gitops/patroni
1
0
Fork 0
mirror of https://github.com/outbackdingo/patroni.git synced 2026-08-25 14:53:37 +00:00
Code Issues Packages Projects Releases Wiki Activity

Archive possibly missing WALs before rewind (#2384)

Browse Source 
There is currently a risk to lose some WAL segments entirely in case
archive_mode was set to 'on' before a promotion and there are some WALs
with .ready files on the former leader we are trying to rewind. It happens
because of the pg_rewind's modus operandi: it simply syncs the content of
pg_wal directory of the old leader with the new leader's one. Including
deletion of all WALs that are not present on the current leader, regardless
their archive status on the former one. Thus, in case the new leader has
already recycled such files, we just remove them entirely.

In case archive_mode was set to 'always' and the .ready WALs are acrually
present in archive, it is for end user who writes the archive_command to
avoid overwritting and to properly test it.

Co-authored-by: Alexander Kukushkin <[email protected]>
This commit is contained in:
Polina Bungina
2022-08-17 09:54:30 +02:00
committed by GitHub
co-authored by Alexander Kukushkin
parent b6f057850a
commit ae0ede6944
2 changed files with 113 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test_rewind.py
+56
View File
@@ -218,6 +218,62 @@ class TestRewind(BaseTestPostgresql):
self.r.cleanup_archive_status()
self.r.cleanup_archive_status()
@patch('os.path.isfile', Mock(return_value=True))
@patch('shutil.move', Mock(side_effect=OSError))
@patch('patroni.postgresql.rewind.logger.info')
def test_archive_ready_wals(self, mock_logger_info):
with patch('os.listdir', Mock(side_effect=OSError)), \
patch.object(Postgresql, 'get_guc_value', Mock(side_effect=['on', 'command %f'])):
self.r._archive_ready_wals()
mock_logger_info.assert_not_called()
# each assert_not_called() calls get_guc_value('archive_mode') + get_guc_value('archive_command')
get_guc_value_res = [
'', 'command %f',
'on', '',
]
with patch.object(Postgresql, 'get_guc_value', Mock(side_effect=get_guc_value_res)):
for _ in range(len(get_guc_value_res)//2):
self.r._archive_ready_wals()
mock_logger_info.assert_not_called()
with patch('os.listdir', Mock(return_value=['000000000000000000000000.ready'])):
# successful archive_command call
with patch.object(CancellableSubprocess, 'call', Mock(return_value=0)):
get_guc_value_res = [
'on', 'command %f',
'always', 'command %f',
]
with patch.object(Postgresql, 'get_guc_value', Mock(side_effect=get_guc_value_res)):
for _ in range(len(get_guc_value_res)//2):
self.r._archive_ready_wals()
mock_logger_info.assert_called_once()
self.assertEqual(('Trying to archive %s: %s',
'000000000000000000000000', 'command 000000000000000000000000'),
mock_logger_info.call_args[0])
mock_logger_info.reset_mock()
# failed archive_command call
with patch.object(CancellableSubprocess, 'call', Mock(return_value=1)):
with patch.object(Postgresql, 'get_guc_value', Mock(side_effect=['on', 'command %f'])):
self.r._archive_ready_wals()
self.assertEqual(('Trying to archive %s: %s',
'000000000000000000000000', 'command 000000000000000000000000'),
mock_logger_info.call_args_list[0][0])
self.assertEqual(('Failed to archive WAL segment %s', '000000000000000000000000'),
mock_logger_info.call_args_list[1][0])
mock_logger_info.reset_mock()
wal_files_to_skip = [
'000000000000000000000000.done',
'000000000000000000000001.partial.done',
'002.ready',
'U00000000000000000000001.ready',
]
with patch('os.listdir', Mock(return_value=wal_files_to_skip)):
self.r._archive_ready_wals()
mock_logger_info.assert_not_called()
@patch('os.unlink', Mock())
@patch('os.listdir', Mock(return_value=[]))
@patch('os.path.isfile', Mock(return_value=True))