swift/test/unit/cli/test_relinker.py
Christian Schwede e1140666d6 Add support to increase object ring partition power
This patch adds methods to increase the partition power of an existing
object ring without downtime for the users using a 3-step process. Data
won't be moved to other nodes; objects using the new increased partition
power will be located on the same device and are hardlinked to avoid
data movement.

1. A new setting "next_part_power" will be added to the rings, and once
the proxy server reloaded the rings it will send this value to the
object servers on any write operation. Object servers will now create a
hard-link in the new location to the original DiskFile object. Already
existing data will be relinked using a new tool in the new locations
using hardlinks.

2. The actual partition power itself will be increased. Servers will now
use the new partition power to read from and write to. No longer
required hard links in the old object location have to be removed now by
the relinker tool; the relinker tool reads the next_part_power setting
to find object locations that need to be cleaned up.

3. The "next_part_power" flag will be removed.

This mostly implements the spec in [1]; however it's not using an
"epoch" as described there. The idea of the epoch was to store data
using different partition powers in their own namespace to avoid
conflicts with auditors and replicators as well as being able to abort
such an operation and just remove the new tree.  This would require some
heavy change of the on-disk data layout, and other object-server
implementations would be required to adopt this scheme too.

Instead the object-replicator is now aware that there is a partition
power increase in progress and will skip replication of data in that
storage policy; the relinker tool should be simply run and afterwards
the partition power will be increased. This shouldn't take that much
time (it's only walking the filesystem and hardlinking); impact should
be low therefore. The relinker should be run on all storage nodes at the
same time in parallel to decrease the required time (though this is not
mandatory). Failures during relinking should not affect cluster
operations - relinking can be even aborted manually and restarted later.

Auditors are not quarantining objects written to a path with a different
partition power and therefore working as before (though they are reading
each object twice in the worst case before the no longer needed hard
links are removed).

Co-Authored-By: Alistair Coles <alistair.coles@hpe.com>
Co-Authored-By: Matthew Oliver <matt@oliver.net.au>
Co-Authored-By: Tim Burke <tim.burke@gmail.com>

[1] https://specs.openstack.org/openstack/swift-specs/specs/in_progress/
increasing_partition_power.html

Change-Id: I7d6371a04f5c1c4adbb8733a71f3c177ee5448bb
2017-06-15 15:08:48 -07:00

173 lines
6.5 KiB
Python

# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
# implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import binascii
import os
import shutil
import struct
import tempfile
import unittest
from swift.cli import relinker
from swift.common import exceptions, ring, utils
from swift.common import storage_policy
from swift.common.storage_policy import (
StoragePolicy, StoragePolicyCollection, POLICIES)
from swift.obj.diskfile import write_metadata
from test.unit import FakeLogger
class TestRelinker(unittest.TestCase):
def setUp(self):
self.logger = FakeLogger()
self.testdir = tempfile.mkdtemp()
self.devices = os.path.join(self.testdir, 'node')
shutil.rmtree(self.testdir, ignore_errors=1)
os.mkdir(self.testdir)
os.mkdir(self.devices)
self.rb = ring.RingBuilder(8, 6.0, 1)
for i in range(6):
ip = "127.0.0.%s" % i
self.rb.add_dev({'id': i, 'region': 0, 'zone': 0, 'weight': 1,
'ip': ip, 'port': 10000, 'device': 'sda1'})
self.rb.rebalance(seed=1)
self.existing_device = 'sda1'
os.mkdir(os.path.join(self.devices, self.existing_device))
self.objects = os.path.join(self.devices, self.existing_device,
'objects')
os.mkdir(self.objects)
self._hash = utils.hash_path('a/c/o')
digest = binascii.unhexlify(self._hash)
part = struct.unpack_from('>I', digest)[0] >> 24
self.next_part = struct.unpack_from('>I', digest)[0] >> 23
self.objdir = os.path.join(
self.objects, str(part), self._hash[-3:], self._hash)
os.makedirs(self.objdir)
self.object_fname = "1278553064.00000.data"
self.objname = os.path.join(self.objdir, self.object_fname)
with open(self.objname, "wb") as dummy:
dummy.write("Hello World!")
write_metadata(dummy, {'name': '/a/c/o', 'Content-Length': '12'})
test_policies = [StoragePolicy(0, 'platin', True)]
storage_policy._POLICIES = StoragePolicyCollection(test_policies)
self.expected_dir = os.path.join(
self.objects, str(self.next_part), self._hash[-3:], self._hash)
self.expected_file = os.path.join(self.expected_dir, self.object_fname)
def _save_ring(self):
rd = self.rb.get_ring()
for policy in POLICIES:
rd.save(os.path.join(
self.testdir, '%s.ring.gz' % policy.ring_name))
# Enforce ring reloading in relinker
policy.object_ring = None
def tearDown(self):
shutil.rmtree(self.testdir, ignore_errors=1)
storage_policy.reload_storage_policies()
def test_relink(self):
self.rb.prepare_increase_partition_power()
self._save_ring()
relinker.relink(self.testdir, self.devices, True)
self.assertTrue(os.path.isdir(self.expected_dir))
self.assertTrue(os.path.isfile(self.expected_file))
stat_old = os.stat(os.path.join(self.objdir, self.object_fname))
stat_new = os.stat(self.expected_file)
self.assertEqual(stat_old.st_ino, stat_new.st_ino)
def _common_test_cleanup(self, relink=True):
# Create a ring that has prev_part_power set
self.rb.prepare_increase_partition_power()
self.rb.increase_partition_power()
self._save_ring()
os.makedirs(self.expected_dir)
if relink:
# Create a hardlink to the original object name. This is expected
# after a normal relinker run
os.link(os.path.join(self.objdir, self.object_fname),
self.expected_file)
def test_cleanup(self):
self._common_test_cleanup()
self.assertEqual(0, relinker.cleanup(self.testdir, self.devices, True))
# Old objectname should be removed, new should still exist
self.assertTrue(os.path.isdir(self.expected_dir))
self.assertTrue(os.path.isfile(self.expected_file))
self.assertFalse(os.path.isfile(
os.path.join(self.objdir, self.object_fname)))
def test_cleanup_not_yet_relinked(self):
self._common_test_cleanup(relink=False)
self.assertEqual(1, relinker.cleanup(self.testdir, self.devices, True))
self.assertTrue(os.path.isfile(
os.path.join(self.objdir, self.object_fname)))
def test_cleanup_deleted(self):
self._common_test_cleanup()
# Pretend the object got deleted inbetween and there is a tombstone
fname_ts = self.expected_file[:-4] + "ts"
os.rename(self.expected_file, fname_ts)
self.assertEqual(0, relinker.cleanup(self.testdir, self.devices, True))
def test_cleanup_doesnotexist(self):
self._common_test_cleanup()
# Pretend the file in the new place got deleted inbetween
os.remove(self.expected_file)
self.assertEqual(
1, relinker.cleanup(self.testdir, self.devices, True, self.logger))
self.assertEqual(self.logger.get_lines_for_level('warning'),
['Error cleaning up %s: %s' % (self.objname,
repr(exceptions.DiskFileNotExist()))])
def test_cleanup_non_durable_fragment(self):
self._common_test_cleanup()
# Actually all fragments are non-durable and raise and DiskFileNotExist
# in EC in this test. However, if the counterpart exists in the new
# location, this is ok - it will be fixed by the reconstructor later on
storage_policy._POLICIES[0].policy_type = 'erasure_coding'
self.assertEqual(
0, relinker.cleanup(self.testdir, self.devices, True, self.logger))
self.assertEqual(self.logger.get_lines_for_level('warning'), [])
def test_cleanup_quarantined(self):
self._common_test_cleanup()
# Pretend the object in the new place got corrupted
with open(self.expected_file, "wb") as obj:
obj.write('trash')
self.assertEqual(
1, relinker.cleanup(self.testdir, self.devices, True, self.logger))
self.assertIn('failed audit and was quarantined',
self.logger.get_lines_for_level('warning')[0])