[
https://issues.apache.org/jira/browse/KAFKA-16578?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17838609#comment-17838609
]
Sagar Rao edited comment on KAFKA-16578 at 4/18/24 3:02 PM:
------------------------------------------------------------
[~kirktrue], I am running the the system tests for connect using the test suite
on my local, and this exact test *test_exactly_once_source* fails regularly for
me for a different config.
{code:java}
--------------------------------------------------------------------------------
test_id:
kafkatest.tests.connect.connect_distributed_test.ConnectDistributedTest.test_exactly_once_source.clean=False.connect_protocol=sessioned.metadata_quorum=ISOLATED_KRAFT.use_new_coordinator=True.group_protocol=consumer
status: FAIL
run time: 7 minutes 59.232 seconds
InsufficientResourcesError('linux nodes requested: 1. linux nodes
available: 0')
Traceback (most recent call last):
File
"/usr/local/lib/python3.9/dist-packages/ducktape/tests/runner_client.py", line
186, in _do_run
data = self.run_test()
File
"/usr/local/lib/python3.9/dist-packages/ducktape/tests/runner_client.py", line
246, in run_test
return self.test_context.function(self.test)
File "/usr/local/lib/python3.9/dist-packages/ducktape/mark/_mark.py", line
433, in wrapper
return functools.partial(f, *args, **kwargs)(*w_args, **w_kwargs)
File
"/opt/kafka-dev/tests/kafkatest/tests/connect/connect_distributed_test.py",
line 929, in test_exactly_once_source
consumer_validator = ConsoleConsumer(self.test_context, 1, self.kafka,
self.source.topic, consumer_timeout_ms=1000, print_key=True,
consumer_properties=consumer_properties)
File "/opt/kafka-dev/tests/kafkatest/services/console_consumer.py", line 97,
in __init__
BackgroundThreadService.__init__(self, context, num_nodes)
File
"/usr/local/lib/python3.9/dist-packages/ducktape/services/background_thread.py",
line 26, in __init__
super(BackgroundThreadService, self).__init__(context, num_nodes,
cluster_spec, *args, **kwargs)
File "/usr/local/lib/python3.9/dist-packages/ducktape/services/service.py",
line 107, in __init__
self.allocate_nodes()
File "/usr/local/lib/python3.9/dist-packages/ducktape/services/service.py",
line 217, in allocate_nodes
self.nodes = self.cluster.alloc(self.cluster_spec)
File "/usr/local/lib/python3.9/dist-packages/ducktape/cluster/cluster.py",
line 54, in alloc
allocated = self.do_alloc(cluster_spec)
File
"/usr/local/lib/python3.9/dist-packages/ducktape/cluster/finite_subcluster.py",
line 37, in do_alloc
good_nodes, bad_nodes = self._available_nodes.remove_spec(cluster_spec)
File
"/usr/local/lib/python3.9/dist-packages/ducktape/cluster/node_container.py",
line 131, in remove_spec
raise InsufficientResourcesError(err)
ducktape.cluster.node_container.InsufficientResourcesError: linux nodes
requested: 1. linux nodes available: 0
{code}
-If you want, I can revert the change as part of my PR. It should be ready for
review by today or tomorrow.-
I updated the PR [https://github.com/apache/kafka/pull/15594] with the changes
rolled back for the test in question. I hope it's ok.
was (Author: sagarrao):
[~kirktrue], I am running the the system tests for connect using the test suite
on my local, and this exact test *test_exactly_once_source* fails regularly for
me for a different config.
{code:java}
--------------------------------------------------------------------------------
test_id:
kafkatest.tests.connect.connect_distributed_test.ConnectDistributedTest.test_exactly_once_source.clean=False.connect_protocol=sessioned.metadata_quorum=ISOLATED_KRAFT.use_new_coordinator=True.group_protocol=consumer
status: FAIL
run time: 7 minutes 59.232 seconds
InsufficientResourcesError('linux nodes requested: 1. linux nodes
available: 0')
Traceback (most recent call last):
File
"/usr/local/lib/python3.9/dist-packages/ducktape/tests/runner_client.py", line
186, in _do_run
data = self.run_test()
File
"/usr/local/lib/python3.9/dist-packages/ducktape/tests/runner_client.py", line
246, in run_test
return self.test_context.function(self.test)
File "/usr/local/lib/python3.9/dist-packages/ducktape/mark/_mark.py", line
433, in wrapper
return functools.partial(f, *args, **kwargs)(*w_args, **w_kwargs)
File
"/opt/kafka-dev/tests/kafkatest/tests/connect/connect_distributed_test.py",
line 929, in test_exactly_once_source
consumer_validator = ConsoleConsumer(self.test_context, 1, self.kafka,
self.source.topic, consumer_timeout_ms=1000, print_key=True,
consumer_properties=consumer_properties)
File "/opt/kafka-dev/tests/kafkatest/services/console_consumer.py", line 97,
in __init__
BackgroundThreadService.__init__(self, context, num_nodes)
File
"/usr/local/lib/python3.9/dist-packages/ducktape/services/background_thread.py",
line 26, in __init__
super(BackgroundThreadService, self).__init__(context, num_nodes,
cluster_spec, *args, **kwargs)
File "/usr/local/lib/python3.9/dist-packages/ducktape/services/service.py",
line 107, in __init__
self.allocate_nodes()
File "/usr/local/lib/python3.9/dist-packages/ducktape/services/service.py",
line 217, in allocate_nodes
self.nodes = self.cluster.alloc(self.cluster_spec)
File "/usr/local/lib/python3.9/dist-packages/ducktape/cluster/cluster.py",
line 54, in alloc
allocated = self.do_alloc(cluster_spec)
File
"/usr/local/lib/python3.9/dist-packages/ducktape/cluster/finite_subcluster.py",
line 37, in do_alloc
good_nodes, bad_nodes = self._available_nodes.remove_spec(cluster_spec)
File
"/usr/local/lib/python3.9/dist-packages/ducktape/cluster/node_container.py",
line 131, in remove_spec
raise InsufficientResourcesError(err)
ducktape.cluster.node_container.InsufficientResourcesError: linux nodes
requested: 1. linux nodes available: 0
{code}
If you want, I can revert the change as part of my PR. It should be ready for
review by today or tomorrow.
> Revert changes to connect_distributed_test.py for the new async Consumer
> ------------------------------------------------------------------------
>
> Key: KAFKA-16578
> URL: https://issues.apache.org/jira/browse/KAFKA-16578
> Project: Kafka
> Issue Type: Task
> Components: clients, consumer, system tests
> Affects Versions: 3.8.0
> Reporter: Kirk True
> Assignee: Kirk True
> Priority: Critical
> Labels: kip-848-client-support, system-tests
> Fix For: 3.8.0
>
>
> To test the new, asynchronous Kafka {{Consumer}} implementation, we migrated
> a slew of system tests to run both the "old" and "new" implementations.
> KAFKA-16272 updated the system tests in {{connect_distributed_test.py}} so it
> could test the new consumer with Connect. However, we are not supporting
> Connect with the new consumer in 3.8.0. Unsurprisingly, when we run the
> Connect system tests with the new {{AsyncKafkaConsumer}}, we get errors like
> the following:
> {code}
> test_id:
> kafkatest.tests.connect.connect_distributed_test.ConnectDistributedTest.test_exactly_once_source.clean=False.connect_protocol=eager.metadata_quorum=ISOLATED_KRAFT.use_new_coordinator=True.group_protocol=consumer
> status: FAIL
> run time: 6 minutes 3.899 seconds
> InsufficientResourcesError('Not enough nodes available to allocate. linux
> nodes requested: 1. linux nodes available: 0')
> Traceback (most recent call last):
> File
> "/home/jenkins/workspace/system-test-kafka-branch-builder/kafka/venv/lib/python3.7/site-packages/ducktape/tests/runner_client.py",
> line 184, in _do_run
> data = self.run_test()
> File
> "/home/jenkins/workspace/system-test-kafka-branch-builder/kafka/venv/lib/python3.7/site-packages/ducktape/tests/runner_client.py",
> line 262, in run_test
> return self.test_context.function(self.test)
> File
> "/home/jenkins/workspace/system-test-kafka-branch-builder/kafka/venv/lib/python3.7/site-packages/ducktape/mark/_mark.py",
> line 433, in wrapper
> return functools.partial(f, *args, **kwargs)(*w_args, **w_kwargs)
> File
> "/home/jenkins/workspace/system-test-kafka-branch-builder/kafka/tests/kafkatest/tests/connect/connect_distributed_test.py",
> line 919, in test_exactly_once_source
> consumer_validator = ConsoleConsumer(self.test_context, 1, self.kafka,
> self.source.topic, consumer_timeout_ms=1000, print_key=True)
> File
> "/home/jenkins/workspace/system-test-kafka-branch-builder/kafka/tests/kafkatest/services/console_consumer.py",
> line 97, in __init__
> BackgroundThreadService.__init__(self, context, num_nodes)
> File
> "/home/jenkins/workspace/system-test-kafka-branch-builder/kafka/venv/lib/python3.7/site-packages/ducktape/services/background_thread.py",
> line 26, in __init__
> super(BackgroundThreadService, self).__init__(context, num_nodes,
> cluster_spec, *args, **kwargs)
> File
> "/home/jenkins/workspace/system-test-kafka-branch-builder/kafka/venv/lib/python3.7/site-packages/ducktape/services/service.py",
> line 107, in __init__
> self.allocate_nodes()
> File
> "/home/jenkins/workspace/system-test-kafka-branch-builder/kafka/venv/lib/python3.7/site-packages/ducktape/services/service.py",
> line 217, in allocate_nodes
> self.nodes = self.cluster.alloc(self.cluster_spec)
> File
> "/home/jenkins/workspace/system-test-kafka-branch-builder/kafka/venv/lib/python3.7/site-packages/ducktape/cluster/cluster.py",
> line 54, in alloc
> allocated = self.do_alloc(cluster_spec)
> File
> "/home/jenkins/workspace/system-test-kafka-branch-builder/kafka/venv/lib/python3.7/site-packages/ducktape/cluster/finite_subcluster.py",
> line 31, in do_alloc
> allocated = self._available_nodes.remove_spec(cluster_spec)
> File
> "/home/jenkins/workspace/system-test-kafka-branch-builder/kafka/venv/lib/python3.7/site-packages/ducktape/cluster/node_container.py",
> line 117, in remove_spec
> raise InsufficientResourcesError("Not enough nodes available to allocate.
> " + msg)
> ducktape.cluster.node_container.InsufficientResourcesError: Not enough nodes
> available to allocate. linux nodes requested: 1. linux nodes available: 0
> {code}
> The task here is to revert the changes made in KAFKA-16272 [PR
> 15576|https://github.com/apache/kafka/pull/15576].
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
