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

Fix pg_rewind behavior with Postgres v16+ (#2944)

Browse Source 
The error message format was changed in
https://github.com/postgres/postgres/commit/4ac30ba4f29d4b586b131404b0d514f16501272a, what caused `pg_rewind` being called by Patroni even when it was not necessary.
This commit is contained in:
Alexander Kukushkin
2023-11-10 09:23:45 +01:00
committed by GitHub
parent 1b96ae9c0a
commit 7370f70f13
2 changed files with 40 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
patroni/postgresql/rewind.py
+25 -6
View File
@@ -101,12 +101,26 @@ class Rewind(object):
return 'not accessible or not healty'
def _get_checkpoint_end(self, timeline: int, lsn: int) -> int:
"""The checkpoint record size in WAL depends on postgres major version and platform (memory alignment).
Hence, the only reliable way to figure out where it ends, read the record from file with the help of pg_waldump
and parse the output. We are trying to read two records, and expect that it will fail to read the second one:
`pg_waldump: fatal: error in WAL record at 0/182E220: invalid record length at 0/182E298: wanted 24, got 0`
The error message contains information about LSN of the next record, which is exactly where checkpoint ends."""
"""Get the end of checkpoint record from WAL.
.. note::
The checkpoint record size in WAL depends on postgres major version and platform (memory alignment).
Hence, the only reliable way to figure out where it ends, is to read the record from file with the
help of ``pg_waldump`` and parse the output.
We are trying to read two records, and expect that it will fail to read the second record with message:
fatal: error in WAL record at 0/182E220: invalid record length at 0/182E298: wanted 24, got 0; or
fatal: error in WAL record at 0/182E220: invalid record length at 0/182E298: expected at least 24, got 0
The error message contains information about LSN of the next record, which is exactly where checkpoint ends.
:param timeline: the checkpoint *timeline* from ``pg_controldata``.
:param lsn: the checkpoint *location* as :class:`int` from ``pg_controldata``.
:returns: the end of checkpoint record as :class:`int` or ``0`` if failed to parse ``pg_waldump`` output.
"""
lsn8 = format_lsn(lsn, True)
lsn_str = format_lsn(lsn)
out, err = self._postgresql.waldump(timeline, lsn_str, 2)
@@ -117,7 +131,12 @@ class Rewind(object):
if len(out) == 1 and len(err) == 1 and ', lsn: {0}, prev '.format(lsn8) in out[0] and pattern in err[0]:
i = err[0].find(pattern) + len(pattern)
j = err[0].find(": wanted ", i)
# Message format depends on the major version:
# * expected at least -- starting from v16
# * wanted -- before v16
# We will simply check all possible combinations.
for pattern in (': expected at least ', ': wanted '):
j = err[0].find(pattern, i)
if j > -1:
try:
return parse_lsn(err[0][i:j])
tests/test_rewind.py
+10
View File
@@ -180,6 +180,16 @@ class TestRewind(BaseTestPostgresql):
self.r.trigger_check_diverged_lsn()
mock_get_local_timeline_lsn.return_value = (False, 2, 67197377)
self.assertTrue(self.r.rewind_or_reinitialize_needed_and_possible(self.leader))
mock_popen.return_value.communicate.return_value = (
b'0, lsn: 0/040159C1, prev 0/\n',
b'pg_waldump: fatal: error in WAL record at 0/40159C1: invalid record '
b'length at 0/402DD98: expected at least 24, got 0\n'
)
self.r.reset_state()
self.r.trigger_check_diverged_lsn()
self.assertFalse(self.r.rewind_or_reinitialize_needed_and_possible(self.leader))
self.r.reset_state()
self.r.trigger_check_diverged_lsn()
mock_popen.side_effect = Exception