summaryrefslogtreecommitdiffstats
path: root/tests/functional/glusterfind/test_glusterfind_when_node_down.py
blob: 1d8b2572aeab06a813b5426c3001ae5b93446fe7 (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
278
279
280
#  Copyright (C) 2020 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.

"""
Description:
    Test Glusterfind when node is down
"""

from random import choice
from time import sleep
from glusto.core import Glusto as g
from glustolibs.gluster.exceptions import ExecutionError
from glustolibs.gluster.gluster_base_class import GlusterBaseClass, runs_on
from glustolibs.gluster.volume_ops import set_volume_options
from glustolibs.gluster.peer_ops import wait_for_peers_to_connect
from glustolibs.gluster.lib_utils import list_files
from glustolibs.gluster.glusterfile import (
    file_exists,
    remove_file,
    check_if_pattern_in_file)
from glustolibs.gluster.glusterfind_ops import (
    gfind_create,
    gfind_list,
    gfind_pre,
    gfind_post,
    gfind_delete)
from glustolibs.gluster.gluster_init import (
    stop_glusterd,
    start_glusterd,
    wait_for_glusterd_to_start)
from glustolibs.misc.misc_libs import (
    reboot_nodes,
    are_nodes_online)


@runs_on([["replicated", "distributed-replicated", "dispersed",
           "distributed", "distributed-dispersed"],
          ["glusterfs"]])
class TestGlusterFindNodeDown(GlusterBaseClass):
    """
    Test glusterfind operation when a node is down.
    """

    def setUp(self):
        """
        setup volume and mount volume
        Initiate necessary variables
        """

        # calling GlusterBaseClass setUp
        self.get_super_method(self, 'setUp')()

        self.file_limit = 0

        # Setup Volume and Mount Volume
        ret = self.setup_volume_and_mount_volume(mounts=self.mounts)
        if not ret:
            raise ExecutionError("Failed to Setup_Volume %s" % self.volname)
        g.log.info("Successful in Setup Volume %s", self.volname)
        self.session = "test-session-%s" % self.volname
        self.outfiles = [("/tmp/test-outfile-%s-%s.txt"
                          % (self.volname, i))for i in range(0, 2)]

        # Set the changelog rollover-time to 1 second
        # This needs to be done in order for glusterfind to keep checking
        # for changes in the mount point
        option = {'changelog.rollover-time': '1'}
        ret = set_volume_options(self.mnode, self.volname, option)
        if not ret:
            raise ExecutionError("Failed to set the volume option %s for %s"
                                 % (option, self.volname))
        g.log.info("Successfully set the volume option for the volume %s",
                   self.volname)

    def _perform_io_and_validate_presence_of_files(self):
        """
        Function to perform the IO and validate the presence of files.
        """
        self.file_limit += 10
        # Starting IO on the mounts
        cmd = ("cd %s ; touch file{%d..%d}" % (self.mounts[0].mountpoint,
                                               self.file_limit-10,
                                               self.file_limit))

        ret, _, _ = g.run(self.mounts[0].client_system, cmd)
        self.assertEqual(ret, 0, "Failed to create files on mountpoint")
        g.log.info("Files created successfully on mountpoint")

        # Gather the list of files from the mount point
        files = list_files(self.mounts[0].client_system,
                           self.mounts[0].mountpoint)
        self.assertIsNotNone(files, "Failed to get the list of files")
        g.log.info("Successfully gathered the list of files from mount point")

        # Check if the files exist
        for filename in files:
            ret = file_exists(self.mounts[0].client_system, filename)
            self.assertTrue(ret, ("Unexpected: File '%s' does not exist"
                                  % filename))
            g.log.info("Successfully validated existence of '%s'", filename)

    def _perform_glusterfind_pre_and_validate_outfile(self):
        """
        Function to perform glusterfind pre and validate outfile
        """
        # Perform glusterfind pre for the session
        ret, _, _ = gfind_pre(self.mnode, self.volname, self.session,
                              self.outfiles[0], full=True, noencode=True,
                              debug=True)
        self.assertEqual(ret, 0, ("Failed to perform glusterfind pre"))
        g.log.info("Successfully performed glusterfind pre")

        # Check if the outfile exists
        ret = file_exists(self.mnode, self.outfiles[0])
        self.assertTrue(ret, ("Unexpected: File '%s' does not exist"
                              % self.outfiles[0]))
        g.log.info("Successfully validated existence of '%s'",
                   self.outfiles[0])

        # Check if all the files are listed in the outfile
        for i in range(1, self.file_limit+1):
            ret = check_if_pattern_in_file(self.mnode, "file%s" % i,
                                           self.outfiles[0])
            self.assertEqual(ret, 0, ("File 'file%s' not listed in %s"
                                      % (i, self.outfiles[0])))
            g.log.info("File 'file%s' listed in %s", i, self.outfiles[0])

    def test_gfind_when_node_down(self):
        """
        Verifying the glusterfind functionality when node is down.

        1. Create a volume
        2. Create a session on the volume
        3. Create various files from mount point
        4. Bring down glusterd on one of the node
        5. Perform glusterfind pre
        6. Perform glusterfind post
        7. Check the contents of outfile
        8. Create more files from mountpoint
        9. Reboot one of the nodes
        10. Perform gluserfind pre
        11. Perform glusterfind post
        12. Check the contents of outfile
        """

        # pylint: disable=too-many-statements
        # Create a session for the volume
        ret, _, _ = gfind_create(self.mnode, self.volname, self.session)
        self.assertEqual(ret, 0, ("Unexpected: Creation of a session for the "
                                  "volume %s failed" % self.volname))
        g.log.info("Successfully created a session for the volume %s",
                   self.volname)

        # Perform glusterfind list to check if session exists
        _, out, _ = gfind_list(self.mnode, volname=self.volname,
                               sessname=self.session)
        self.assertNotEqual(out, "No sessions found.",
                            "Failed to list the glusterfind session")
        g.log.info("Successfully listed the glusterfind session")

        self._perform_io_and_validate_presence_of_files()

        # Wait for changelog to get updated
        sleep(2)

        # Bring one of the node down.
        self.random_server = choice(self.servers[1:])
        ret = stop_glusterd(self.random_server)
        self.assertTrue(ret, "Failed to stop glusterd on one node.")
        g.log.info("Succesfully stopped glusterd on one node.")

        self._perform_glusterfind_pre_and_validate_outfile()

        # Perform glusterfind post for the session
        ret, _, _ = gfind_post(self.mnode, self.volname, self.session)
        self.assertEqual(ret, 0, ("Failed to perform glusterfind post"))
        g.log.info("Successfully performed glusterfind post")

        # Bring glusterd which was downed on a random node, up.
        ret = start_glusterd(self.random_server)
        self.assertTrue(ret, "Failed to start glusterd on %s"
                        % self.random_server)
        g.log.info("Successfully started glusterd on node : %s",
                   self.random_server)

        # Waiting for glusterd to start completely.
        ret = wait_for_glusterd_to_start(self.random_server)
        self.assertTrue(ret, "glusterd is not running on %s"
                        % self.random_server)
        g.log.info("glusterd is started and running on %s",
                   self.random_server)

        self._perform_io_and_validate_presence_of_files()

        # Perform IO
        self._perform_io_and_validate_presence_of_files()

        # Wait for changelog to get updated
        sleep(2)

        # Reboot one of the nodes.
        self.random_server = choice(self.servers[1:])
        ret = reboot_nodes(self.random_server)
        self.assertTrue(ret, "Failed to reboot the said node.")
        g.log.info("Successfully started reboot process on one node.")

        self._perform_glusterfind_pre_and_validate_outfile()

        # Perform glusterfind post for the session
        ret, _, _ = gfind_post(self.mnode, self.volname, self.session)
        self.assertEqual(ret, 0, ("Failed to perform glusterfind post"))
        g.log.info("Successfully performed glusterfind post")

        # Gradual sleep backoff till the node has rebooted.
        counter = 0
        timeout = 300
        ret = False
        while counter < timeout:
            ret, _ = are_nodes_online(self.random_server)
            if not ret:
                g.log.info("Node's offline, Retrying after 5 seconds ...")
                sleep(5)
                counter += 5
            else:
                ret = True
                break
        self.assertTrue(ret, "Node is still offline.")
        g.log.info("Rebooted node is online")

        # Wait for glusterd to start completely
        ret = wait_for_glusterd_to_start(self.random_server)
        self.assertTrue(ret, "glusterd is not running on %s"
                        % self.random_server)
        g.log.info("glusterd is started and running on %s",
                   self.random_server)

    def tearDown(self):
        """
        tearDown for every test
        Clean up and unmount the volume
        """
        # calling GlusterBaseClass tearDown
        self.get_super_method(self, 'tearDown')()

        # Delete the glusterfind sessions
        ret, _, _ = gfind_delete(self.mnode, self.volname, self.session)
        if ret:
            raise ExecutionError("Failed to delete session %s" % self.session)
        g.log.info("Successfully deleted session %s", self.session)

        # Remove the outfiles created during 'glusterfind pre'
        for out in self.outfiles:
            ret = remove_file(self.mnode, out, force=True)
            if not ret:
                raise ExecutionError("Failed to remove the outfile %s" % out)
        g.log.info("Successfully removed the outfiles")

        # Wait for the peers to be connected.
        ret = wait_for_peers_to_connect(self.mnode, self.servers, 100)
        if not ret:
            raise ExecutionError("Peers are not in connected state.")

        # Cleanup the volume
        ret = self.unmount_volume_and_cleanup_volume(mounts=self.mounts)
        if not ret:
            raise ExecutionError("Failed to Cleanup Volume")
        g.log.info("Successful in Cleanup Volume")