summaryrefslogtreecommitdiffstats
path: root/tests/functional/arbiter/test_no_data_loss_arbiter_vol_after_rename_file.py
blob: 80339e5d301789348bb397c00ff56d4179d6cfac (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
#  Copyright (C) 2016-2018  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,
                                           get_volume_options)
from glustolibs.gluster.brick_libs import (bring_bricks_offline,
                                           bring_bricks_online,
                                           are_bricks_offline,
                                           get_all_bricks)
from glustolibs.gluster.heal_libs import (monitor_heal_completion,
                                          is_heal_complete,
                                          is_volume_in_split_brain)
from glustolibs.misc.misc_libs import upload_scripts


@runs_on([['replicated'],
          ['glusterfs']])
class ArbiterSelfHealTests(GlusterBaseClass):
    """
        Arbiter Self-Heal tests
    """
    @classmethod
    def setUpClass(cls):
        # Calling GlusterBaseClass setUpClass
        GlusterBaseClass.setUpClass.im_func(cls)

        # 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):
        """
        setUp method for every test
        """

        # calling GlusterBaseClass setUp
        GlusterBaseClass.setUp.im_func(self)

        # Setup Volume and Mount Volume
        g.log.info("Starting to Setup Volume %s", self.volname)
        ret = self.setup_volume_and_mount_volume(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

        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_no_data_loss_arbiter_vol_after_rename_file(self):
        """
        - Create a 1x(2+1) arbiter replicate volume
        - Turn off self-heal daemon
        - Create a directory 'test_dir'
        - Bring down the 1-st data brick
        - Create a file under 'test_dir'
        - Bring down the 2-nd data brick
        - Bring up the 1-st data brick
        - Rename file under 'test_dir'
        - Bring up the 2-nd data brick
        - Trigger heal
        - Check if no pending heals
        - Check if md5sum on mountpoint is the same for md5sum_node on nodes
        """
        # pylint: disable=too-many-locals,too-many-statements
        test_dir = 'test_dir'

        # Setting options
        options = {"self-heal-daemon": "off"}
        g.log.info('Setting options %s for volume %s...',
                   options, self.volname)
        ret = set_volume_options(self.mnode, self.volname, options)
        self.assertTrue(ret, 'Failed to set options %s for volume %s'
                        % (options, self.volname))
        g.log.info("Successfully set %s for volume %s",
                   options, self.volname)

        # Check if options are set to off
        options_dict = get_volume_options(self.mnode, self.volname)
        self.assertEqual(options_dict['cluster.self-heal-daemon'], 'off',
                         'Option self-heal-daemon is not set to off')
        g.log.info('Option are set to off for volume %s: %s',
                   options, self.volname)

        # Creating IO on client side
        g.log.info("Generating data for %s:%s",
                   self.mounts[0].client_system, self.mounts[0].mountpoint)
        # Create dir
        g.log.info('Creating dir...')
        command = ('python %s create_deep_dir -d 1 -l 0 -n 1 %s/%s'
                   % (self.script_upload_path,
                      self.mounts[0].mountpoint,
                      test_dir))

        ret, _, err = g.run(self.mounts[0].client_system, command,
                            user=self.mounts[0].user)

        self.assertFalse(ret, err)
        g.log.info("IO is successful")

        # get the bricks for the volume
        g.log.info("Fetching bricks for the volume : %s", self.volname)
        bricks_list = get_all_bricks(self.mnode, self.volname)
        g.log.info("Brick List : %s", bricks_list)

        # Bring brick 1 offline
        bricks_to_bring_offline = [bricks_list[0]]
        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)

        # Create file under dir test_dir
        g.log.info("Generating file for %s:%s",
                   self.mounts[0].client_system, self.mounts[0].mountpoint)
        # Create file
        g.log.info('Creating file...')
        command = ("python %s create_files -f 1 %s/%s"
                   % (self.script_upload_path,
                      self.mounts[0].mountpoint,
                      test_dir))

        ret, _, err = g.run(self.mounts[0].client_system, command,
                            user=self.mounts[0].user)

        self.assertFalse(ret, err)
        g.log.info("Created file successfully")

        # get md5sum for file
        g.log.info('Getting md5sum for file on %s', self.mounts[0].mountpoint)

        command = ("md5sum %s/%s/testfile0.txt | awk '{ print $1 }'"
                   % (self.mounts[0].mountpoint, test_dir))

        ret, md5sum, err = g.run(self.mounts[0].client_system, command,
                                 user=self.mounts[0].user)
        self.assertFalse(ret, err)
        g.log.info('md5sum: %s', md5sum)

        # Bring brick 2 offline
        bricks_to_bring_offline = [bricks_list[1]]
        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)

        # Bring 1-st brick online
        bricks_to_bring_online = [bricks_list[0]]
        g.log.info('Bringing bricks %s online...', bricks_to_bring_online)
        ret = bring_bricks_online(self.mnode, self.volname,
                                  bricks_to_bring_online)
        self.assertTrue(ret, 'Failed to bring bricks %s online'
                        % bricks_to_bring_online)
        g.log.info('Bringing bricks %s online is successful',
                   bricks_to_bring_online)

        # Rename file under test_dir
        g.log.info("Renaming file for %s:%s",
                   self.mounts[0].client_system, self.mounts[0].mountpoint)
        command = ("python %s mv %s/%s"
                   % (self.script_upload_path,
                      self.mounts[0].mountpoint,
                      test_dir))
        ret, _, err = g.run(self.mounts[0].client_system, command)
        self.assertFalse(ret, err)
        g.log.info("Renaming file for %s:%s is successful",
                   self.mounts[0].client_system, self.mounts[0].mountpoint)

        # Bring 2-nd 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)

        # Mount and unmount mounts
        ret = self.unmount_volume(self.mounts)
        self.assertTrue(ret, 'Failed to unmount %s' % self.volname)

        ret = self.mount_volume(self.mounts)
        self.assertTrue(ret, 'Unable to mount %s' % self.volname)

        # Trigger heal from mount point
        g.log.info("Triggering heal for %s:%s",
                   self.mounts[0].client_system, self.mounts[0].mountpoint)
        command = ("python %s read %s/%s"
                   % (self.script_upload_path,
                      self.mounts[0].mountpoint,
                      test_dir))

        ret, _, err = g.run(self.mounts[0].client_system, command)
        self.assertFalse(ret, 'Failed to start "find . | xargs stat" '
                              'on %s'
                         % self.mounts[0].client_system)

        # 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 md5sum for file on all nodes and compare with mountpoint
        for brick in bricks_list[0:2]:
            g.log.info('Getting md5sum for file on %s', brick)
            node, brick_path = brick.split(':')
            command = ("md5sum %s/%s/testfile0_a.txt  | awk '{ print $1 }'"
                       % (brick_path, test_dir))
            ret, md5sum_node, err = g.run(node, command,
                                          user=self.mounts[0].user)
            self.assertFalse(ret, err)
            g.log.info('md5sum for the node: %s', md5sum_node)

            # comparing md5sum_node result with mountpoint
            g.log.info('Comparing md5sum result with mountpoint...')
            self.assertEqual(md5sum, md5sum_node, 'File contents are not equal'
                                                  ' on %s and %s'
                             % (self.mounts[0].mountpoint, brick))
            g.log.info('File contents are equal on %s and %s',
                       self.mounts[0].mountpoint, brick)