github/krkn
1
0
Fork 0
mirror of https://github.com/krkn-chaos/krkn.git synced 2026-08-25 09:27:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: improve logging clarity , reduce noise, fix log levels, and reword misleading messages (#1562)

Browse Source 
* fix: improve logging clarity — reduce noise, fix log levels, and reword misleading messages

- Move per-directory rollback WARNING to DEBUG; add single INFO summary
- Change "No rollback context directories found" from WARNING to DEBUG
- Change "Skip cleanup/execution" from WARNING to DEBUG
- Fix misleading Cerberus "still failing" message: early-return when
  disabled, use correct log levels, remove inaccurate wording
- Change "No error logs collected" from INFO to DEBUG
- Reword "Detected distribution" to "Detected cluster platform"
- Reword OCP metadata collection log for clarity

Closes #1559

Signed-off-by: ddjain <darjain@redhat.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Signed-off-by: ddjain <darjain@redhat.com>
Co-authored-by: Cursor <cursoragent@cursor.com>

* fix: address review comments — fix tests, reword log messages

- Add cerberus_enabled = True to 4 publish_kraken_status tests broken
  by early-return guard
- Add new test for cerberus_disabled early-return path
- Reword rollback skip summary to neutral wording
- Remove capitalize() from platform detection log

Signed-off-by: ddjain <darjain@redhat.com>
Co-authored-by: Cursor <cursoragent@cursor.com>

---------

Signed-off-by: ddjain <darjain@redhat.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Darshan Jain
2026-08-14 09:45:55 -04:00
committed by GitHub
co-authored by Cursor
parent 7658a6b871
commit 51f41e3595
5 changed files with 38 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
krkn/cerberus/setup.py
+13 -13
View File
@@ -91,34 +91,34 @@ def get_status(start_time, end_time):
return cerberus_status
def publish_kraken_status( start_time, end_time):
def publish_kraken_status(start_time, end_time):
"""
Publish kraken status to cerberus
Check cerberus health status after a scenario run and act on exit_on_failure.
"""
if not cerberus_enabled:
return
cerberus_status = get_status(start_time, end_time)
if not cerberus_status:
if exit_on_failure:
logging.info(
"Cerberus status is not healthy and post action scenarios "
"are still failing, exiting kraken run"
logging.error(
"Cerberus reports cluster is NOT healthy, exiting kraken run"
)
sys.exit(1)
else:
logging.info(
"Cerberus status is not healthy and post action scenarios "
"are still failing"
logging.warning(
"Cerberus reports cluster is NOT healthy"
)
else:
if exit_on_failure:
logging.info(
"Cerberus status is healthy but post action scenarios "
"are still failing, exiting kraken run"
logging.warning(
"Cerberus reports cluster is healthy, "
"but exit_on_failure is set — exiting kraken run"
)
sys.exit(1)
else:
logging.info(
"Cerberus status is healthy but post action scenarios "
"are still failing"
"Cerberus reports cluster is healthy"
)
krkn/rollback/config.py
+7 -2
View File
@@ -221,14 +221,19 @@ class RollbackConfig(metaclass=SingletonMeta):
return []
rollback_context_directories = []
skipped_count = 0
for dir in os.listdir(cls().versions_directory):
if cls.is_rollback_context_directory_format(dir, run_uuid):
rollback_context_directories.append(dir)
else:
logger.warning(f"Directory {dir} does not match expected pattern of <timestamp>-<run_uuid>")
skipped_count += 1
logger.debug(f"Directory {dir} does not match expected pattern of <timestamp>-<run_uuid>")
if skipped_count > 0:
logger.info(f"Skipped {skipped_count} non-matching entries in rollback versions directory")
if not rollback_context_directories:
logger.warning(f"No rollback context directories found for run UUID {run_uuid}")
logger.debug(f"No rollback context directories found for run UUID {run_uuid}")
return []
krkn/rollback/handler.py
+2 -2
View File
@@ -155,7 +155,7 @@ def execute_rollback_version_files(
# Get the rollback versions directory
version_files = RollbackConfig.search_rollback_version_files(run_uuid, scenario_type)
if not version_files:
logger.warning(f"Skip execution for run_uuid={run_uuid or '*'}, scenario_type={scenario_type or '*'}")
logger.debug(f"Skip execution for run_uuid={run_uuid or '*'}, scenario_type={scenario_type or '*'}")
return
# Execute all version files in the directory
@@ -206,7 +206,7 @@ def cleanup_rollback_version_files(run_uuid: str, scenario_type: str):
# Get the rollback versions directory
version_files = RollbackConfig.search_rollback_version_files(run_uuid, scenario_type)
if not version_files:
logger.warning(f"Skip cleanup for run_uuid={run_uuid}, scenario_type={scenario_type or '*'}")
logger.debug(f"Skip cleanup for run_uuid={run_uuid}, scenario_type={scenario_type or '*'}")
return
# Remove all version files in the directory
run_kraken.py
+3 -3
View File
@@ -268,7 +268,7 @@ def main(options, command: Optional[str], out: Optional[dict] = None) -> int:
distribution = "kubernetes"
if ocpcli.is_openshift():
distribution = "openshift"
logging.info("Detected distribution %s" % (distribution))
logging.info("Detected cluster platform: %s" % (distribution))
# find node kraken might be running on
kubecli.find_kraken_node()
@@ -599,7 +599,7 @@ def main(options, command: Optional[str], out: Optional[dict] = None) -> int:
# through OCP specific APIs
if distribution == "openshift":
logging.info(
"collecting OCP cluster metadata, this may take few minutes...."
"Collecting OCP cluster metadata (nodes, resources, network plugins)..."
)
telemetry_ocp.collect_cluster_metadata(chaos_telemetry)
else:
@@ -611,7 +611,7 @@ def main(options, command: Optional[str], out: Optional[dict] = None) -> int:
logging.info(f"Collected {len(error_logs)} error logs for telemetry")
chaos_telemetry.error_logs = error_logs
else:
logging.info("No error logs collected during chaos run")
logging.debug("No error logs collected during chaos run")
chaos_telemetry.error_logs = []
if resiliency_obj and hist_window is None:
try:
tests/test_cerberus_setup.py
+13
View File
@@ -160,9 +160,19 @@ class TestCerberusSetup(unittest.TestCase):
self.assertEqual(cm.exception.code, 1)
@patch('krkn.cerberus.setup.get_status')
def test_publish_kraken_status_cerberus_disabled_skips(self, mock_get_status):
"""Test publish_kraken_status returns immediately when cerberus is disabled"""
cerberus_setup.cerberus_enabled = False
cerberus_setup.publish_kraken_status(0, 100)
mock_get_status.assert_not_called()
@patch('krkn.cerberus.setup.get_status')
def test_publish_kraken_status_healthy_exit_on_failure_false(self, mock_get_status):
"""Test publish_kraken_status when cluster is healthy and exit_on_failure is False"""
cerberus_setup.cerberus_enabled = True
cerberus_setup.exit_on_failure = False
mock_get_status.return_value = True
@@ -173,6 +183,7 @@ class TestCerberusSetup(unittest.TestCase):
@patch('krkn.cerberus.setup.get_status')
def test_publish_kraken_status_healthy_exit_on_failure_true(self, mock_get_status):
"""Test publish_kraken_status when cluster is healthy and exit_on_failure is True"""
cerberus_setup.cerberus_enabled = True
cerberus_setup.exit_on_failure = True
mock_get_status.return_value = True
@@ -185,6 +196,7 @@ class TestCerberusSetup(unittest.TestCase):
@patch('krkn.cerberus.setup.get_status')
def test_publish_kraken_status_unhealthy_exit_on_failure_false(self, mock_get_status):
"""Test publish_kraken_status when cluster is unhealthy and exit_on_failure is False"""
cerberus_setup.cerberus_enabled = True
cerberus_setup.exit_on_failure = False
mock_get_status.return_value = False
@@ -195,6 +207,7 @@ class TestCerberusSetup(unittest.TestCase):
@patch('krkn.cerberus.setup.get_status')
def test_publish_kraken_status_unhealthy_exit_on_failure_true(self, mock_get_status):
"""Test publish_kraken_status when cluster is unhealthy and exit_on_failure is True"""
cerberus_setup.cerberus_enabled = True
cerberus_setup.exit_on_failure = True
mock_get_status.return_value = False