[Test] Test self-heal of 50k files

Steps:
- Create an volume and mount it
- Bring bricks offline
- Write 50k files
- Bring bricks online
- Monitor heal completion
- Check for split-brain

Change-Id: I40739effdfa1c1068fa0628467154b9a667161a3
Signed-off-by: ubansal <ubansal@redhat.com>

1 files changed, 140 insertions, 0 deletions

diff --git a/tests/functional/arbiter/test_self_heal_50k_files.py b/tests/functional/arbiter/test_self_heal_50k_files.py
new file mode 100644
index 000000000..887959fa0
--- /dev/null
+++ b/tests/functional/arbiter/test_self_heal_50k_files.py
@@ -0,0 +1,140 @@
+#  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.
+
+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_libs import (
+    verify_all_process_of_volume_are_online,
+    wait_for_volume_process_to_be_online)
+from glustolibs.gluster.brick_libs import (select_bricks_to_bring_offline,
+                                           bring_bricks_offline,
+                                           bring_bricks_online,
+                                           are_bricks_offline)
+from glustolibs.gluster.heal_libs import (monitor_heal_completion,
+                                          is_volume_in_split_brain)
+from glustolibs.io.utils import validate_io_procs
+
+
+@runs_on([['arbiter', 'distributed-arbiter'], ['glusterfs']])
+class TestSelfHeal50kFiles(GlusterBaseClass):
+    """
+    Description:
+        Arbiter self heal of 50k files
+    """
+    def setUp(self):
+        # Calling GlusterBaseClass
+        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")
+
+    def tearDown(self):
+        """
+        Cleanup and umount volume
+        """
+
+        # 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_self_heal_50k_files(self):
+        """
+        Description:
+        - Select bricks to bring offline
+        - Bring brick offline
+        - Create 50k files
+        - Validate IO
+        - Bring bricks online
+        - Monitor heal
+        - Check for split-brain
+        - Validate IO
+        """
+        # pylint: disable=too-many-statements,too-many-locals
+        # Select bricks to bring offline
+        bricks_to_bring_offline_dict = select_bricks_to_bring_offline(
+            self.mnode, self.volname)
+        bricks_to_bring_offline = bricks_to_bring_offline_dict['volume_bricks']
+
+        # Bring brick offline
+        ret = bring_bricks_offline(self.volname, bricks_to_bring_offline)
+        self.assertTrue(ret, 'Failed to bring bricks %s offline' %
+                        bricks_to_bring_offline)
+        self.assertIsNotNone(bricks_to_bring_offline, "List is empty")
+
+        ret = are_bricks_offline(self.mnode, self.volname,
+                                 bricks_to_bring_offline)
+        self.assertTrue(ret, 'Bricks %s are not offline'
+                        % bricks_to_bring_offline)
+        g.log.info('Bringing bricks %s offline is successful',
+                   bricks_to_bring_offline)
+
+        # Create 50k files
+        command = ("cd %s ; "
+                   "for i in `seq 1 50000` ; "
+                   "do dd if=/dev/urandom of=test.$i "
+                   "bs=100k count=1 ;  "
+                   "done ;"
+                   % self.mounts[0].mountpoint)
+        proc = g.run_async(self.mounts[0].client_system, command,
+                           user=self.mounts[0].user)
+
+        # Validate IO
+        self.assertTrue(
+            validate_io_procs([proc], self.mounts[0]),
+            "IO failed on some of the clients"
+        )
+
+        # Bring brick online
+        ret = bring_bricks_online(self.mnode, self.volname,
+                                  bricks_to_bring_offline)
+        self.assertTrue(ret, 'Failed to bring bricks %s online' %
+                        bricks_to_bring_offline)
+        g.log.info('Bringing bricks %s online is successful',
+                   bricks_to_bring_offline)
+
+        # Wait for volume processes to be 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("Successful in waiting for volume %s processes to be "
+                   "online", self.volname)
+
+        # Verify 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)
+
+        # Monitor heal completion
+        ret = monitor_heal_completion(self.mnode, self.volname,
+                                      timeout_period=3000)
+        self.assertTrue(ret, 'Heal has not yet completed')
+
+        # Check for split-brain
+        ret = is_volume_in_split_brain(self.mnode, self.volname)
+        self.assertFalse(ret, 'Volume is in split-brain state')
+        g.log.info('Volume is not in split-brain state')