def _collateral(
self,
project_uuid: str,
task_id: str,
pipeline: Pipeline,
run_config: Dict[str, Any],
env_variables: Dict[str, Any],
**kwargs,
):
# Get docker ids of images to use and make it so that the images
# will not be deleted in case they become outdated by an
# environment rebuild.
try:
env_uuid_docker_id_mappings = lock_environment_images_for_run(
task_id,
project_uuid,
pipeline.get_environments(),
)
except errors.ImageNotFound as e:
msg = (
"Pipeline references environments that do not exist in the"
f" project, the following environments do not exist: [{e}].\n\n"
"Please make sure all pipeline steps are assigned an"
" environment that exists in the project."
)
raise errors.ImageNotFound(msg)
# Create Celery object with the Flask context and construct the
# kwargs for the job.
celery = make_celery(current_app)
run_config["env_uuid_docker_id_mappings"] = env_uuid_docker_id_mappings
run_config["user_env_variables"] = env_variables
celery_job_kwargs = {
"pipeline_definition": pipeline.to_dict(),
"project_uuid": project_uuid,
"run_config": run_config,
}
# Start the run as a background task on Celery. Due to circular
# imports we send the task by name instead of importing the
# function directly.
res = celery.send_task(
"app.core.tasks.run_pipeline",
kwargs=celery_job_kwargs,
task_id=task_id,
)
# NOTE: this is only if a backend is configured. The task does
# not return anything. Therefore we can forget its result and
# make sure that the Celery backend releases recourses (for
# storing and transmitting results) associated to the task.
# Uncomment the line below if applicable.
res.forget()
def _transaction(
self,
project_uuid: str,
run_config: Dict[str, Any],
pipeline: Pipeline,
):
# specify the task_id beforehand to avoid race conditions
# between the task and its presence in the db
task_id = str(uuid.uuid4())
# NOTE: we are setting the status of the run ourselves without
# using the option of celery to get the status of tasks. This
# way we do not have to configure a backend (where the default
# of "rpc://" does not give the results we would want).
run = {
"uuid": task_id,
"pipeline_uuid": pipeline.properties["uuid"],
"project_uuid": project_uuid,
"status": "PENDING",
}
db.session.add(models.InteractivePipelineRun(**run))
# need to flush because otherwise the bulk insertion of pipeline
# steps will lead to foreign key errors
# https://docs.sqlalchemy.org/en/13/orm/persistence_techniques.html#bulk-operations-caveats
db.session.flush()
# Set an initial value for the status of the pipeline steps that
# will be run.
step_uuids = [s.properties["uuid"] for s in pipeline.steps]
pipeline_steps = []
for step_uuid in step_uuids:
pipeline_steps.append(
models.PipelineRunStep(
**{
"run_uuid": task_id,
"step_uuid": step_uuid,
"status": "PENDING",
}
)
)
db.session.bulk_save_objects(pipeline_steps)
run["pipeline_steps"] = pipeline_steps
try:
env_uuid_to_image = environments.lock_environment_images_for_run(
task_id,
project_uuid,
pipeline.get_environments(),
)
except self_errors.PipelineDefinitionNotValid:
msg = "Please make sure every pipeline step is assigned an environment."
raise self_errors.PipelineDefinitionNotValid(msg)
self.collateral_kwargs["project_uuid"] = project_uuid
self.collateral_kwargs["task_id"] = task_id
self.collateral_kwargs["pipeline"] = pipeline
self.collateral_kwargs["run_config"] = run_config
self.collateral_kwargs["env_variables"] = get_proj_pip_env_variables(
project_uuid, pipeline.properties["uuid"]
)
self.collateral_kwargs["env_uuid_to_image"] = env_uuid_to_image
return run
