summaryrefslogtreecommitdiffstats
path: root/tests/functional/afr/test_heal_command_unsuccessful_as_bricks_down.py
blob: 366736bf62517cba5f1a47ff3d183bd6eaf1ac4f (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
#  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.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.gluster.heal_ops import trigger_heal
from glustolibs.misc.misc_libs import upload_scripts
from glustolibs.io.utils import (validate_io_procs,
                                 wait_for_io_to_complete)


@runs_on([['replicated'],
          ['glusterfs', 'cifs', 'nfs']])
class TestSelfHeal(GlusterBaseClass):
    @classmethod
    def setUpClass(cls):
        # Calling GlusterBaseClass setUpClass
        cls.get_super_method(cls, 'setUpClass')()

        # Upload io scripts for running IO on mounts
        g.log.info("Upload io scripts to clients %s for running IO on mounts",
                   cls.clients)
        cls.script_upload_path = ("/usr/share/glustolibs/io/scripts/"
                                  "file_dir_ops.py")
        ret = upload_scripts(cls.clients, cls.script_upload_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)

        if cls.volume_type == "replicated":
            # Define x3 replicated volume
            cls.volume['voltype'] = {
                'type': 'replicated',
                'replica_count': 3,
                'transport': 'tcp'}

    def setUp(self):
        # 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
        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")

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

    def test_heal_command_unsuccessful_as_bricks_down(self):
        """
        - write 2 Gb file on mount
        - while write is in progress, kill brick b0
        - start heal on the volume (should fail and have error message)
        - bring up the brick which was down (b0)
        - bring down another brick (b1)
        - start heal on the volume (should fail and have error message)
        - bring bricks up
        - wait for heal to complete
        """
        # pylint: disable=too-many-statements
        bricks_list = get_all_bricks(self.mnode, self.volname)
        self.assertIsNotNone(bricks_list, 'Brick list is None')

        # Creating files on client side
        for mount_obj in self.mounts:
            g.log.info("Generating data for %s:%s",
                       mount_obj.client_system, mount_obj.mountpoint)
            # Create 2 Gb file
            g.log.info('Creating files...')
            command = ("cd %s ; dd if=/dev/zero of=file1  bs=10M  count=200"
                       % mount_obj.mountpoint)

            proc = g.run_async(mount_obj.client_system, command,
                               user=mount_obj.user)
            self.all_mounts_procs.append(proc)
        self.io_validation_complete = False

        # Bring brick0 offline
        g.log.info('Bringing bricks %s offline...', bricks_list[0])
        ret = bring_bricks_offline(self.volname, [bricks_list[0]])
        self.assertTrue(ret, 'Failed to bring bricks %s offline' %
                        bricks_list[0])

        ret = are_bricks_offline(self.mnode, self.volname,
                                 [bricks_list[0]])
        self.assertTrue(ret, 'Bricks %s are not offline'
                        % bricks_list[0])
        g.log.info('Bringing bricks %s offline is successful',
                   bricks_list[0])

        # Start healing
        # Need to use 'gluster volume heal' command to check error message
        # after g.run
        cmd = "gluster volume heal %s" % self.volname
        ret, _, err = g.run(self.mnode, cmd)
        self.assertTrue(ret, 'Heal is started')
        # Check for error message
        self.assertIn("Launching heal operation to perform index self heal on "
                      "volume %s has been unsuccessful" % self.volname,
                      err,
                      "Error message is not present or not valid")
        g.log.info('Expected: Healing is not started')

        # Bring brick0 online
        g.log.info("Bring bricks: %s online", bricks_list[0])
        ret = bring_bricks_online(self.mnode, self.volname,
                                  [bricks_list[0]])
        self.assertTrue(ret, "Failed to bring bricks: %s online"
                        % bricks_list[0])
        g.log.info("Successfully brought all bricks:%s online",
                   bricks_list[0])

        # Bring brick1 offline
        g.log.info('Bringing bricks %s offline...', bricks_list[1])
        ret = bring_bricks_offline(self.volname, [bricks_list[1]])
        self.assertTrue(ret, 'Failed to bring bricks %s offline' %
                        bricks_list[1])

        ret = are_bricks_offline(self.mnode, self.volname,
                                 [bricks_list[1]])
        self.assertTrue(ret, 'Bricks %s are not offline'
                        % bricks_list[1])
        g.log.info('Bringing bricks %s offline is successful',
                   bricks_list[1])

        # Start healing
        # Need to use 'gluster volume heal' command to check error message
        # after g.run
        cmd = "gluster volume heal %s" % self.volname
        ret, _, err = g.run(self.mnode, cmd)
        self.assertTrue(ret, 'Heal is started')
        # Check for error message
        self.assertIn("Launching heal operation to perform index self heal on "
                      "volume %s has been unsuccessful" % self.volname,
                      err,
                      "Error message is not present or not valid")
        g.log.info('Expected: Healing is not started')

        # Bring brick 1 online
        g.log.info("Bring bricks: %s online", bricks_list[1])
        ret = bring_bricks_online(self.mnode, self.volname,
                                  [bricks_list[1]])
        self.assertTrue(ret, "Failed to bring bricks: %s online"
                        % bricks_list[1])
        g.log.info("Successfully brought all bricks:%s online",
                   bricks_list[1])

        # 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')

        # 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