summaryrefslogtreecommitdiffstats
path: root/tests/functional/arbiter/test_oom_on_client_heal_is_in_progress_arbiter.py
blob: 0e55cdf8ab64f2d237dfabb7e8fc1c063a5e1873 (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
#  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.brick_libs import (bring_bricks_offline,
                                           bring_bricks_online,
                                           are_bricks_offline,
                                           get_all_bricks)
from glustolibs.io.utils import (validate_io_procs,
                                 list_all_files_and_dirs_mounts,
                                 wait_for_io_to_complete)
from glustolibs.gluster.lib_utils import list_files
from glustolibs.misc.misc_libs import upload_scripts


@runs_on([['replicated'],
          ['glusterfs', 'nfs', 'cifs']])
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)

        self.all_mounts_procs = []
        self.io_validation_complete = False

        # 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
        """
        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_oom_on_client_heal_in_progress(self):
        """
        - Create a 1x(2+1) arbiter replicate volume
        - Create IO
        - Bring down the 1-st data brick while creating IO
        - Bring up the 1-st data brick after creating and checking IO
        - Bring down the 3-d arbiter brick
        - Bring up the 3-d arbiter brick
        - Check there no any oom by listing the files from mountpoint
        """

        # Creating IO 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 files
            g.log.info('Creating files...')
            command = ("python %s create_files "
                       "-f 1000 "
                       "--fixed-file-size 10k "
                       "%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

        # 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)

        # 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

        # Bring 1-st 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)

        # Bring brick 3 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 brick 3 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)

        # Get file list from mountpoint
        g.log.info('Getting file list from mountpoints...')
        for mount_obj in self.mounts:
            g.log.info("Getting file list for %s:%s",
                       mount_obj.client_system, mount_obj.mountpoint)
            g.log.info('Getting file list...')
            file_list = list_files(mount_obj.client_system,
                                   mount_obj.mountpoint)
            self.assertIsNotNone(file_list)
        g.log.info('Getting file list from mountpoints finished successfully')