summaryrefslogtreecommitdiffstats
path: root/tests/functional/glusterd/test_remove_brick_after_restart_glusterd.py
blob: 40012b00979b9af194818f188d9cf9dd07572abd (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
#  Copyright (C) 2018-2020  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.

from time import sleep
from glusto.core import Glusto as g
from glustolibs.gluster.gluster_base_class import GlusterBaseClass, runs_on
from glustolibs.gluster.volume_ops import (volume_create, volume_start,
                                           get_volume_list)
from glustolibs.gluster.brick_libs import get_all_bricks
from glustolibs.gluster.volume_libs import (cleanup_volume)
from glustolibs.gluster.peer_ops import (peer_probe, peer_detach,
                                         peer_probe_servers,
                                         nodes_from_pool_list,
                                         is_peer_connected)
from glustolibs.gluster.lib_utils import form_bricks_list
from glustolibs.gluster.brick_ops import remove_brick
from glustolibs.gluster.exceptions import ExecutionError
from glustolibs.gluster.mount_ops import mount_volume, umount_volume
from glustolibs.io.utils import validate_io_procs
from glustolibs.gluster.gluster_init import restart_glusterd


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

    def setUp(self):

        # Performing peer detach
        for server in self.servers[1:]:
            ret, _, _ = peer_detach(self.mnode, server)
            if ret != 0:
                raise ExecutionError("Peer detach failed")
            g.log.info("Peer detach SUCCESSFUL.")
        self.get_super_method(self, 'setUp')()

    def tearDown(self):

        # Cleanup and umount volume
        g.log.info("Starting to Unmount Volume %s", self.volname)
        ret = umount_volume(self.mounts[0].client_system,
                            self.mounts[0].mountpoint, mtype=self.mount_type)
        self.assertTrue(ret, ("Failed to Unmount Volume %s" % self.volname))

        # Clean up all volumes and peer probe to form cluster
        vol_list = get_volume_list(self.mnode)
        if vol_list is not None:
            for volume in vol_list:
                ret = cleanup_volume(self.mnode, volume)
                if not ret:
                    raise ExecutionError("Failed to cleanup volume")
                g.log.info("Volume deleted successfully : %s", volume)
        g.log.info("Successful in umounting the volume and Cleanup")

        # Peer probe detached servers
        pool = nodes_from_pool_list(self.mnode)
        for node in pool:
            peer_detach(self.mnode, node)
        ret = peer_probe_servers(self.mnode, self.servers)
        if not ret:
            raise ExecutionError("Failed to probe detached "
                                 "servers %s" % self.servers)
        g.log.info("Peer probe success for detached "
                   "servers %s", self.servers)
        self.get_super_method(self, 'tearDown')()

    def test_remove_brick(self):
        """
        In this test case:
        1. Trusted storage Pool of 4 nodes
        2. Create a distributed-replicated volumes with 4 bricks
        3. Start the volume
        4. Fuse mount the gluster volume on out of trusted nodes
        5. Create some data file
        6. Start remove-brick operation for one replica pair
        7. Restart glusterd on all nodes
        8. Try to commit the remove-brick operation while rebalance
           is in progress, it should fail
        """

        # pylint: disable=too-many-statements
        my_servers = self.servers[0:4]
        my_server_info = {}
        for server in self.servers[0:4]:
            my_server_info[server] = self.all_servers_info[server]
        for index in range(1, 4):
            ret, _, _ = peer_probe(self.servers[0], self.servers[index])
            self.assertEqual(ret, 0, ("peer probe from %s to %s is failed",
                                      self.servers[0], self.servers[index]))
            g.log.info("peer probe is success from %s to "
                       "%s", self.servers[0], self.servers[index])

        # Validating whether the peer are connected or not
        # In jenkins This case is failing saying peers are not in connected
        # state, that is reason adding a check whether peers are connected
        # or not
        count = 0
        while count < 30:
            ret = is_peer_connected(self.mnode, my_servers)
            if ret:
                g.log.info("Peers are in connected state")
                break
            sleep(3)
            count = count + 1
        self.assertTrue(ret, "Some peers are not in connected state")

        self.volname = "testvol"
        bricks_list = form_bricks_list(self.mnode, self.volname, 4,
                                       my_servers,
                                       my_server_info)
        g.log.info("Creating a volume %s ", self.volname)
        kwargs = {}
        kwargs['replica_count'] = 2
        ret = volume_create(self.mnode, self.volname,
                            bricks_list, force=False, **kwargs)
        self.assertEqual(ret[0], 0, ("Unable"
                                     "to create volume %s" % self.volname))
        g.log.info("Volume created successfully %s", self.volname)

        ret, _, _ = volume_start(self.mnode, self.volname, False)
        self.assertEqual(ret, 0, ("Failed to start the "
                                  "volume %s", self.volname))
        g.log.info("Get all the bricks of the volume")
        bricks_list = get_all_bricks(self.mnode, self.volname)
        self.assertIsNotNone(bricks_list, "Failed to get the brick list")
        g.log.info("Successfully got the list of bricks of volume")

        # Mounting a volume
        ret, _, _ = mount_volume(self.volname, mtype=self.mount_type,
                                 mpoint=self.mounts[0].mountpoint,
                                 mserver=self.mnode,
                                 mclient=self.mounts[0].client_system)
        self.assertEqual(ret, 0, ("Volume %s is not mounted") % self.volname)
        g.log.info("Volume mounted successfully : %s", self.volname)

        self.all_mounts_procs = []
        # Creating files
        command = ("cd %s/ ; "
                   "for i in `seq 1 10` ; "
                   "do mkdir l1_dir.$i ; "
                   "for j in `seq 1 5` ; "
                   "do mkdir l1_dir.$i/l2_dir.$j ; "
                   "for k in `seq 1 10` ; "
                   "do dd if=/dev/urandom of=l1_dir.$i/l2_dir.$j/test.$k "
                   "bs=128k count=$k ; "
                   "done ; "
                   "done ; "
                   "done ; "
                   % (self.mounts[0].mountpoint))

        proc = g.run_async(self.mounts[0].client_system, command,
                           user=self.mounts[0].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

        remove_brick_list = bricks_list[2:4]
        ret, _, _ = remove_brick(self.mnode, self.volname, remove_brick_list,
                                 'start')
        self.assertEqual(ret, 0, "Failed to start remove brick operation")
        g.log.info("Remove bricks operation started successfully")
        g.log.info("Restart glusterd on servers %s", self.servers)
        ret = restart_glusterd(self.servers)
        self.assertTrue(ret, ("Failed to restart glusterd on servers %s",
                              self.servers))
        g.log.info("Successfully restarted glusterd on servers %s",
                   self.servers)

        ret, _, _ = remove_brick(self.mnode, self.volname, remove_brick_list,
                                 'commit')
        self.assertNotEqual(ret, 0, "Remove brick commit ops should be fail")
        g.log.info("Remove bricks commit operation failure is expected")