python%d %s create_deep_dirs_with_files "
                   "--dirname-start-num %d "
                   "--dir-depth 2 "
                   "--dir-length 35 "
                   "--max-num-of-dirs 5 "
                   "--num-of-files 5 %s" % (
                       sys.version_info.major, self.script_upload_path,
                       self.counter, mount_obj.mountpoint))
            proc = g.run_async(mount_obj.client_system, cmd,
                               user=mount_obj.user)
            self.all_mounts_procs.append(proc)
            self.counter = self.counter + 10
        self.io_validation_complete = False

        # Log Volume Info and Status before expanding the volume.
        g.log.info("Logging volume info and Status before expanding volume")
        ret = log_volume_info_and_status(self.mnode, self.volname)
        self.assertTrue(ret, ("Logging volume info and status failed on "
                              "volume %s", self.volname))
        g.log.info("Successful in logging volume info and status of volume %s",
                   self.volname)

        # Start add-brick (subvolume-increase)
        g.log.info("Start adding bricks to volume when IO in progress")
        ret = expand_volume(self.mnode, self.volname, self.servers,
                            self.all_servers_info)
        self.assertTrue(ret, ("Failed to expand the volume when IO in "
                              "progress on volume %s", self.volname))
        g.log.info("Expanding volume when IO in progress is successful on "
                   "volume %s", self.volname)

        # Log Volume Info and Status after expanding the volume
        g.log.info("Logging volume info and Status after expanding volume")
        ret = log_volume_info_and_status(self.mnode, self.volname)
        self.assertTrue(ret, ("Logging volume info and status failed on "
                              "volume %s", self.volname))
        g.log.info("Successful in logging volume info and status of volume %s",
                   self.volname)

        # Wait for volume processes to be online
        g.log.info("Wait for volume processes to be online")
        ret = wait_for_volume_process_to_be_online(self.mnode, self.volname)
        self.assertTrue(ret, ("Failed to wait for volume %s processes to "
                              "be online", self.volname))
        g.log.info("Successful in waiting for volume %s processes to be "
                   "online", self.volname)

        # Verify volume's all process are online
        g.log.info("Verifying volume's all process are online")
        ret = verify_all_process_of_volume_are_online(self.mnode, self.volname)
        self.assertTrue(ret, ("Volume %s : All process are not online",
                              self.volname))
        g.log.info("Volume %s : All process are online", self.volname)

        # Start Rebalance
        g.log.info("Starting Rebalance on the volume")
        ret, _, _ = rebalance_start(self.mnode, self.volname)
        self.assertEqual(ret, 0, ("Failed to start rebalance on the volume "
                                  "%s", self.volname))
        g.log.info("Successfully started rebalance on the volume %s",
                   self.volname)

        # Log Rebalance status
        g.log.info("Log Rebalance status")
        _, _, _ = rebalance_status(self.mnode, self.volname)

        # Wait for rebalance to complete
        g.log.info("Waiting for rebalance to complete")
        ret = wait_for_rebalance_to_complete(self.mnode, self.volname, 600)
        self.assertTrue(ret, "Rebalance did not start "
                             "despite waiting for 5 mins")
        g.log.info("Rebalance is successfully complete on the volume %s",
                   self.volname)

        # Log Volume Info and Status before replacing brick from the volume.
        g.log.info("Logging volume info and Status before replacing brick "
                   "from the volume %s", self.volname)
        ret = log_volume_info_and_status(self.mnode, self.volname)
        self.assertTrue(ret, ("Logging volume info and status failed on "
                              "volume %s", self.volname))
        g.log.info("Successful in logging volume info and status of volume %s",
                   self.volname)

        # Replace brick from a sub-volume
        g.log.info("Replace a faulty brick from the volume")
        ret = replace_brick_from_volume(self.mnode, self.volname,
                                        self.servers, self.all_servers_info)
        self.assertTrue(ret, "Failed to replace faulty brick from the volume")
        g.log.info("Successfully replaced faulty brick from the volume")

        # Log Volume Info and Status after replacing the brick
        g.log.info("Logging volume info and Status after replacing brick "
                   "from the volume %s", self.volname)
        ret = log_volume_info_and_status(self.mnode, self.volname)
        self.assertTrue(ret, ("Logging volume info and status failed on "
                              "volume %s", self.volname))
        g.log.info("Successful in logging volume info and status of volume %s",
                   self.volname)

        # Wait for volume processes to be online
        g.log.info("Wait for volume processes to be online")
        ret = wait_for_volume_process_to_be_online(self.mnode, self.volname)
        self.assertTrue(ret, ("Failed to wait for volume %s processes to "
                              "be online", self.volname))
        g.log.info("Successful in waiting for volume %s processes to be "
                   "online", self.volname)

        # Verify volume's all process are online
        g.log.info("Verifying volume's all process are online")
        ret = verify_all_process_of_volume_are_online(self.mnode, self.volname)
        self.assertTrue(ret, ("Volume %s : All process are not online",
                              self.volname))
        g.log.info("Volume %s : All process are online", self.volname)

        # Wait for self-heal to complete
        g.log.info("Wait for self-heal to complete")
        ret = monitor_heal_completion(self.mnode, self.volname)
        self.assertTrue(ret, "Self heal didn't complete even after waiting "
                        "for 20 minutes. 20 minutes is too much a time for "
                        "current test workload")
        g.log.info("self-heal is successful after replace-brick operation")

        # Log Volume Info and Status before shrinking the volume.
        g.log.info("Logging volume info and Status before shrinking volume")
        ret = log_volume_info_and_status(self.mnode, self.volname)
        self.assertTrue(ret, ("Logging volume info and status failed on "
                              "volume %s", self.volname))
        g.log.info("Successful in logging volume info and status of volume %s",
                   self.volname)

        # Shrinking volume by removing bricks from volume when IO in progress
        g.log.info("Start removing bricks from volume when IO in progress")
        ret = shrink_volume(self.mnode, self.volname, rebalance_timeout=900)
        self.assertTrue(ret, ("Failed to shrink the volume when IO in "
                              "progress on volume %s", self.volname))
        g.log.info("Shrinking volume when IO in progress is successful on "
                   "volume %s", self.volname)

        # Log Volume Info and Status after shrinking the volume
        g.log.info("Logging volume info and Status after shrinking volume")
        ret = log_volume_info_and_status(self.mnode, self.volname)
        self.assertTrue(ret, ("Logging volume info and status failed on "
                              "volume %s", self.volname))
        g.log.info("Successful in logging volume info and status of volume %s",
                   self.volname)

        # Wait for volume processes to be online
        g.log.info("Wait for volume processes to be online")
        ret = wait_for_volume_process_to_be_online(self.mnode, self.volname)
        self.assertTrue(ret, ("Failed to wait for volume %s processes to "
                              "be online", self.volname))
        g.log.info("Successful in waiting for volume %s processes to be "
                   "online", self.volname)

        # Verify volume's all process are online
        g.log.info("Verifying volume's all process are online after "
                   "shrinking volume")
        ret = verify_all_process_of_volume_are_online(self.mnode, self.volname)
        self.assertTrue(ret, ("Volume %s : All process are not online",
                              self.volname))
        g.log.info("Volume %s : All process are online after shrinking volume",
                   self.volname)

        # Validate IO
        self.assertTrue(
            validate_io_procs(self.all_mounts_procs, self.mounts),
            "IO failed on some of the clients"
        )
        self.io_validation_complete = True