def test_process_spark_submit_log_k8s(self):
# Given
hook = SparkSubmitHook(conn_id='spark_k8s_cluster')
log_lines = [
'INFO LoggingPodStatusWatcherImpl:54 - State changed, new state:'
+ 'pod name: spark-pi-edf2ace37be7353a958b38733a12f8e6-driver' +
'namespace: default' +
'labels: spark-app-selector -> spark-465b868ada474bda82ccb84ab2747fcd,'
+ 'spark-role -> driver' +
'pod uid: ba9c61f6-205f-11e8-b65f-d48564c88e42' +
'creation time: 2018-03-05T10:26:55Z' +
'service account name: spark' +
'volumes: spark-init-properties, download-jars-volume,' +
'download-files-volume, spark-token-2vmlm' + 'node name: N/A' +
'start time: N/A' + 'container images: N/A' + 'phase: Pending' +
'status: []' +
'2018-03-05 11:26:56 INFO LoggingPodStatusWatcherImpl:54 - State changed,'
+ ' new state:' +
'pod name: spark-pi-edf2ace37be7353a958b38733a12f8e6-driver' +
'namespace: default' + 'Exit code: 999'
]
# When
hook._process_spark_submit_log(log_lines)
# Then
assert hook._kubernetes_driver_pod == 'spark-pi-edf2ace37be7353a958b38733a12f8e6-driver'
assert hook._spark_exit_code == 999
def test_yarn_process_on_kill(self, mock_popen):
# Given
mock_popen.return_value.stdout = io.StringIO('stdout')
mock_popen.return_value.stderr = io.StringIO('stderr')
mock_popen.return_value.poll.return_value = None
mock_popen.return_value.wait.return_value = 0
log_lines = [
'SPARK_MAJOR_VERSION is set to 2, using Spark2',
'WARN NativeCodeLoader: Unable to load native-hadoop library for your '
+ 'platform... using builtin-java classes where applicable',
'WARN DomainSocketFactory: The short-circuit local reads feature cannot '
+ 'be used because libhadoop cannot be loaded.',
'INFO Client: Requesting a new application from cluster with 10 ' +
'NodeManagerapplication_1486558679801_1820s',
'INFO Client: Submitting application application_1486558679801_1820 '
+ 'to ResourceManager'
]
hook = SparkSubmitHook(conn_id='spark_yarn_cluster')
hook._process_spark_submit_log(log_lines)
hook.submit()
# When
hook.on_kill()
# Then
self.assertIn(
call([
'yarn', 'application', '-kill',
'application_1486558679801_1820'
],
stderr=-1,
stdout=-1), mock_popen.mock_calls)
def test_process_spark_submit_log_k8s_spark_3(self):
# Given
hook = SparkSubmitHook(conn_id='spark_k8s_cluster')
log_lines = ['exit code: 999']
# When
hook._process_spark_submit_log(log_lines)
# Then
assert hook._spark_exit_code == 999
def test_yarn_process_on_kill(self, mock_popen, mock_renew_from_kt):
# Given
mock_popen.return_value.stdout = io.StringIO('stdout')
mock_popen.return_value.stderr = io.StringIO('stderr')
mock_popen.return_value.poll.return_value = None
mock_popen.return_value.wait.return_value = 0
log_lines = [
'SPARK_MAJOR_VERSION is set to 2, using Spark2',
'WARN NativeCodeLoader: Unable to load native-hadoop library for your '
+ 'platform... using builtin-java classes where applicable',
'WARN DomainSocketFactory: The short-circuit local reads feature cannot '
+ 'be used because libhadoop cannot be loaded.',
'INFO Client: Requesting a new application from cluster with 10 ' +
'NodeManagerapplication_1486558679801_1820s',
'INFO Client: Submitting application application_1486558679801_1820 '
+ 'to ResourceManager',
]
env = {"PATH": "hadoop/bin"}
hook = SparkSubmitHook(conn_id='spark_yarn_cluster', env_vars=env)
hook._process_spark_submit_log(log_lines)
hook.submit()
# When
hook.on_kill()
# Then
assert (call(
['yarn', 'application', '-kill', 'application_1486558679801_1820'],
env={
**os.environ,
**env
},
stderr=-1,
stdout=-1,
) in mock_popen.mock_calls)
# resetting the mock to test kill with keytab & principal
mock_popen.reset_mock()
# Given
hook = SparkSubmitHook(conn_id='spark_yarn_cluster',
keytab='privileged_user.keytab',
principal='user/[email protected]')
hook._process_spark_submit_log(log_lines)
hook.submit()
# When
hook.on_kill()
# Then
expected_env = os.environ.copy()
expected_env["KRB5CCNAME"] = '/tmp/airflow_krb5_ccache'
assert (call(
['yarn', 'application', '-kill', 'application_1486558679801_1820'],
env=expected_env,
stderr=-1,
stdout=-1,
) in mock_popen.mock_calls)
def test_process_spark_submit_log_standalone_cluster(self):
# Given
hook = SparkSubmitHook(conn_id='spark_standalone_cluster')
log_lines = [
'Running Spark using the REST application submission protocol.',
'17/11/28 11:14:15 INFO RestSubmissionClient: Submitting a request '
'to launch an application in spark://spark-standalone-master:6066',
'17/11/28 11:14:15 INFO RestSubmissionClient: Submission successfully ' +
'created as driver-20171128111415-0001. Polling submission state...'
]
# When
hook._process_spark_submit_log(log_lines)
# Then
self.assertEqual(hook._driver_id, 'driver-20171128111415-0001')
def test_process_spark_submit_log_yarn(self):
# Given
hook = SparkSubmitHook(conn_id='spark_yarn_cluster')
log_lines = [
'SPARK_MAJOR_VERSION is set to 2, using Spark2',
'WARN NativeCodeLoader: Unable to load native-hadoop library for your '
+ 'platform... using builtin-java classes where applicable',
'WARN DomainSocketFactory: The short-circuit local reads feature cannot '
'be used because libhadoop cannot be loaded.',
'INFO Client: Requesting a new application from cluster with 10 NodeManagers',
'INFO Client: Submitting application application_1486558679801_1820 '
+ 'to ResourceManager',
]
# When
hook._process_spark_submit_log(log_lines)
# Then
assert hook._yarn_application_id == 'application_1486558679801_1820'
def test_k8s_process_on_kill(self, mock_popen, mock_client_method):
# Given
mock_popen.return_value.stdout = io.StringIO('stdout')
mock_popen.return_value.stderr = io.StringIO('stderr')
mock_popen.return_value.poll.return_value = None
mock_popen.return_value.wait.return_value = 0
client = mock_client_method.return_value
hook = SparkSubmitHook(conn_id='spark_k8s_cluster')
log_lines = [
'INFO LoggingPodStatusWatcherImpl:54 - State changed, new state:' +
'pod name: spark-pi-edf2ace37be7353a958b38733a12f8e6-driver' +
'namespace: default' +
'labels: spark-app-selector -> spark-465b868ada474bda82ccb84ab2747fcd,' +
'spark-role -> driver' +
'pod uid: ba9c61f6-205f-11e8-b65f-d48564c88e42' +
'creation time: 2018-03-05T10:26:55Z' +
'service account name: spark' +
'volumes: spark-init-properties, download-jars-volume,' +
'download-files-volume, spark-token-2vmlm' +
'node name: N/A' +
'start time: N/A' +
'container images: N/A' +
'phase: Pending' +
'status: []' +
'2018-03-05 11:26:56 INFO LoggingPodStatusWatcherImpl:54 - State changed,' +
' new state:' +
'pod name: spark-pi-edf2ace37be7353a958b38733a12f8e6-driver' +
'namespace: default' +
'Exit code: 0'
]
hook._process_spark_submit_log(log_lines)
hook.submit()
# When
hook.on_kill()
# Then
import kubernetes
kwargs = {'pretty': True, 'body': kubernetes.client.V1DeleteOptions()}
client.delete_namespaced_pod.assert_called_once_with(
'spark-pi-edf2ace37be7353a958b38733a12f8e6-driver',
'mynamespace', **kwargs)
def test_standalone_cluster_process_on_kill(self):
# Given
log_lines = [
'Running Spark using the REST application submission protocol.',
'17/11/28 11:14:15 INFO RestSubmissionClient: Submitting a request ' +
'to launch an application in spark://spark-standalone-master:6066',
'17/11/28 11:14:15 INFO RestSubmissionClient: Submission successfully ' +
'created as driver-20171128111415-0001. Polling submission state...'
]
hook = SparkSubmitHook(conn_id='spark_standalone_cluster')
hook._process_spark_submit_log(log_lines)
# When
kill_cmd = hook._build_spark_driver_kill_command()
# Then
self.assertEqual(kill_cmd[0], '/path/to/spark_home/bin/spark-submit')
self.assertEqual(kill_cmd[1], '--master')
self.assertEqual(kill_cmd[2], 'spark://spark-standalone-master:6066')
self.assertEqual(kill_cmd[3], '--kill')
self.assertEqual(kill_cmd[4], 'driver-20171128111415-0001')
