summaryrefslogtreecommitdiffstats
path: root/tests/functional/arbiter/brick_cases/test_cyclic_brick_kill_list.py
blob: 8dbf0bcac4c639190e183609ff4172bae1ebd73e (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
#  Copyright (C) 2017-2018  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.

import time
from glusto.core import Glusto as g
from glustolibs.gluster.gluster_base_class import GlusterBaseClass, runs_on
from glustolibs.gluster.volume_libs import log_volume_info_and_status
from glustolibs.gluster.brick_libs import (
    bring_bricks_offline, bring_bricks_online,
    are_bricks_offline, get_all_bricks,
    are_bricks_online)
from glustolibs.gluster.heal_libs import (
    monitor_heal_completion, are_all_self_heal_daemons_are_online)
from glustolibs.gluster.exceptions import ExecutionError
from glustolibs.io.utils import (validate_io_procs,
                                 list_all_files_and_dirs_mounts,
                                 wait_for_io_to_complete)
from glustolibs.misc.misc_libs import upload_scripts


@runs_on([['replicated', 'distributed-replicated'],
          ['glusterfs', 'nfs']])
class ListMount(GlusterBaseClass):
    """
    Tetstcase involves killing brick in cyclic order and
    listing the directories after healing from mount point
    """
    @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/"
                             "fd_writes.py")
        cls.script_upload_path = ("/usr/share/glustolibs/io/scripts/"
                                  "fd_writes.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)

        cls.counter = 1
        # int: Value of counter is used for dirname-start-num argument for
        # file_dir_ops.py create_deep_dirs_with_files.

        # The --dir-length argument value for file_dir_ops.py
        # create_deep_dirs_with_files is set to 10 (refer to the cmd in setUp
        # method). This means every mount will create
        # 10 top level dirs. For every mountpoint/testcase to create new set of
        # dirs, we are incrementing the counter by --dir-length value i.e 10
        # in this test suite.

        # If we are changing the --dir-length to new value, ensure the counter
        # is also incremented by same value to create new set of files/dirs.

    def setUp(self):
        # 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 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

        Unmount Volume and Cleanup Volume
        """
        # Wait for IO to complete if io validation is not executed in the
        # test method
        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")

        # Unmount Volume and Cleanup 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 Unmount Volume and Cleanup Volume")
        g.log.info("Successful in Unmount Volume and Cleanup Volume")

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

    def test_files_on_mount(self):
        """""
        Description:-
        - I/O on the mounts
        - kill brick in cyclic order
        - list the files after healing
        """""

        # IO on the mount point
        # Each client will write 2 files each of 1 GB and keep
        # modifying the same file
        g.log.info("Starting IO on all mounts...")
        for mount_obj in self.mounts:
            g.log.info("Starting IO on %s:%s", mount_obj.client_system,
                       mount_obj.mountpoint)
            cmd = ("python %s "
                   "--file-sizes-list 1G "
                   "--chunk-sizes-list 128 "
                   "--write-time 900 "
                   "--num-of-files 2 "
                   "--base-file-name test_brick_down_from_client_%s.txt "
                   "--dir %s " % (self.script_upload_path,
                                  mount_obj.client_system,
                                  mount_obj.mountpoint))
            proc = g.run_async(mount_obj.client_system, cmd,
                               user=mount_obj.user)
            self.all_mounts_procs.append(proc)
            self.counter = self.counter + 10
        self.io_validation_complete = False

        # Killing bricks in cyclic order
        bricks_list = get_all_bricks(self.mnode, self.volname)

        # Total number of cyclic brick-down cycles to be executed
        number_of_cycles = 0
        while number_of_cycles < 3:
            number_of_cycles += 1
            for brick in bricks_list:
                # Bring brick offline
                g.log.info('Bringing bricks %s offline', brick)
                ret = bring_bricks_offline(self.volname, [brick])
                self.assertTrue(ret, ("Failed to bring bricks %s offline"
                                      % brick))

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

                # Introducing 30 second sleep when brick is down
                g.log.info("Waiting for 30 seconds, with ongoing IO while "
                           "brick %s is offline", brick)
                ret = time.sleep(30)

                # Bring brick online
                g.log.info('Bringing bricks %s online', brick)
                ret = bring_bricks_online(self.mnode, self.volname, [brick])
                self.assertTrue(ret, ("Failed to bring bricks %s online "
                                      % brick))
                g.log.info('Bricks %s are online', brick)

                # Check if bricks are online
                ret = are_bricks_online(self.mnode, self.volname, bricks_list)
                self.assertTrue(ret, 'Bricks %s are not online' % bricks_list)
                g.log.info('Bricks %s are online', bricks_list)

                # Check daemons
                g.log.info('Checking daemons...')
                ret = are_all_self_heal_daemons_are_online(self.mnode,
                                                           self.volname)
                self.assertTrue(ret, ("Some of the self-heal Daemons are "
                                      "offline"))
                g.log.info('All self-heal Daemons are online')

        # 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

        # Checking volume status
        g.log.info("Logging volume info and Status after bringing bricks "
                   "offline from the volume %s", self.volname)
        ret = log_volume_info_and_status(self.mnode, self.volname)
        self.assertTrue(ret, ("Logging volume info and status failed on "
                              "volume %s" % self.volname))
        g.log.info("Successful in logging volume info and status of volume %s",
                   self.volname)

        # Monitoring heals on the volume
        g.log.info("Wait for self-heal to completeon the volume")
        ret = monitor_heal_completion(self.mnode, self.volname)
        self.assertTrue(ret, ("Self heal didn't complete even after waiting "
                              "for 20 minutes."))
        g.log.info("self-heal is successful after changing the volume type "
                   "from replicated to arbitered volume")

        # List all files and dirs created
        g.log.info("List all files and directories:")
        ret = list_all_files_and_dirs_mounts(self.mounts)
        self.assertTrue(ret, "Failed to list all files and dirs")
        g.log.info("Listing all files and directories is successful")