def submit_job(self, job_configuration):
try:
cluster_data = self._get_cluster_data(job_configuration.id)
node_data = NodeData(
job_configuration.as_cluster_config()).add_core().done()
zip_resource_files = cluster_data.upload_node_data(
node_data).to_resource_file()
start_task = create_cluster_helper.generate_cluster_start_task(
self,
zip_resource_files,
job_configuration.gpu_enabled,
job_configuration.docker_repo,
worker_on_master=job_configuration.worker_on_master)
application_tasks = []
for application in job_configuration.applications:
application_tasks.append((application,
cluster_submit_helper.generate_task(
self, job_configuration.id,
application)))
job_manager_task = job_submit_helper.generate_task(
self, job_configuration, application_tasks)
software_metadata_key = "spark"
vm_image = models.VmImage(publisher='Canonical',
offer='UbuntuServer',
sku='16.04')
if job_configuration.max_dedicated_nodes and not job_configuration.max_low_pri_nodes:
autoscale_formula = "maxNumberofVMs = {0}; targetNumberofVMs = {1};" \
" $TargetDedicatedNodes=min(maxNumberofVMs, targetNumberofVMs)".format(
job_configuration.max_dedicated_nodes, job_configuration.max_dedicated_nodes)
elif job_configuration.max_low_pri_nodes and not job_configuration.max_dedicated_nodes:
autoscale_formula = "maxNumberofVMs = {0}; targetNumberofVMs = {1};" \
" $TargetLowPriorityNodes=min(maxNumberofVMs, targetNumberofVMs)".format(
job_configuration.max_low_pri_nodes, job_configuration.max_low_pri_nodes)
else:
raise error.AztkError("Jobs do not support both dedicated and low priority nodes." \
" JobConfiguration fields max_dedicated_nodes and max_low_pri_nodes are mutually exclusive values.")
job = self.__submit_job(
job_configuration=job_configuration,
start_task=start_task,
job_manager_task=job_manager_task,
autoscale_formula=autoscale_formula,
software_metadata_key=software_metadata_key,
vm_image_model=vm_image,
application_metadata='\n'.join(
application.name
for application in (job_configuration.applications or [])))
return models.Job(job)
except batch_error.BatchErrorException as e:
raise error.AztkError(helpers.format_batch_exception(e))
def create_cluster(core_cluster_operations,
spark_cluster_operations,
cluster_conf: models.ClusterConfiguration,
vm_image: base_models.VmImage,
wait: bool = False):
"""
Create a new aztk spark cluster
Args:
cluster_conf(aztk.spark.models.models.ClusterConfiguration): Configuration for the the cluster to be created
wait(bool): If you should wait for the cluster to be ready before returning
vm_image: models for cluster vm
Returns:
:obj:`aztk.spark.models.Cluster`
"""
cluster_conf = _apply_default_for_cluster_config(cluster_conf)
cluster_conf.validate()
cluster_data = core_cluster_operations.get_cluster_data(
cluster_conf.cluster_id)
try:
zip_resource_files = None
node_data = NodeData(cluster_conf).add_core().done()
zip_resource_files = cluster_data.upload_node_data(
node_data).to_resource_file()
start_task = spark_cluster_operations._generate_cluster_start_task(
core_cluster_operations,
zip_resource_files,
cluster_conf.cluster_id,
cluster_conf.gpu_enabled(),
cluster_conf.get_docker_repo(),
cluster_conf.get_docker_run_options(),
cluster_conf.file_shares,
cluster_conf.mixed_mode(),
cluster_conf.worker_on_master,
)
software_metadata_key = base_models.Software.spark
cluster = core_cluster_operations.create(cluster_conf,
software_metadata_key,
start_task, vm_image)
# Wait for the master to be ready
if wait:
util.wait_for_master_to_be_ready(core_cluster_operations,
spark_cluster_operations,
cluster.id)
cluster = spark_cluster_operations.get(cluster.id)
return cluster
except BatchErrorException as e:
raise error.AztkError(helpers.format_batch_exception(e))
def submit_job(self, job_configuration: models.JobConfiguration):
try:
job_configuration = _apply_default_for_job_config(
job_configuration)
job_configuration.validate()
cluster_data = self._get_cluster_data(job_configuration.id)
node_data = NodeData(
job_configuration.to_cluster_config()).add_core().done()
zip_resource_files = cluster_data.upload_node_data(
node_data).to_resource_file()
start_task = create_cluster_helper.generate_cluster_start_task(
self,
zip_resource_files,
job_configuration.id,
job_configuration.gpu_enabled,
job_configuration.get_docker_repo(),
mixed_mode=job_configuration.mixed_mode(),
worker_on_master=job_configuration.worker_on_master)
application_tasks = []
for application in job_configuration.applications:
application_tasks.append((application,
cluster_submit_helper.generate_task(
self, job_configuration.id,
application)))
job_manager_task = job_submit_helper.generate_task(
self, job_configuration, application_tasks)
software_metadata_key = "spark"
vm_image = models.VmImage(publisher='Canonical',
offer='UbuntuServer',
sku='16.04')
autoscale_formula = "$TargetDedicatedNodes = {0}; " \
"$TargetLowPriorityNodes = {1}".format(
job_configuration.max_dedicated_nodes,
job_configuration.max_low_pri_nodes)
job = self.__submit_job(
job_configuration=job_configuration,
start_task=start_task,
job_manager_task=job_manager_task,
autoscale_formula=autoscale_formula,
software_metadata_key=software_metadata_key,
vm_image_model=vm_image,
application_metadata='\n'.join(
application.name
for application in (job_configuration.applications or [])))
return models.Job(job)
except batch_error.BatchErrorException as e:
raise error.AztkError(helpers.format_batch_exception(e))
def submit_job(core_job_operations,
spark_job_operations,
job_configuration: models.JobConfiguration,
wait: bool = False):
try:
job_configuration = _apply_default_for_job_config(job_configuration)
job_configuration.validate()
cluster_data = core_job_operations.get_cluster_data(job_configuration.id)
node_data = NodeData(job_configuration.to_cluster_config()).add_core().done()
zip_resource_files = cluster_data.upload_node_data(node_data).to_resource_file()
start_task = spark_job_operations._generate_cluster_start_task(
core_job_operations,
zip_resource_files,
job_configuration.id,
job_configuration.gpu_enabled,
job_configuration.get_docker_repo(),
job_configuration.get_docker_run_options(),
mixed_mode=job_configuration.mixed_mode(),
worker_on_master=job_configuration.worker_on_master,
)
application_tasks = []
for application in job_configuration.applications:
application_tasks.append((
application,
spark_job_operations._generate_application_task(core_job_operations, job_configuration.id, application),
))
job_manager_task = generate_job_manager_task(core_job_operations, job_configuration, application_tasks)
software_metadata_key = base_models.Software.spark
vm_image = models.VmImage(publisher="Canonical", offer="UbuntuServer", sku="16.04")
autoscale_formula = "$TargetDedicatedNodes = {0}; " "$TargetLowPriorityNodes = {1}".format(
job_configuration.max_dedicated_nodes, job_configuration.max_low_pri_nodes)
job = core_job_operations.submit(
job_configuration=job_configuration,
start_task=start_task,
job_manager_task=job_manager_task,
autoscale_formula=autoscale_formula,
software_metadata_key=software_metadata_key,
vm_image_model=vm_image,
application_metadata="\n".join(application.name for application in (job_configuration.applications or [])),
)
if wait:
spark_job_operations.wait(id=job_configuration.id)
return models.Job(job)
except batch_error.BatchErrorException as e:
raise error.AztkError(helpers.format_batch_exception(e))
def create_cluster(self, configuration: models.ClusterConfiguration, wait: bool = False):
"""
Create a new aztk spark cluster
Args:
cluster_conf(aztk.spark.models.models.ClusterConfiguration): Configuration for the the cluster to be created
wait(bool): If you should wait for the cluster to be ready before returning
Returns:
aztk.spark.models.Cluster
"""
cluster_conf = models.ClusterConfiguration()
cluster_conf.merge(DEFAULT_CLUSTER_CONFIG)
cluster_conf.merge(configuration)
cluster_conf.validate()
cluster_data = self._get_cluster_data(cluster_conf.cluster_id)
try:
zip_resource_files = None
node_data = NodeData(cluster_conf).add_core().done()
zip_resource_files = cluster_data.upload_node_data(node_data).to_resource_file()
start_task = create_cluster_helper.generate_cluster_start_task(self,
zip_resource_files,
cluster_conf.cluster_id,
cluster_conf.gpu_enabled(),
cluster_conf.get_docker_repo(),
cluster_conf.file_shares,
cluster_conf.plugins,
cluster_conf.mixed_mode(),
cluster_conf.worker_on_master)
software_metadata_key = "spark"
vm_image = models.VmImage(
publisher='Canonical',
offer='UbuntuServer',
sku='16.04')
cluster = self.__create_pool_and_job(
cluster_conf, software_metadata_key, start_task, vm_image)
# Wait for the master to be ready
if wait:
util.wait_for_master_to_be_ready(self, cluster.id)
cluster = self.get_cluster(cluster.id)
return cluster
except batch_error.BatchErrorException as e:
raise error.AztkError(helpers.format_batch_exception(e))
def create_cluster(self,
cluster_conf: models.ClusterConfiguration,
wait: bool = False):
cluster_conf.validate()
cluster_data = self._get_cluster_data(cluster_conf.cluster_id)
try:
zip_resource_files = None
node_data = NodeData(cluster_conf).add_core().done()
zip_resource_files = cluster_data.upload_node_data(
node_data).to_resource_file()
start_task = create_cluster_helper.generate_cluster_start_task(
self, zip_resource_files, cluster_conf.gpu_enabled(),
cluster_conf.docker_repo,
cluster_conf.file_shares, cluster_conf.plugins,
cluster_conf.mixed_mode(), cluster_conf.worker_on_master)
software_metadata_key = "spark"
vm_image = models.VmImage(publisher='Canonical',
offer='UbuntuServer',
sku='16.04')
cluster = self.__create_pool_and_job(cluster_conf,
software_metadata_key,
start_task, vm_image)
# Wait for the master to be ready
if wait:
util.wait_for_master_to_be_ready(self, cluster.id)
cluster = self.get_cluster(cluster.id)
return cluster
except batch_error.BatchErrorException as e:
raise error.AztkError(helpers.format_batch_exception(e))