summaryrefslogtreecommitdiffstats
path: root/tests/functional/arbiter/test_data_self_heal_algorithm_diff_heal_command.py
blob: fadfc1150dadecd61bbf01ebf43323bd9574ec85 (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
#  Copyright (C) 2015-2018  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.

from glusto.core import Glusto as g
from glustolibs.gluster.gluster_base_class import (GlusterBaseClass, runs_on)
from glustolibs.gluster.exceptions import ExecutionError
from glustolibs.gluster.volume_ops import set_volume_options
from glustolibs.gluster.volume_libs import expand_volume
from glustolibs.gluster.brick_libs import (select_bricks_to_bring_offline,
                                           bring_bricks_offline,
                                           bring_bricks_online,
                                           are_bricks_offline)
from glustolibs.gluster.heal_libs import (
    monitor_heal_completion,
    is_heal_complete,
    is_volume_in_split_brain,
    is_shd_daemonized)
from glustolibs.gluster.rebalance_ops import (rebalance_start,
                                              wait_for_rebalance_to_complete)
from glustolibs.gluster.heal_ops import trigger_heal
from glustolibs.misc.misc_libs import upload_scripts
from glustolibs.io.utils import (collect_mounts_arequal, validate_io_procs)


@runs_on([['replicated', 'distributed-replicated'],
          ['glusterfs', 'cifs', 'nfs']])
class TestSelfHeal(GlusterBaseClass):
    """
    Description:
        Arbiter Test cases related to
        healing in default configuration of the volume
    """

    @classmethod
    def setUpClass(cls):
        # Calling GlusterBaseClass setUpClass
        GlusterBaseClass.setUpClass.im_func(cls)

        # Overriding the volume type to specifically test the volume type
        # Change from distributed-replicated to arbiter
        if cls.volume_type == "distributed-replicated":
            cls.volume['voltype'] = {
                'type': 'distributed-replicated',
                'dist_count': 2,
                'replica_count': 3,
                'arbiter_count': 1,
                '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)

    def setUp(self):
        # Calling GlusterBaseClass setUp
        GlusterBaseClass.setUp.im_func(self)

        # 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):
        """
        Cleanup and umount volume
        """

        # Cleanup and umount 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 umount the vol & cleanup Volume")
        g.log.info("Successful in umounting the volume and Cleanup")

        # Calling GlusterBaseClass teardown
        GlusterBaseClass.tearDown.im_func(self)

    def test_data_self_heal_algorithm_diff_heal_command(self):
        """
        Test Volume Option - 'cluster.data-self-heal-algorithm' : 'diff'

        Description:
        - set the volume option
        "metadata-self-heal": "off"
        "entry-self-heal": "off"
        "data-self-heal": "off"
        "data-self-heal-algorithm": "diff"
        "self-heal-daemon": "off"
        - create IO
        - calculate arequal
        - bring down all bricks processes from selected set
        - modify the data
        - get arequal before getting bricks online
        - bring bricks online
        - expand volume by adding bricks to the volume
        - do rebalance
        - set the volume option "self-heal-daemon": "on" and check for daemons
        - start healing
        - check if heal is completed
        - check for split-brain
        - calculate arequal and compare with arequal before bringing bricks
        offline and after bringing bricks online
        """
        # pylint: disable=too-many-branches,too-many-statements
        # Setting options
        g.log.info('Setting options...')
        options = {"metadata-self-heal": "off",
                   "entry-self-heal": "off",
                   "data-self-heal": "off",
                   "data-self-heal-algorithm": "diff"}
        ret = set_volume_options(self.mnode, self.volname, options)
        self.assertTrue(ret, 'Failed to set options')
        g.log.info("Options "
                   "'metadata-self-heal', "
                   "'entry-self-heal', "
                   "'data-self-heal', "
                   "'self-heal-daemon' "
                   "are set to 'off',"
                   "'data-self-heal-algorithm' "
                   "is set to 'diff' successfully")

        # Creating files on client side
        all_mounts_procs = []
        g.log.info("Generating data for %s:%s",
                   self.mounts[0].client_system, self.mounts[0].mountpoint)
        # Creating files
        command = ("python %s create_files -f 100 %s"
                   % (self.script_upload_path, self.mounts[0].mountpoint))

        proc = g.run_async(self.mounts[0].client_system, command,
                           user=self.mounts[0].user)
        all_mounts_procs.append(proc)

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

        # Setting options
        g.log.info('Setting options...')
        options = {"self-heal-daemon": "off"}
        ret = set_volume_options(self.mnode, self.volname, options)
        self.assertTrue(ret, 'Failed to set options')
        g.log.info("Option 'self-heal-daemon' is set to 'off' successfully")

        # Select bricks to bring offline
        bricks_to_bring_offline_dict = (select_bricks_to_bring_offline(
            self.mnode, self.volname))
        bricks_to_bring_offline = filter(None, (
            bricks_to_bring_offline_dict['hot_tier_bricks'] +
            bricks_to_bring_offline_dict['cold_tier_bricks'] +
            bricks_to_bring_offline_dict['volume_bricks']))

        # Bring brick offline
        g.log.info('Bringing bricks %s offline...', bricks_to_bring_offline)
        ret = bring_bricks_offline(self.volname, bricks_to_bring_offline)
        self.assertTrue(ret, 'Failed to bring bricks %s offline' %
                        bricks_to_bring_offline)

        ret = are_bricks_offline(self.mnode, self.volname,
                                 bricks_to_bring_offline)
        self.assertTrue(ret, 'Bricks %s are not offline'
                        % bricks_to_bring_offline)
        g.log.info('Bringing bricks %s offline is successful',
                   bricks_to_bring_offline)

        # Modify the data
        all_mounts_procs = []
        g.log.info("Modifying data for %s:%s",
                   self.mounts[0].client_system, self.mounts[0].mountpoint)
        command = ("python %s create_files -f 100 --fixed-file-size 1M %s"
                   % (self.script_upload_path, self.mounts[0].mountpoint))

        proc = g.run_async(self.mounts[0].client_system, command,
                           user=self.mounts[0].user)
        all_mounts_procs.append(proc)

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

        # Get arequal before getting bricks online
        g.log.info('Getting arequal before getting bricks online...')
        ret, result_before_online = collect_mounts_arequal(self.mounts)
        self.assertTrue(ret, 'Failed to get arequal')
        g.log.info('Getting arequal before getting bricks online '
                   'is successful')

        # Bring brick online
        g.log.info('Bringing bricks %s online...', bricks_to_bring_offline)
        ret = bring_bricks_online(self.mnode, self.volname,
                                  bricks_to_bring_offline)
        self.assertTrue(ret, 'Failed to bring bricks %s online' %
                        bricks_to_bring_offline)
        g.log.info('Bringing bricks %s online is successful',
                   bricks_to_bring_offline)

        # Expand volume by adding bricks to the volume
        g.log.info("Start adding bricks to volume...")
        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 is successful on volume %s", self.volname)

        # Do rebalance
        ret, _, _ = rebalance_start(self.mnode, self.volname)
        self.assertEqual(ret, 0, 'Failed to start rebalance')
        g.log.info('Rebalance is started')

        ret = wait_for_rebalance_to_complete(self.mnode, self.volname)
        self.assertTrue(ret, 'Rebalance is not completed')
        g.log.info('Rebalance is completed successfully')

        # Setting options
        g.log.info('Setting options...')
        options = {"self-heal-daemon": "on"}
        ret = set_volume_options(self.mnode, self.volname, options)
        self.assertTrue(ret, 'Failed to set options')
        g.log.info("Option 'self-heal-daemon' is set to 'on' successfully")

        # Wait for self-heal-daemons to be online
        g.log.info("Waiting for self-heal-daemons to be online")
        ret = is_shd_daemonized(self.all_servers)
        self.assertTrue(ret, "Either No self heal daemon process found")
        g.log.info("All self-heal-daemons are online")

        # Start healing
        ret = trigger_heal(self.mnode, self.volname)
        self.assertTrue(ret, 'Heal is not started')
        g.log.info('Healing is started')

        # Monitor heal completion
        ret = monitor_heal_completion(self.mnode, self.volname)
        self.assertTrue(ret, 'Heal has not yet completed')

        # Check if heal is completed
        ret = is_heal_complete(self.mnode, self.volname)
        self.assertTrue(ret, 'Heal is not complete')
        g.log.info('Heal is completed successfully')

        # Check for split-brain
        ret = is_volume_in_split_brain(self.mnode, self.volname)
        self.assertFalse(ret, 'Volume is in split-brain state')
        g.log.info('Volume is not in split-brain state')

        # Get arequal after getting bricks online
        g.log.info('Getting arequal after getting bricks online...')
        ret, result_after_online = collect_mounts_arequal(self.mounts)
        self.assertTrue(ret, 'Failed to get arequal')
        g.log.info('Getting arequal after getting bricks online '
                   'is successful')

        # Checking arequals before bringing bricks offline
        # and after bringing bricks online
        self.assertItemsEqual(result_before_online, result_after_online,
                              'Checksums are not equal')
        g.log.info('Checksums are equal')