summaryrefslogtreecommitdiffstats
path: root/tests/functional/dht/test_rebalance_dir_file_from_multiple_clients.py
blob: 3644061476267746a5ac07a9e17d6a9b5e405c8f (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
#  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 sys

from glusto.core import Glusto as g

from glustolibs.gluster.constants import FILETYPE_DIRS
from glustolibs.gluster.constants import \
    TEST_LAYOUT_IS_COMPLETE as LAYOUT_IS_COMPLETE
from glustolibs.gluster.dht_test_utils import validate_files_in_dir
from glustolibs.gluster.exceptions import ExecutionError
from glustolibs.gluster.gluster_base_class import GlusterBaseClass, runs_on
from glustolibs.gluster.rebalance_ops import (
    get_rebalance_status,
    rebalance_start,
    rebalance_status,
    wait_for_rebalance_to_complete
)
from glustolibs.gluster.volume_libs import (
    expand_volume,
    log_volume_info_and_status,
    verify_all_process_of_volume_are_online,
    wait_for_volume_process_to_be_online
)
from glustolibs.io.utils import (
    list_all_files_and_dirs_mounts,
    validate_io_procs,
    wait_for_io_to_complete
)
from glustolibs.misc.misc_libs import upload_scripts


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

    @classmethod
    def setUpClass(cls):

        # Calling GlusterBaseClass setUpClass
        cls.get_super_method(cls, 'setUpClass')()

        # Setup Volume and Mount Volume
        g.log.info("Starting to Setup Volume and Mount Volume")
        ret = cls.setup_volume_and_mount_volume(mounts=cls.mounts)
        if not ret:
            raise ExecutionError("Failed to Setup_Volume and Mount_Volume")
        g.log.info("Successful in Setup Volume and Mount Volume")

        # 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)

    def setUp(self):
        """
        - Setup Volume and Mount Volume
        - setUp starts the io from all the mounts.
        - IO creates deep dirs and files.
        """
        # Calling GlusterBaseClass setUp
        self.get_super_method(self, 'setUp')()

        # 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")

        # Start IO on mounts
        g.log.info("Starting IO on all mounts...")
        self.all_mounts_procs = []

        # Value of counter(index) 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.

        for index, mount_obj in enumerate(self.mounts, start=1):
            g.log.info("Starting IO on %s:%s", mount_obj.client_system,
                       mount_obj.mountpoint)
            cmd = ("/usr/bin/env python%d %s create_deep_dirs_with_files "
                   "--dirname-start-num %d "
                   "--dir-depth 2 "
                   "--dir-length 5 "
                   "--max-num-of-dirs 5 "
                   "--num-of-files 5 %s" % (
                       sys.version_info.major, self.script_upload_path,
                       index + 10, mount_obj.mountpoint))
            proc = g.run_async(mount_obj.client_system, cmd,
                               user=mount_obj.user)
            self.all_mounts_procs.append(proc)
        self.io_validation_complete = False

    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 on all mounts: Success")

            # 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: 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("Unmount Volume and Cleanup Volume: Fail")
        g.log.info("Unmount Volume and Cleanup Volume: Success")

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

    def test_expanding_volume_when_io_in_progress(self):
        # pylint: disable=too-many-statements
        # Log Volume Info and Status before expanding the volume.
        g.log.info("Logging volume info and Status before expanding volume")
        log_volume_info_and_status(self.mnode, self.volname)

        # Expanding volume by adding bricks to the volume when IO in progress
        g.log.info("Start adding bricks to volume when IO in progress")
        ret = expand_volume(self.mnode, self.volname, self.servers,
                            self.all_servers_info)
        self.assertTrue(ret, ("Failed to expand the volume while IO in "
                              "progress on volume %s", self.volname))
        g.log.info("Expanding volume while IO in progress on "
                   "volume %s : Success", self.volname)

        # Wait for gluster processes to come online
        g.log.info("Wait for gluster processes to come online")
        ret = wait_for_volume_process_to_be_online(self.mnode, self.volname)
        self.assertTrue(ret, ("Failed to wait for volume %s processes to "
                              "be online", self.volname))
        g.log.info("Waiting for volume %s process to be online", self.volname)

        # Log Volume Info and Status after expanding the volume
        g.log.info("Logging volume info and Status after expanding volume")
        log_volume_info_and_status(self.mnode, self.volname)

        # Verify volume's all process are online
        g.log.info("Verifying volume's all process are online")
        ret = verify_all_process_of_volume_are_online(self.mnode,
                                                      self.volname)
        self.assertTrue(ret, ("Volume %s : All process are not online",
                              self.volname))
        g.log.info("Volume %s : All process are online", self.volname)

        # Start Rebalance
        g.log.info("Starting Rebalance on the volume")
        ret, _, _ = rebalance_start(self.mnode, self.volname)
        self.assertEqual(ret, 0, ("Failed to start rebalance on the volume "
                                  "%s", self.volname))
        g.log.info("Started rebalance on the volume %s: Success",
                   self.volname)

        # Wait for rebalance to complete
        g.log.info("Waiting for rebalance to complete")
        ret = wait_for_rebalance_to_complete(self.mnode, self.volname,
                                             timeout=600)
        self.assertTrue(ret, ("Rebalance is not yet complete on the volume "
                              "%s", self.volname))
        g.log.info("Rebalance status on volume %s: Complete",
                   self.volname)

        # Check Rebalance status after rebalance is complete
        g.log.info("Checking Rebalance status")
        ret, _, _ = rebalance_status(self.mnode, self.volname)
        self.assertEqual(ret, 0, ("Failed to get rebalance status for the "
                                  "volume %s", self.volname))
        g.log.info("Rebalance status on volume %s: Complete",
                   self.volname)

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

        # 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("List all files and directories: Success")

        # DHT Layout validation
        g.log.debug("Verifying hash layout values %s:%s",
                    self.clients[0], self.mounts[0].mountpoint)
        ret = validate_files_in_dir(self.clients[0], self.mounts[0].mountpoint,
                                    test_type=LAYOUT_IS_COMPLETE,
                                    file_type=FILETYPE_DIRS)
        self.assertTrue(ret, "LAYOUT_IS_COMPLETE: FAILED")
        g.log.info("LAYOUT_IS_COMPLETE: PASS")

        # Checking if there are any migration failures
        status = get_rebalance_status(self.mnode, self.volname)
        for each_node in status['node']:
            self.assertEqual(0, int(each_node['failures']),
                             "Rebalance failed to migrate few files on %s" %
                             each_node['nodeName'])
            g.log.info("No migration failures on %s", each_node['nodeName'])