summaryrefslogtreecommitdiffstats
path: root/tests/functional/disperse/test_ec_verify_full_heal.py
blob: e0074d51346775b0bbed6ca3bdea6e893adb324f (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
#  Copyright (C) 2015-2016  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_libs import get_subvols
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_full
from glustolibs.misc.misc_libs import upload_scripts
from glustolibs.io.utils import (collect_mounts_arequal,
                                 validate_io_procs,
                                 list_all_files_and_dirs_mounts,
                                 wait_for_io_to_complete)


@runs_on([['dispersed', 'distributed-dispersed'],
          ['glusterfs']])
class TestHealFull(GlusterBaseClass):

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

        # Setup Volumes
        if self.volume_type == "distributed-replicated":
            self.volume_configs = []

        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,
                                                 volume_create_force=False)
        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
        """
        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")

        # 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_heal_full_after_deleting_files(self):
        """
        - Create IO
        - Calculate arequal from mount
        - Delete data from backend from the EC volume
        - Trigger heal full
        - Check if heal is completed
        - Check for split-brain
        - Calculate arequal checksum and compare it
        """
        # pylint: disable=too-many-locals,too-many-statements
        # 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 dirs with file
            g.log.info('Creating dirs with file...')
            command = ("python %s create_deep_dirs_with_files "
                       "-d 2 "
                       "-l 2 "
                       "-n 2 "
                       "-f 20 "
                       "%s"
                       % (self.script_upload_path, 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

        # Validate IO
        g.log.info("Wait for IO to complete and validate IO ...")
        ret = validate_io_procs(self.all_mounts_procs, self.mounts)
        self.assertTrue(ret, "IO failed on some of the clients")
        self.io_validation_complete = True
        g.log.info("IO is successful on all mounts")

        # Get areequal before deleting the files from brick
        g.log.info('Getting areequal before getting bricks offline...')
        ret, result_before_killing_procs = collect_mounts_arequal(self.mounts)
        self.assertTrue(ret, 'Failed to get arequal')
        g.log.info('Getting areequal before getting bricks offline '
                   'is successful')

        subvols = get_subvols(self.mnode, self.volname)['volume_subvols']

        # Delete data from backend from the erasure node
        for subvol in subvols:
            erasure = subvol[-1]
            g.log.info('Clearing ec brick %s', erasure)
            node, brick_path = erasure.split(':')
            ret, _, err = g.run(node, 'cd %s/ ; rm -rf *' % brick_path)
            g.log.error('Clearing ec brick %s is unsuccessful', erasure)
            self.assertFalse(ret, err)
        g.log.info('Clearing data from brick is successful')

        # Trigger heal full
        ret = trigger_heal_full(self.mnode, self.volname)

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

        # Comparing areequals
        self.assertEqual(result_before_killing_procs, result_after_healing,
                         'Areequals areequals before before killing arbiter '
                         'processes and after healing are not equal')
        g.log.info('Areequals areequals before before killing arbiter '
                   'processes and after healing equal')