def create_job(self, k8s_job_client: client.BatchV1Api):
job_creation_response = k8s_job_client.create_namespaced_job(
body=self.mlcube_job_manifest,
namespace=self.namespace,
)
logging.info("MLCommons Box k8s job created. Status='%s'" %
str(job_creation_response.status))
def _create_flush_job(
batch_api: BatchV1Api,
command: List[str],
env: List[V1EnvVar],
image: str,
name: str,
namespace: str,
service_account_name: str,
) -> V1Job:
logger.info(f"creating job: {name}")
try:
return batch_api.create_namespaced_job(
namespace=namespace,
body=V1Job(
api_version="batch/v1",
kind="Job",
metadata=V1ObjectMeta(name=name, namespace=namespace),
spec=V1JobSpec(
template=V1PodTemplateSpec(
spec=V1PodSpec(
containers=[
V1Container(
image=image,
command=command,
name="flush",
volume_mounts=[
V1VolumeMount(mount_path="/data", name="queue")
],
env=env,
)
],
restart_policy="OnFailure",
volumes=[
V1Volume(
name="queue",
persistent_volume_claim=(
V1PersistentVolumeClaimVolumeSource(
claim_name=name
)
),
)
],
service_account_name=service_account_name,
)
)
),
),
)
except ApiException as e:
if e.reason == CONFLICT and json.loads(e.body)["reason"] == ALREADY_EXISTS:
logger.info(f"using existing job: {name}")
return batch_api.read_namespaced_job(name, namespace)
raise