summaryrefslogtreecommitdiffstats
path: root/tests/functional/afr/test_shd_should_not_crash_executed_heal_info.py
blob: e6a19527db97b5cfcb5623fe81bde58e80f9605b (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
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
#  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.

import sys

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_ops import set_volume_options
from glustolibs.gluster.brick_libs import (bring_bricks_offline,
                                           are_bricks_offline,
                                           get_all_bricks)
from glustolibs.gluster.heal_ops import get_heal_info_summary
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']])
class VerifySelfHealTriggersHealCommand(GlusterBaseClass):
    """
    Description:
        Verify self-heal Triggers with self heal with heal command
    """
    @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)

        # Override Volumes
        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

        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")

        # 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_shd_should_not_crash_executed_heal_info(self):
        """
        - set "entry-self-heal", "metadata-self-heal", "data-self-heal" to off
        - write a few files
        - bring down brick0
        - add IO
        - do a heal info and check for files pending heal on last 2 bricks
        - set "performance.enable-least-priority" to "enable"
        - bring down brick1
        - set the "quorum-type" to "fixed"
        - add IO
        - do a heal info and check for files pending heal on the last brick
        """
        # pylint: disable=too-many-statements
        bricks_list = get_all_bricks(self.mnode, self.volname)
        # Setting options
        g.log.info('Setting options...')
        options = {"metadata-self-heal": "off",
                   "entry-self-heal": "off",
                   "data-self-heal": "off"}
        ret = set_volume_options(self.mnode, self.volname, options)
        self.assertTrue(ret, 'Failed to set options %s' % options)
        g.log.info("Successfully set %s for volume %s",
                   options, self.volname)

        # 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 files
            g.log.info('Creating files...')
            command = ("/usr/bin/env python%d %s create_files -f 10 "
                       "--fixed-file-size 1M %s" % (
                           sys.version_info.major, 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
        self.assertTrue(
            validate_io_procs(self.all_mounts_procs, self.mounts),
            "IO failed on some of the clients"
        )
        self.io_validation_complete = True

        # 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])

        # Creating files on client side
        number_of_files_one_brick_off = '1000'
        self.all_mounts_procs = []
        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 = ("/usr/bin/env python%d %s create_files "
                       "-f %s "
                       "--fixed-file-size 1k "
                       "--base-file-name new_file "
                       "%s"
                       % (sys.version_info.major,
                          self.script_upload_path,
                          number_of_files_one_brick_off,
                          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
        self.assertTrue(
            validate_io_procs(self.all_mounts_procs, self.mounts),
            "IO failed on some of the clients"
        )
        self.io_validation_complete = True

        # Get heal info
        g.log.info("Getting heal info...")
        heal_info_data = get_heal_info_summary(self.mnode, self.volname)
        self.assertIsNotNone(heal_info_data, 'Failed to get heal info.')
        g.log.info('Success in getting heal info')

        # Check quantity of file pending heal
        for brick in bricks_list[1:]:
            self.assertEqual(heal_info_data[brick]['numberOfEntries'],
                             str(int(number_of_files_one_brick_off)+1),
                             'Number of files pending heal is not correct')

        # Setting options
        g.log.info('Setting options...')
        options = {"performance.enable-least-priority": "enable"}
        ret = set_volume_options(self.mnode, self.volname, options)
        self.assertTrue(ret, 'Failed to set options %s' % options)
        g.log.info("Successfully set %s for volume %s",
                   options, self.volname)

        # 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])

        # Setting options
        g.log.info('Setting options...')
        options = {"quorum-type": "fixed"}
        ret = set_volume_options(self.mnode, self.volname, options)
        self.assertTrue(ret, 'Failed to set options %s' % options)
        g.log.info("Successfully set %s for volume %s",
                   options, self.volname)

        # Creating files on client side
        number_of_files_two_brick_off = '100'
        self.all_mounts_procs = []
        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 = ("/usr/bin/env python%d %s create_files "
                       "-f %s "
                       "--fixed-file-size 1k "
                       "--base-file-name new_new_file "
                       "%s"
                       % (sys.version_info.major,
                          self.script_upload_path,
                          number_of_files_two_brick_off,
                          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
        self.assertTrue(
            validate_io_procs(self.all_mounts_procs, self.mounts),
            "IO failed on some of the clients"
        )
        self.io_validation_complete = True

        # Get heal info
        g.log.info("Getting heal info...")
        heal_info_data = get_heal_info_summary(self.mnode, self.volname)
        self.assertIsNotNone(heal_info_data, 'Failed to get heal info.')
        g.log.info('Success in getting heal info')

        # Check quantity of file pending heal
        number_of_files_to_check = str(int(number_of_files_one_brick_off) +
                                       int(number_of_files_two_brick_off) + 1)
        self.assertEqual(heal_info_data[bricks_list[-1]]['numberOfEntries'],
                         number_of_files_to_check,
                         'Number of files pending heal is not correct')