You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@cassandra.apache.org by "Josh McKenzie (Jira)" <ji...@apache.org> on 2022/01/26 18:07:00 UTC
[jira] [Created] (CASSANDRA-17305) Test Failure: dtest-upgrade.upgrade_tests.upgrade_through_versions_test.TestProtoV3Upgrade_AllVersions_RandomPartitioner_EndsAt_3_11_X_HEAD.test_parallel_upgrade
Josh McKenzie created CASSANDRA-17305:
-----------------------------------------
Summary: Test Failure: dtest-upgrade.upgrade_tests.upgrade_through_versions_test.TestProtoV3Upgrade_AllVersions_RandomPartitioner_EndsAt_3_11_X_HEAD.test_parallel_upgrade
Key: CASSANDRA-17305
URL: https://issues.apache.org/jira/browse/CASSANDRA-17305
Project: Cassandra
Issue Type: Bug
Components: Test/dtest/python
Reporter: Josh McKenzie
Failed 2 times in the last 29 runs. Flakiness: 7%, Stability: 93%
Error Message
Failed: Timeout >900.0s
{code}
Stacktrace
self = <upgrade_tests.upgrade_through_versions_test.TestProtoV3Upgrade_AllVersions_RandomPartitioner_EndsAt_3_11_X_HEAD object at 0x7f19858d59d0>
def test_parallel_upgrade(self):
"""
Test upgrading cluster all at once (requires cluster downtime).
"""
> self.upgrade_scenario()
upgrade_tests/upgrade_through_versions_test.py:313:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
upgrade_tests/upgrade_through_versions_test.py:435: in upgrade_scenario
cluster.stop()
../venv/lib/python3.8/site-packages/ccmlib/cluster.py:576: in stop
if not node.stop(wait=wait, signal_event=signal_event, **kwargs):
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
self = <ccmlib.node.Node object at 0x7f1985bba040>, wait = True
wait_other_notice = False, signal_event = <Signals.SIGTERM: 15>, kwargs = {}
still_running = True, wait_time_sec = 16, i = 4
def stop(self, wait=True, wait_other_notice=False, signal_event=signal.SIGTERM, **kwargs):
"""
Stop the node.
- wait: if True (the default), wait for the Cassandra process to be
really dead. Otherwise return after having sent the kill signal.
- wait_other_notice: return only when the other live nodes of the
cluster have marked this node has dead.
- signal_event: Signal event to send to Cassandra; default is to
let Cassandra clean up and shut down properly (SIGTERM [15])
- Optional:
+ gently: Let Cassandra clean up and shut down properly; unless
false perform a 'kill -9' which shuts down faster.
"""
if self.is_running():
if wait_other_notice:
marks = [(node, node.mark_log()) for node in list(self.cluster.nodes.values()) if node.is_live() and node is not self]
if common.is_win():
# Just taskkill the instance, don't bother trying to shut it down gracefully.
# Node recovery should prevent data loss from hard shutdown.
# We have recurring issues with nodes not stopping / releasing files in the CI
# environment so it makes more sense just to murder it hard since there's
# really little downside.
# We want the node to flush its data before shutdown as some tests rely on small writes being present.
# The default Periodic sync at 10 ms may not have flushed data yet, causing tests to fail.
# This is not a hard requirement, however, so we swallow any exceptions this may throw and kill anyway.
if signal_event is signal.SIGTERM:
try:
self.flush()
except:
common.warning("Failed to flush node: {0} on shutdown.".format(self.name))
pass
os.system("taskkill /F /PID " + str(self.pid))
if self._find_pid_on_windows():
common.warning("Failed to terminate node: {0} with pid: {1}".format(self.name, self.pid))
else:
# Determine if the signal event should be updated to keep API compatibility
if 'gently' in kwargs and kwargs['gently'] is False:
signal_event = signal.SIGKILL
os.kill(self.pid, signal_event)
if wait_other_notice:
for node, mark in marks:
node.watch_log_for_death(self, from_mark=mark)
else:
time.sleep(.1)
still_running = self.is_running()
if still_running and wait:
wait_time_sec = 1
for i in xrange(0, 7):
# we'll double the wait time each try and cassandra should
# not take more than 1 minute to shutdown
> time.sleep(wait_time_sec)
E Failed: Timeout >900.0s
../venv/lib/python3.8/site-packages/ccmlib/node.py:970: Failed
{code}
--
This message was sent by Atlassian Jira
(v8.20.1#820001)
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@cassandra.apache.org
For additional commands, e-mail: commits-help@cassandra.apache.org