def _job_template(self, external_schedule):
check.inst_param(external_schedule, 'external_schedule', ExternalSchedule)
local_target = external_schedule.get_origin()
job_config = self.job_config
external_schedule_name = external_schedule.name
job_name = get_k8s_job_name(external_schedule_name)
pod_name = job_name
job_template = construct_dagster_k8s_job(
job_config=job_config,
command=['dagster'],
args=[
'api',
'launch_scheduled_execution',
'/tmp/launch_scheduled_execution_output', # https://bugs.python.org/issue20074 prevents using /dev/stdout
'--schedule_name',
external_schedule_name,
]
+ local_target.get_repo_cli_args().split(' '),
job_name=job_name,
pod_name=pod_name,
component='scheduled_job',
)
return job_template
def _job_template(self, external_schedule):
check.inst_param(external_schedule, "external_schedule", ExternalSchedule)
local_target = external_schedule.get_external_origin()
job_config = self.job_config
external_schedule_name = external_schedule.name
job_name = get_k8s_job_name(external_schedule_name)
pod_name = job_name
job_template = construct_dagster_k8s_job(
job_config=job_config,
args=[
"dagster",
"api",
"launch_scheduled_execution",
"/tmp/launch_scheduled_execution_output", # https://bugs.python.org/issue20074 prevents using /dev/stdout
"--schedule_name",
external_schedule_name,
]
+ local_target.get_repo_cli_args().split(" "),
job_name=job_name,
pod_name=pod_name,
component="scheduled_job",
)
return job_template
def check_step_health(
self,
step_contexts: List[IStepContext],
known_state: KnownExecutionState,
):
assert len(step_contexts) == 1, "Checking multiple steps is not currently supported"
step_context = step_contexts[0]
k8s_name_key = get_k8s_job_name(
self.pipeline_context.plan_data.pipeline_run.run_id,
step_context.step.key,
)
job_name = "dagster-job-%s" % (k8s_name_key)
job = kubernetes.client.BatchV1Api().read_namespaced_job(
namespace=self._job_namespace, name=job_name
)
if job.status.failed:
step_failure_event = DagsterEvent.step_failure_event(
step_context=step_context,
step_failure_data=StepFailureData(error=None, user_failure_data=None),
)
return [step_failure_event]
return []
def launch_steps(
self,
step_contexts: List[IStepContext],
known_state: KnownExecutionState,
):
assert len(
step_contexts
) == 1, "Launching multiple steps is not currently supported"
step_context = step_contexts[0]
k8s_name_key = get_k8s_job_name(
self.pipeline_context.plan_data.pipeline_run.run_id,
step_context.step.key,
)
job_name = "dagster-job-%s" % (k8s_name_key)
pod_name = "dagster-job-%s" % (k8s_name_key)
pipeline_origin = self.pipeline_context.reconstructable_pipeline.get_python_origin(
)
execute_step_args = ExecuteStepArgs(
pipeline_origin=pipeline_origin,
pipeline_run_id=self.pipeline_context.pipeline_run.run_id,
step_keys_to_execute=[step_context.step.key],
instance_ref=self.pipeline_context.instance.get_ref(),
retry_mode=self.retries.for_inner_plan(),
known_state=known_state,
should_verify_step=True,
)
input_json = serialize_dagster_namedtuple(execute_step_args)
args = ["dagster", "api", "execute_step", input_json]
job_config = self._job_config
if not job_config.job_image:
job_config = job_config.with_image(
pipeline_origin.repository_origin.container_image)
if not job_config.job_image:
raise Exception(
"No image included in either executor config or the pipeline")
job = construct_dagster_k8s_job(
job_config,
args,
job_name,
get_user_defined_k8s_config(frozentags()),
pod_name,
)
kubernetes.config.load_incluster_config()
kubernetes.client.BatchV1Api().create_namespaced_job(
body=job, namespace=self._job_namespace)
def _execute_step_k8s_job(
self,
execute_step_args_packed,
job_config_dict,
job_namespace,
load_incluster_config,
user_defined_k8s_config_dict=None,
kubeconfig_file=None,
):
"""Run step execution in a K8s job pod."""
execute_step_args = unpack_value(
check.dict_param(
execute_step_args_packed,
"execute_step_args_packed",
))
check.inst_param(execute_step_args, "execute_step_args",
ExecuteStepArgs)
check.invariant(
len(execute_step_args.step_keys_to_execute) == 1,
"Celery K8s task executor can only execute 1 step at a time",
)
# Celery will serialize this as a list
job_config = DagsterK8sJobConfig.from_dict(job_config_dict)
check.inst_param(job_config, "job_config", DagsterK8sJobConfig)
check.str_param(job_namespace, "job_namespace")
check.bool_param(load_incluster_config, "load_incluster_config")
user_defined_k8s_config = UserDefinedDagsterK8sConfig.from_dict(
user_defined_k8s_config_dict)
check.opt_inst_param(
user_defined_k8s_config,
"user_defined_k8s_config",
UserDefinedDagsterK8sConfig,
)
check.opt_str_param(kubeconfig_file, "kubeconfig_file")
# For when launched via DinD or running the cluster
if load_incluster_config:
kubernetes.config.load_incluster_config()
else:
kubernetes.config.load_kube_config(kubeconfig_file)
instance = DagsterInstance.from_ref(execute_step_args.instance_ref)
pipeline_run = instance.get_run_by_id(
execute_step_args.pipeline_run_id)
check.inst(
pipeline_run,
PipelineRun,
"Could not load run {}".format(execute_step_args.pipeline_run_id),
)
step_key = execute_step_args.step_keys_to_execute[0]
celery_worker_name = self.request.hostname
celery_pod_name = os.environ.get("HOSTNAME")
instance.report_engine_event(
"Task for step {step_key} picked up by Celery".format(
step_key=step_key),
pipeline_run,
EngineEventData([
EventMetadataEntry.text(celery_worker_name,
"Celery worker name"),
EventMetadataEntry.text(celery_pod_name,
"Celery worker Kubernetes Pod name"),
]),
CeleryK8sJobExecutor,
step_key=step_key,
)
if pipeline_run.status != PipelineRunStatus.STARTED:
instance.report_engine_event(
"Not scheduling step because pipeline run status is not STARTED",
pipeline_run,
EngineEventData([
EventMetadataEntry.text(step_key, "Step key"),
]),
CeleryK8sJobExecutor,
step_key=step_key,
)
return []
# Ensure we stay below k8s name length limits
k8s_name_key = get_k8s_job_name(execute_step_args.pipeline_run_id,
step_key)
retry_state = execute_step_args.known_state.get_retry_state()
if retry_state.get_attempt_count(step_key):
attempt_number = retry_state.get_attempt_count(step_key)
job_name = "dagster-job-%s-%d" % (k8s_name_key, attempt_number)
pod_name = "dagster-job-%s-%d" % (k8s_name_key, attempt_number)
else:
job_name = "dagster-job-%s" % (k8s_name_key)
pod_name = "dagster-job-%s" % (k8s_name_key)
input_json = serialize_dagster_namedtuple(execute_step_args)
args = ["dagster", "api", "execute_step", input_json]
job = construct_dagster_k8s_job(job_config, args, job_name,
user_defined_k8s_config, pod_name)
# Running list of events generated from this task execution
events = []
# Post event for starting execution
job_name = job.metadata.name
engine_event = instance.report_engine_event(
"Executing step {} in Kubernetes job {}".format(
step_key, job_name),
pipeline_run,
EngineEventData(
[
EventMetadataEntry.text(step_key, "Step key"),
EventMetadataEntry.text(job_name, "Kubernetes Job name"),
EventMetadataEntry.text(job_config.job_image, "Job image"),
EventMetadataEntry.text(job_config.image_pull_policy,
"Image pull policy"),
EventMetadataEntry.text(str(job_config.image_pull_secrets),
"Image pull secrets"),
EventMetadataEntry.text(
str(job_config.service_account_name),
"Service account name"),
],
marker_end=DELEGATE_MARKER,
),
CeleryK8sJobExecutor,
# validated above that step_keys is length 1, and it is not possible to use ETH or
# execution plan in this function (Celery K8s workers should not access to user code)
step_key=step_key,
)
events.append(engine_event)
try:
kubernetes.client.BatchV1Api().create_namespaced_job(
body=job, namespace=job_namespace)
except kubernetes.client.rest.ApiException as e:
if e.reason == "Conflict":
# There is an existing job with the same name so proceed and see if the existing job succeeded
instance.report_engine_event(
"Did not create Kubernetes job {} for step {} since job name already "
"exists, proceeding with existing job.".format(
job_name, step_key),
pipeline_run,
EngineEventData(
[
EventMetadataEntry.text(step_key, "Step key"),
EventMetadataEntry.text(job_name,
"Kubernetes Job name"),
],
marker_end=DELEGATE_MARKER,
),
CeleryK8sJobExecutor,
step_key=step_key,
)
else:
instance.report_engine_event(
"Encountered unexpected error while creating Kubernetes job {} for step {}, "
"exiting.".format(job_name, step_key),
pipeline_run,
EngineEventData(
[
EventMetadataEntry.text(step_key, "Step key"),
],
error=serializable_error_info_from_exc_info(
sys.exc_info()),
),
CeleryK8sJobExecutor,
step_key=step_key,
)
return []
try:
wait_for_job_success(
job_name=job_name,
namespace=job_namespace,
instance=instance,
run_id=execute_step_args.pipeline_run_id,
)
except (DagsterK8sError, DagsterK8sTimeoutError) as err:
step_failure_event = construct_step_failure_event_and_handle(
pipeline_run, step_key, err, instance=instance)
events.append(step_failure_event)
except DagsterK8sPipelineStatusException:
instance.report_engine_event(
"Terminating Kubernetes Job because pipeline run status is not STARTED",
pipeline_run,
EngineEventData([
EventMetadataEntry.text(step_key, "Step key"),
EventMetadataEntry.text(job_name, "Kubernetes Job name"),
EventMetadataEntry.text(job_namespace,
"Kubernetes Job namespace"),
]),
CeleryK8sJobExecutor,
step_key=step_key,
)
delete_job(job_name=job_name, namespace=job_namespace)
return []
except (
DagsterK8sUnrecoverableAPIError,
DagsterK8sAPIRetryLimitExceeded,
# We shouldn't see unwrapped APIExceptions anymore, as they should all be wrapped in
# a retry boundary. We still catch it here just in case we missed one so that we can
# report it to the event log
kubernetes.client.rest.ApiException,
) as err:
instance.report_engine_event(
"Encountered unexpected error while waiting on Kubernetes job {} for step {}, "
"exiting.".format(job_name, step_key),
pipeline_run,
EngineEventData(
[
EventMetadataEntry.text(step_key, "Step key"),
],
error=serializable_error_info_from_exc_info(
sys.exc_info()),
),
CeleryK8sJobExecutor,
step_key=step_key,
)
return []
try:
pod_names = get_pod_names_in_job(job_name, namespace=job_namespace)
except kubernetes.client.rest.ApiException as e:
instance.report_engine_event(
"Encountered unexpected error retreiving Pods for Kubernetes job {} for step {}, "
"exiting.".format(job_name, step_key),
pipeline_run,
EngineEventData(
[
EventMetadataEntry.text(step_key, "Step key"),
],
error=serializable_error_info_from_exc_info(
sys.exc_info()),
),
CeleryK8sJobExecutor,
step_key=step_key,
)
return []
# Post engine event for log retrieval
engine_event = instance.report_engine_event(
"Retrieving logs from Kubernetes Job pods",
pipeline_run,
EngineEventData(
[EventMetadataEntry.text("\n".join(pod_names), "Pod names")]),
CeleryK8sJobExecutor,
step_key=step_key,
)
events.append(engine_event)
logs = []
for pod_name in pod_names:
try:
raw_logs = retrieve_pod_logs(pod_name, namespace=job_namespace)
logs += raw_logs.split("\n")
except kubernetes.client.rest.ApiException as e:
instance.report_engine_event(
"Encountered unexpected error while fetching pod logs for Kubernetes job {}, "
"Pod name {} for step {}. Will attempt to continue with other pods."
.format(job_name, pod_name, step_key),
pipeline_run,
EngineEventData(
[
EventMetadataEntry.text(step_key, "Step key"),
],
error=serializable_error_info_from_exc_info(
sys.exc_info()),
),
CeleryK8sJobExecutor,
step_key=step_key,
)
events += filter_dagster_events_from_pod_logs(logs)
serialized_events = [
serialize_dagster_namedtuple(event) for event in events
]
return serialized_events
def _execute_step_k8s_job(
self,
instance_ref_dict,
step_keys,
run_config,
mode,
repo_name,
repo_location_name,
run_id,
job_config_dict,
job_namespace,
load_incluster_config,
retries_dict,
pipeline_origin_packed,
user_defined_k8s_config_dict=None,
kubeconfig_file=None,
):
"""Run step execution in a K8s job pod.
"""
check.dict_param(instance_ref_dict, "instance_ref_dict")
check.list_param(step_keys, "step_keys", of_type=str)
check.invariant(
len(step_keys) == 1, "Celery K8s task executor can only execute 1 step at a time"
)
check.dict_param(run_config, "run_config")
check.str_param(mode, "mode")
check.str_param(repo_name, "repo_name")
check.str_param(repo_location_name, "repo_location_name")
check.str_param(run_id, "run_id")
# Celery will serialize this as a list
job_config = DagsterK8sJobConfig.from_dict(job_config_dict)
check.inst_param(job_config, "job_config", DagsterK8sJobConfig)
check.str_param(job_namespace, "job_namespace")
check.bool_param(load_incluster_config, "load_incluster_config")
check.dict_param(retries_dict, "retries_dict")
pipeline_origin = unpack_value(
check.dict_param(
pipeline_origin_packed, "pipeline_origin_packed"
) # TODO: make part of args
)
check.inst(pipeline_origin, PipelineOrigin)
user_defined_k8s_config = UserDefinedDagsterK8sConfig.from_dict(
user_defined_k8s_config_dict
)
check.opt_inst_param(
user_defined_k8s_config, "user_defined_k8s_config", UserDefinedDagsterK8sConfig,
)
check.opt_str_param(kubeconfig_file, "kubeconfig_file")
# For when launched via DinD or running the cluster
if load_incluster_config:
kubernetes.config.load_incluster_config()
else:
kubernetes.config.load_kube_config(kubeconfig_file)
instance_ref = InstanceRef.from_dict(instance_ref_dict)
instance = DagsterInstance.from_ref(instance_ref)
pipeline_run = instance.get_run_by_id(run_id)
check.invariant(pipeline_run, "Could not load run {}".format(run_id))
step_key = step_keys[0]
celery_worker_name = self.request.hostname
celery_pod_name = os.environ.get("HOSTNAME")
instance.report_engine_event(
"Task for step {step_key} picked up by Celery".format(step_key=step_key),
pipeline_run,
EngineEventData(
[
EventMetadataEntry.text(celery_worker_name, "Celery worker name"),
EventMetadataEntry.text(celery_pod_name, "Celery worker Kubernetes Pod name"),
]
),
CeleryK8sJobExecutor,
step_key=step_key,
)
if pipeline_run.status != PipelineRunStatus.STARTED:
instance.report_engine_event(
"Not scheduling step because pipeline run status is not STARTED",
pipeline_run,
EngineEventData([EventMetadataEntry.text(step_key, "Step keys"),]),
CeleryK8sJobExecutor,
step_key=step_key,
)
return
# Ensure we stay below k8s name length limits
k8s_name_key = get_k8s_job_name(run_id, step_key)
retries = Retries.from_config(retries_dict)
if retries.get_attempt_count(step_key):
attempt_number = retries.get_attempt_count(step_key)
job_name = "dagster-job-%s-%d" % (k8s_name_key, attempt_number)
pod_name = "dagster-job-%s-%d" % (k8s_name_key, attempt_number)
else:
job_name = "dagster-job-%s" % (k8s_name_key)
pod_name = "dagster-job-%s" % (k8s_name_key)
input_json = serialize_dagster_namedtuple(
ExecuteStepArgs(
pipeline_origin=pipeline_origin,
pipeline_run_id=run_id,
instance_ref=None,
mode=mode,
step_keys_to_execute=step_keys,
run_config=run_config,
retries_dict=retries_dict,
)
)
command = ["dagster"]
args = ["api", "execute_step_with_structured_logs", input_json]
job = construct_dagster_k8s_job(
job_config, command, args, job_name, user_defined_k8s_config, pod_name
)
# Running list of events generated from this task execution
events = []
# Post event for starting execution
job_name = job.metadata.name
engine_event = instance.report_engine_event(
"Executing step {} in Kubernetes job {}".format(step_key, job_name),
pipeline_run,
EngineEventData(
[
EventMetadataEntry.text(step_key, "Step keys"),
EventMetadataEntry.text(job_name, "Kubernetes Job name"),
EventMetadataEntry.text(pod_name, "Kubernetes Pod name"),
EventMetadataEntry.text(job_config.job_image, "Job image"),
EventMetadataEntry.text(job_config.image_pull_policy, "Image pull policy"),
EventMetadataEntry.text(
str(job_config.image_pull_secrets), "Image pull secrets"
),
EventMetadataEntry.text(
str(job_config.service_account_name), "Service account name"
),
],
marker_end=DELEGATE_MARKER,
),
CeleryK8sJobExecutor,
# validated above that step_keys is length 1, and it is not possible to use ETH or
# execution plan in this function (Celery K8s workers should not access to user code)
step_key=step_key,
)
events.append(engine_event)
try:
kubernetes.client.BatchV1Api().create_namespaced_job(body=job, namespace=job_namespace)
except kubernetes.client.rest.ApiException as e:
if e.reason == "Conflict":
# There is an existing job with the same name so do not procede.
instance.report_engine_event(
"Did not create Kubernetes job {} for step {} since job name already "
"exists, exiting.".format(job_name, step_key),
pipeline_run,
EngineEventData(
[
EventMetadataEntry.text(step_key, "Step keys"),
EventMetadataEntry.text(job_name, "Kubernetes Job name"),
EventMetadataEntry.text(pod_name, "Kubernetes Pod name"),
],
marker_end=DELEGATE_MARKER,
),
CeleryK8sJobExecutor,
step_key=step_key,
)
else:
instance.report_engine_event(
"Encountered unexpected error while creating Kubernetes job {} for step {}, "
"exiting.".format(job_name, step_key),
pipeline_run,
EngineEventData(
[
EventMetadataEntry.text(step_key, "Step keys"),
EventMetadataEntry.text(e, "Error"),
]
),
CeleryK8sJobExecutor,
step_key=step_key,
)
return
try:
wait_for_job_success(
job_name=job_name, namespace=job_namespace, instance=instance, run_id=run_id,
)
except DagsterK8sPipelineStatusException:
instance.report_engine_event(
"Terminating Kubernetes Job because pipeline run status is not STARTED",
pipeline_run,
EngineEventData(
[
EventMetadataEntry.text(step_key, "Step keys"),
EventMetadataEntry.text(job_name, "Kubernetes Job name"),
EventMetadataEntry.text(job_namespace, "Kubernetes Job namespace"),
]
),
CeleryK8sJobExecutor,
step_key=step_key,
)
delete_job(job_name=job_name, namespace=job_namespace)
return
pod_names = get_pod_names_in_job(job_name, namespace=job_namespace)
# Post engine event for log retrieval
engine_event = instance.report_engine_event(
"Retrieving logs from Kubernetes Job pods",
pipeline_run,
EngineEventData([EventMetadataEntry.text("\n".join(pod_names), "Pod names")]),
CeleryK8sJobExecutor,
step_key=step_key,
)
events.append(engine_event)
logs = []
for pod_name in pod_names:
raw_logs = retrieve_pod_logs(pod_name, namespace=job_namespace)
logs += raw_logs.split("\n")
events += filter_dagster_events_from_pod_logs(logs)
serialized_events = [serialize_dagster_namedtuple(event) for event in events]
return serialized_events
def _execute_step_k8s_job(
_self,
instance_ref_dict,
step_keys,
run_config,
mode,
repo_name,
repo_location_name,
run_id,
job_config_dict,
job_namespace,
load_incluster_config,
retries_dict,
pipeline_origin_packed,
resources=None,
kubeconfig_file=None,
):
'''Run step execution in a K8s job pod.
'''
check.dict_param(instance_ref_dict, 'instance_ref_dict')
check.list_param(step_keys, 'step_keys', of_type=str)
check.invariant(
len(step_keys) == 1,
'Celery K8s task executor can only execute 1 step at a time')
check.dict_param(run_config, 'run_config')
check.str_param(mode, 'mode')
check.str_param(repo_name, 'repo_name')
check.str_param(repo_location_name, 'repo_location_name')
check.str_param(run_id, 'run_id')
# Celery will serialize this as a list
job_config = DagsterK8sJobConfig.from_dict(job_config_dict)
check.inst_param(job_config, 'job_config', DagsterK8sJobConfig)
check.str_param(job_namespace, 'job_namespace')
check.bool_param(load_incluster_config, 'load_incluster_config')
check.dict_param(retries_dict, 'retries_dict')
pipeline_origin = unpack_value(
check.dict_param(
pipeline_origin_packed,
'pipeline_origin_packed') # TODO: make part of args
)
check.inst(pipeline_origin, PipelineOrigin)
check.opt_dict_param(resources,
'resources',
key_type=str,
value_type=dict)
check.opt_str_param(kubeconfig_file, 'kubeconfig_file')
# For when launched via DinD or running the cluster
if load_incluster_config:
kubernetes.config.load_incluster_config()
else:
kubernetes.config.load_kube_config(kubeconfig_file)
instance_ref = InstanceRef.from_dict(instance_ref_dict)
instance = DagsterInstance.from_ref(instance_ref)
pipeline_run = instance.get_run_by_id(run_id)
check.invariant(pipeline_run, 'Could not load run {}'.format(run_id))
step_key = step_keys[0]
if pipeline_run.status != PipelineRunStatus.STARTED:
instance.report_engine_event(
'Not scheduling step because pipeline run status is not STARTED',
pipeline_run,
EngineEventData([
EventMetadataEntry.text(step_key, 'Step keys'),
]),
CeleryK8sJobExecutor,
step_key=step_key,
)
return
# Ensure we stay below k8s name length limits
k8s_name_key = get_k8s_job_name(run_id, step_key)
retries = Retries.from_config(retries_dict)
if retries.get_attempt_count(step_key):
attempt_number = retries.get_attempt_count(step_key)
job_name = 'dagster-job-%s-%d' % (k8s_name_key, attempt_number)
pod_name = 'dagster-job-%s-%d' % (k8s_name_key, attempt_number)
else:
job_name = 'dagster-job-%s' % (k8s_name_key)
pod_name = 'dagster-job-%s' % (k8s_name_key)
input_json = serialize_dagster_namedtuple(
ExecuteStepArgs(
pipeline_origin=pipeline_origin,
pipeline_run_id=run_id,
instance_ref=None,
mode=mode,
step_keys_to_execute=step_keys,
run_config=run_config,
retries_dict=retries_dict,
))
command = ['dagster']
args = ['api', 'execute_step_with_structured_logs', input_json]
job = construct_dagster_k8s_job(job_config, command, args, job_name,
resources, pod_name)
# Running list of events generated from this task execution
events = []
# Post event for starting execution
job_name = job.metadata.name
engine_event = instance.report_engine_event(
'Executing step {} in Kubernetes job {}'.format(
step_key, job_name),
pipeline_run,
EngineEventData(
[
EventMetadataEntry.text(step_key, 'Step keys'),
EventMetadataEntry.text(job_name, 'Kubernetes Job name'),
EventMetadataEntry.text(pod_name, 'Kubernetes Pod name'),
EventMetadataEntry.text(job_config.job_image, 'Job image'),
EventMetadataEntry.text(job_config.image_pull_policy,
'Image pull policy'),
EventMetadataEntry.text(str(job_config.image_pull_secrets),
'Image pull secrets'),
EventMetadataEntry.text(
str(job_config.service_account_name),
'Service account name'),
],
marker_end=DELEGATE_MARKER,
),
CeleryK8sJobExecutor,
# validated above that step_keys is length 1, and it is not possible to use ETH or
# execution plan in this function (Celery K8s workers should not access to user code)
step_key=step_key,
)
events.append(engine_event)
try:
kubernetes.client.BatchV1Api().create_namespaced_job(
body=job, namespace=job_namespace)
except kubernetes.client.rest.ApiException as e:
if e.reason == 'Conflict':
# There is an existing job with the same name so do not procede.
instance.report_engine_event(
'Did not create Kubernetes job {} for step {} since job name already '
'exists, exiting.'.format(job_name, step_key),
pipeline_run,
EngineEventData(
[
EventMetadataEntry.text(step_key, 'Step keys'),
EventMetadataEntry.text(job_name,
'Kubernetes Job name'),
EventMetadataEntry.text(pod_name,
'Kubernetes Pod name'),
],
marker_end=DELEGATE_MARKER,
),
CeleryK8sJobExecutor,
step_key=step_key,
)
else:
instance.report_engine_event(
'Encountered unexpected error while creating Kubernetes job {} for step {}, '
'exiting.'.format(job_name, step_key),
pipeline_run,
EngineEventData([
EventMetadataEntry.text(step_key, 'Step keys'),
EventMetadataEntry.text(e, 'Error'),
]),
CeleryK8sJobExecutor,
step_key=step_key,
)
return
try:
wait_for_job_success(
job_name=job_name,
namespace=job_namespace,
instance=instance,
run_id=run_id,
)
except DagsterK8sPipelineStatusException:
instance.report_engine_event(
'Terminating Kubernetes Job because pipeline run status is not STARTED',
pipeline_run,
EngineEventData([
EventMetadataEntry.text(step_key, 'Step keys'),
EventMetadataEntry.text(job_name, 'Kubernetes Job name'),
EventMetadataEntry.text(job_namespace,
'Kubernetes Job namespace'),
]),
CeleryK8sJobExecutor,
step_key=step_key,
)
delete_job(job_name=job_name, namespace=job_namespace)
return
pod_names = get_pod_names_in_job(job_name, namespace=job_namespace)
# Post engine event for log retrieval
engine_event = instance.report_engine_event(
'Retrieving logs from Kubernetes Job pods',
pipeline_run,
EngineEventData(
[EventMetadataEntry.text('\n'.join(pod_names), 'Pod names')]),
CeleryK8sJobExecutor,
step_key=step_key,
)
events.append(engine_event)
logs = []
for pod_name in pod_names:
raw_logs = retrieve_pod_logs(pod_name, namespace=job_namespace)
logs += raw_logs.split('\n')
events += filter_dagster_events_from_pod_logs(logs)
serialized_events = [
serialize_dagster_namedtuple(event) for event in events
]
return serialized_events
def test_k8s_executor_combine_configs(
dagster_instance_for_k8s_run_launcher,
helm_namespace_for_k8s_run_launcher,
dagster_docker_image,
dagit_url_for_k8s_run_launcher,
):
# Verifies that the step pods created by the k8s executor combine secrets
# from run launcher config and executor config. Also includes each executor secret
# twice to verify that duplicates within the combined config are acceptable
run_config = merge_dicts(
load_yaml_from_path(
os.path.join(get_test_project_environments_path(), "env.yaml")),
load_yaml_from_path(
os.path.join(get_test_project_environments_path(), "env_s3.yaml")),
{
"execution": {
"k8s": {
"config": {
"job_image":
dagster_docker_image,
"image_pull_secrets": [
{
"name": TEST_OTHER_IMAGE_PULL_SECRET_NAME
},
{
"name": TEST_OTHER_IMAGE_PULL_SECRET_NAME
},
],
"env_config_maps":
[TEST_OTHER_CONFIGMAP_NAME, TEST_OTHER_CONFIGMAP_NAME],
"env_secrets":
[TEST_OTHER_SECRET_NAME, TEST_OTHER_SECRET_NAME],
"labels": {
"executor_label_key": "executor_label_value"
},
}
}
},
},
)
run_id = _launch_executor_run(
dagit_url_for_k8s_run_launcher,
run_config,
dagster_instance_for_k8s_run_launcher,
helm_namespace_for_k8s_run_launcher,
)
step_job_key = get_k8s_job_name(run_id, "count_letters")
step_job_name = f"dagster-job-{step_job_key}"
step_pods = get_pods_in_job(job_name=step_job_name,
namespace=helm_namespace_for_k8s_run_launcher)
assert len(step_pods) == 1
step_pod = step_pods[0]
assert len(step_pod.spec.containers) == 1, str(step_pod)
labels = step_pod.metadata.labels
assert labels["run_launcher_label_key"] == "run_launcher_label_value"
assert labels["executor_label_key"] == "executor_label_value"
env_from = step_pod.spec.containers[0].env_from
config_map_names = {
env.config_map_ref.name
for env in env_from if env.config_map_ref
}
secret_names = {env.secret_ref.name for env in env_from if env.secret_ref}
# Run launcher secrets and config maps included
assert TEST_SECRET_NAME in secret_names
assert TEST_CONFIGMAP_NAME in config_map_names
# Executor secrets and config maps included
assert TEST_OTHER_SECRET_NAME in secret_names
assert TEST_OTHER_CONFIGMAP_NAME in config_map_names
image_pull_secrets_names = [
secret.name for secret in step_pod.spec.image_pull_secrets
]
assert TEST_IMAGE_PULL_SECRET_NAME in image_pull_secrets_names
assert TEST_OTHER_IMAGE_PULL_SECRET_NAME in image_pull_secrets_names
