def execute(args: typing.NamedTuple):
spark_client = aztk.spark.Client(config.load_aztk_secrets())
cluster_conf = ClusterConfiguration()
cluster_conf.spark_configuration = load_aztk_spark_config()
# read cluster.yaml configuration file, overwrite values with args
file_config, wait = config.read_cluster_config()
cluster_conf.merge(file_config)
cluster_conf.merge(
ClusterConfiguration(
cluster_id=args.cluster_id,
size=args.size,
size_low_priority=args.size_low_priority,
vm_size=args.vm_size,
subnet_id=args.subnet_id,
user_configuration=UserConfiguration(username=args.username, password=args.password),
))
if cluster_conf.toolkit:
if args.docker_repo:
cluster_conf.toolkit.docker_repo = args.docker_repo
if args.docker_run_options:
cluster_conf.toolkit.docker_run_options = args.docker_run_options
wait = wait if args.wait is None else args.wait
user_configuration = cluster_conf.user_configuration
if user_configuration and user_configuration.username:
ssh_key, password = utils.get_ssh_key_or_prompt(
spark_client.secrets_configuration.ssh_pub_key,
user_configuration.username,
user_configuration.password,
spark_client.secrets_configuration,
)
cluster_conf.user_configuration = aztk.spark.models.UserConfiguration(
username=user_configuration.username, password=password, ssh_key=ssh_key)
else:
cluster_conf.user_configuration = None
cluster_conf.validate()
utils.print_cluster_conf(cluster_conf, wait)
with utils.Spinner():
# create spark cluster
cluster = spark_client.cluster.create(cluster_configuration=cluster_conf, wait=wait)
if wait:
log.info("Cluster %s created successfully.", cluster.id)
else:
log.info("Cluster %s is being provisioned.", cluster.id)
def cluster_config_from_dict(config: dict):
output = ClusterConfiguration()
wait = False
if config.get('id') is not None:
output.cluster_id = config['id']
if config.get('vm_size') is not None:
output.vm_size = config['vm_size']
if config.get('size'):
output.vm_count = config['size']
if config.get('size_low_pri'):
output.vm_low_pri_count = config['size_low_pri']
if config.get('subnet_id') is not None:
output.subnet_id = config['subnet_id']
if config.get('username') is not None:
output.user_configuration = UserConfiguration(
username=config['username'])
if config.get('password') is not None:
output.user_configuration.password = config['password']
if config.get('custom_scripts') not in [[None], None]:
output.custom_scripts = []
for custom_script in config['custom_scripts']:
output.custom_scripts.append(
aztk.spark.models.CustomScript(script=custom_script['script'],
run_on=custom_script['runOn']))
if config.get('azure_files') not in [[None], None]:
output.file_shares = []
for file_share in config['azure_files']:
output.file_shares.append(
aztk.spark.models.FileShare(
storage_account_name=file_share['storage_account_name'],
storage_account_key=file_share['storage_account_key'],
file_share_path=file_share['file_share_path'],
mount_path=file_share['mount_path'],
))
if config.get('docker_repo') is not None:
output.docker_repo = config['docker_repo']
if config.get('plugins') not in [[None], None]:
output.plugins = []
for plugin in config['plugins']:
ref = PluginReference.from_dict(plugin)
output.plugins.append(ref.get_plugin())
if config.get('worker_on_master') is not None:
output.worker_on_master = config['worker_on_master']
if config.get('wait') is not None:
wait = config['wait']
return output, wait