def _adjust_path(candidate, adjustment, file_uploader: FileUploader):
if isinstance(candidate, str):
# path already adjusted or points to another dbfs object - pass it
if candidate.startswith("dbfs"):
return candidate
else:
file_path = pathlib.Path(candidate)
# this is a fix for pathlib behaviour related to WinError
# in case if we pass incorrect or unsupported string, for example local[*] on Win we receive a OSError
try:
local_file_exists = file_path.exists()
except OSError:
local_file_exists = False
if local_file_exists:
adjusted_path = "%s/%s" % (adjustment, file_path.as_posix())
if file_uploader.file_exists(adjusted_path):
dbx_echo(
"File is already stored in the deployment, no action needed"
)
else:
file_uploader.upload_file(file_path)
return adjusted_path
else:
return candidate
else:
return candidate
def execute(
environment: str,
cluster_id: str,
cluster_name: str,
job: str,
deployment_file: str,
requirements_file: str,
no_package: bool,
no_rebuild: bool,
):
api_client = prepare_environment(environment)
cluster_id = _preprocess_cluster_args(api_client, cluster_name, cluster_id)
dbx_echo(
f"Executing job: {job} in environment {environment} on cluster {cluster_name} (id: {cluster_id})"
)
handle_package(no_rebuild)
deployment = get_deployment_config(deployment_file).get_environment(
environment)
_verify_deployment(deployment, environment, deployment_file)
found_jobs = [j for j in deployment["jobs"] if j["name"] == job]
if not found_jobs:
raise RuntimeError(
f"Job {job} was not found in environment jobs, please check the deployment file"
)
job_payload = found_jobs[0]
entrypoint_file = job_payload.get("spark_python_task").get("python_file")
if not entrypoint_file:
raise FileNotFoundError(
f"No entrypoint file provided in job {job}. "
f"Please add one under spark_python_task.python_file section")
cluster_service = ClusterService(api_client)
dbx_echo("Preparing interactive cluster to accept jobs")
awake_cluster(cluster_service, cluster_id)
v1_client = ApiV1Client(api_client)
context_id = get_context_id(v1_client, cluster_id, "python")
file_uploader = FileUploader(api_client)
with mlflow.start_run() as execution_run:
artifact_base_uri = execution_run.info.artifact_uri
localized_base_path = artifact_base_uri.replace("dbfs:/", "/dbfs/")
requirements_fp = pathlib.Path(requirements_file)
if requirements_fp.exists():
file_uploader.upload_file(requirements_fp)
localized_requirements_path = f"{localized_base_path}/{str(requirements_fp)}"
installation_command = f"%pip install -U -r {localized_requirements_path}"
dbx_echo("Installing provided requirements")
execute_command(v1_client,
cluster_id,
context_id,
installation_command,
verbose=False)
dbx_echo("Provided requirements installed")
else:
dbx_echo(
f"Requirements file {requirements_fp} is not provided" +
", following the execution without any additional packages")
if not no_package:
package_file = get_package_file()
if not package_file:
raise FileNotFoundError(
"Project package was not found. Please check that /dist directory exists."
)
file_uploader.upload_file(package_file)
localized_package_path = f"{localized_base_path}/{str(package_file.as_posix())}"
dbx_echo("Installing package")
installation_command = f"%pip install --force-reinstall {localized_package_path}"
execute_command(v1_client,
cluster_id,
context_id,
installation_command,
verbose=False)
dbx_echo("Package installation finished")
else:
dbx_echo(
"Package was disabled via --no-package, only the code from entrypoint will be used"
)
tags = {"dbx_action_type": "execute", "dbx_environment": environment}
mlflow.set_tags(tags)
dbx_echo("Processing parameters")
task_props: List[Any] = job_payload.get("spark_python_task").get(
"parameters", [])
if task_props:
def adjustment_callback(p: Any):
return _adjust_path(p, artifact_base_uri, file_uploader)
_walk_content(adjustment_callback, task_props)
task_props = ["python"] + task_props
parameters_command = f"""
import sys
sys.argv = {task_props}
"""
execute_command(v1_client,
cluster_id,
context_id,
parameters_command,
verbose=False)
dbx_echo("Processing parameters - done")
dbx_echo("Starting entrypoint file execution")
execute_command(v1_client, cluster_id, context_id,
pathlib.Path(entrypoint_file).read_text())
dbx_echo("Command execution finished")
def execute(
environment: str,
cluster_id: str,
cluster_name: str,
job: str,
deployment_file: str,
requirements_file: str,
no_rebuild: bool,
):
api_client = prepare_environment(environment)
cluster_id = _preprocess_cluster_args(api_client, cluster_name, cluster_id)
dbx_echo(
f"Executing job: {job} with environment: {environment} on cluster: {cluster_id}"
)
handle_package(no_rebuild)
deployment = DeploymentFile(deployment_file).get_environment(environment)
if not deployment:
raise NameError(
f"Environment {environment} is not provided in deployment file {deployment_file}"
+ " please add this environment first"
)
env_jobs = deployment.get("jobs")
if not env_jobs:
raise RuntimeError(
f"No jobs section found in environment {environment}, please check the deployment file"
)
found_jobs = [j for j in deployment["jobs"] if j["name"] == job]
if not found_jobs:
raise RuntimeError(
f"Job {job} was not found in environment jobs, please check the deployment file"
)
job_payload = found_jobs[0]
entrypoint_file = job_payload.get("spark_python_task").get("python_file")
if not entrypoint_file:
raise FileNotFoundError(
f"No entrypoint file provided in job {job}. "
f"Please add one under spark_python_task.python_file section"
)
cluster_service = ClusterService(api_client)
dbx_echo("Preparing interactive cluster to accept jobs")
awake_cluster(cluster_service, cluster_id)
v1_client = ApiV1Client(api_client)
context_id = get_context_id(v1_client, cluster_id, "python")
file_uploader = FileUploader(api_client)
with mlflow.start_run() as execution_run:
artifact_base_uri = execution_run.info.artifact_uri
localized_base_path = artifact_base_uri.replace("dbfs:/", "/dbfs/")
requirements_fp = pathlib.Path(requirements_file)
if requirements_fp.exists():
file_uploader.upload_file(requirements_fp)
localized_requirements_path = (
f"{localized_base_path}/{str(requirements_fp)}"
)
installation_command = f"%pip install -U -r {localized_requirements_path}"
dbx_echo("Installing provided requirements")
execute_command(
v1_client, cluster_id, context_id, installation_command, verbose=False
)
dbx_echo("Provided requirements installed")
else:
dbx_echo(
f"Requirements file {requirements_fp} is not provided"
+ ", following the execution without any additional packages"
)
project_package_path = list(pathlib.Path(".").rglob("dist/*.whl"))
# Make sure we always take the newest package (i.e. sort by time)
project_package_path.sort(key=os.path.getctime, reverse=True)
project_package_path = project_package_path[0]
file_uploader.upload_file(project_package_path)
localized_package_path = (
f"{localized_base_path}/{str(project_package_path.as_posix())}"
)
dbx_echo("Installing package")
installation_command = f"%pip install {localized_package_path} --force-reinstall"
execute_command(
v1_client, cluster_id, context_id, installation_command, verbose=False
)
dbx_echo("Package installation finished")
tags = {"dbx_action_type": "execute", "dbx_environment": environment}
mlflow.set_tags(tags)
dbx_echo("Starting entrypoint file execution")
execute_command(
v1_client, cluster_id, context_id, pathlib.Path(entrypoint_file).read_text()
)
dbx_echo("Command execution finished")
def deploy(
deployment_file: str,
jobs: str,
requirements_file: str,
tags: List[str],
environment: str,
no_rebuild: bool,
no_package: bool,
files_only: bool,
write_specs_to_file: Optional[str],
branch_name: Optional[str],
):
dbx_echo(f"Starting new deployment for environment {environment}")
api_client = prepare_environment(environment)
additional_tags = parse_multiple(tags)
handle_package(no_rebuild)
package_file = get_package_file()
if not branch_name:
branch_name = get_current_branch_name()
_verify_deployment_file(deployment_file)
deployment_file_config = get_deployment_config(deployment_file)
deployment = deployment_file_config.get_environment(environment)
if not deployment:
raise NameError(f"""
Requested environment {environment} is non-existent in the deployment file {deployment_file}.
Available environments are: {deployment_file_config.get_all_environment_names()}
""")
if jobs:
requested_jobs = jobs.split(",")
else:
requested_jobs = None
requirements_payload = _preprocess_requirements(requirements_file)
_preprocess_deployment(deployment, requested_jobs)
_file_uploader = FileUploader(api_client)
with mlflow.start_run() as deployment_run:
artifact_base_uri = deployment_run.info.artifact_uri
if no_package:
dbx_echo(
"No package definition will be added into job description")
package_requirement = []
else:
if package_file:
package_requirement = [{"whl": str(package_file)}]
else:
dbx_echo(
"Package file was not found! Please check your /dist/ folder"
)
package_requirement = []
_adjust_job_definitions(deployment["jobs"], artifact_base_uri,
requirements_payload, package_requirement,
_file_uploader, api_client)
if not files_only:
dbx_echo("Updating job definitions")
deployment_data = _create_jobs(deployment["jobs"], api_client)
_log_dbx_file(deployment_data, "deployments.json")
for job_spec in deployment.get("jobs"):
permissions = job_spec.get("permissions")
if permissions:
job_name = job_spec.get("name")
dbx_echo(
f"Permission settings are provided for job {job_name}, setting it up"
)
job_id = deployment_data.get(job_spec.get("name"))
api_client.perform_query("PUT",
f"/permissions/jobs/{job_id}",
data=permissions)
dbx_echo(
f"Permission settings were successfully set for job {job_name}"
)
dbx_echo("Updating job definitions - done")
deployment_tags = {
"dbx_action_type": "deploy",
"dbx_environment": environment,
"dbx_status": "SUCCESS",
}
deployment_spec = {environment: deployment}
deployment_tags.update(additional_tags)
if branch_name:
deployment_tags["dbx_branch_name"] = branch_name
if files_only:
deployment_tags["dbx_deploy_type"] = "files_only"
_log_dbx_file(deployment_spec, "deployment-result.json")
mlflow.set_tags(deployment_tags)
dbx_echo(
f"Deployment for environment {environment} finished successfully")
if write_specs_to_file:
dbx_echo("Writing final job specifications into file")
specs_file = pathlib.Path(write_specs_to_file)
if specs_file.exists():
specs_file.unlink()
specs_file.write_text(json.dumps(deployment_spec, indent=4))
def deploy(
deployment_file: str,
jobs: str,
requirements_file: str,
tags: List[str],
environment: str,
no_rebuild: bool,
no_package: bool,
):
dbx_echo(f"Starting new deployment for environment {environment}")
api_client = prepare_environment(environment)
additional_tags = parse_multiple(tags)
branch_name = get_current_branch_name()
handle_package(no_rebuild)
package_file = get_package_file()
_verify_deployment_file(deployment_file)
deployment_file_controller = DeploymentFile(deployment_file)
deployment = deployment_file_controller.get_environment(environment)
if not deployment:
raise NameError(f"""
Requested environment {environment} is non-existent in the deployment file {deployment_file}.
Available environments are: {deployment_file_controller.get_all_environment_names()}
""")
if jobs:
requested_jobs = jobs.split(",")
else:
requested_jobs = None
requirements_payload = _preprocess_requirements(requirements_file)
_preprocess_deployment(deployment, requested_jobs)
_file_uploader = FileUploader(api_client)
with mlflow.start_run() as deployment_run:
artifact_base_uri = deployment_run.info.artifact_uri
if no_package:
dbx_echo(
"No package definition will be added into job description")
package_requirement = []
else:
if package_file:
package_requirement = [{"whl": str(package_file)}]
else:
dbx_echo(
"Package file was not found! Please check your /dist/ folder"
)
package_requirement = []
_adjust_job_definitions(
deployment["jobs"],
artifact_base_uri,
requirements_payload,
package_requirement,
_file_uploader,
)
deployment_data = _create_jobs(deployment["jobs"], api_client)
_log_deployments(deployment_data)
deployment_tags = {
"dbx_action_type": "deploy",
"dbx_environment": environment,
"dbx_status": "SUCCESS",
}
deployment_tags.update(additional_tags)
if branch_name:
deployment_tags["dbx_branch_name"] = branch_name
mlflow.set_tags(deployment_tags)
dbx_echo(
f"Deployment for environment {environment} finished successfully")