Skip to content

Add support for associating custom tags to job runs submitted via EmrContainerOperator #23769

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
potiuk merged 4 commits into from
May 22, 2022
Merged

Add support for associating custom tags to job runs submitted via EmrContainerOperator #23769

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
9dcc3b1
Added support for associating custom tags to job runs submited via E…
May 18, 2022
f437fad
Added support for associating custom tags to job runs submited via E…
May 18, 2022
df76231
add the tags parameter in the TestEMRContainerOperator unit test case
skadyan May 22, 2022
b444046
Merge branch 'master' of https://github.com/skadyan/airflow
skadyan May 22, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions airflow/providers/amazon/aws/hooks/emr.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -133,6 +133,7 @@ def submit_job(
job_driver: dict,
configuration_overrides: Optional[dict] = None,
client_request_token: Optional[str] = None,
tags: Optional[dict] = None,
) -> str:
"""
Submit a job to the EMR Containers API and return the job ID.
Expand All @@ -148,6 +149,7 @@ def submit_job(
specifically either application configuration or monitoring configuration.
:param client_request_token: The client idempotency token of the job run request.
Use this if you want to specify a unique ID to prevent two jobs from getting started.
:param tags: The tags assigned to job runs.
:return: Job ID
"""
params = {
Expand All @@ -157,6 +159,7 @@ def submit_job(
"releaseLabel": release_label,
"jobDriver": job_driver,
"configurationOverrides": configuration_overrides or {},
"tags": tags or {},
}
if client_request_token:
params["clientToken"] = client_request_token
Expand Down
5 changes: 5 additions & 0 deletions airflow/providers/amazon/aws/operators/emr.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,6 +136,8 @@ class EmrContainerOperator(BaseOperator):
:param poll_interval: Time (in seconds) to wait between two consecutive calls to check query status on EMR
:param max_tries: Maximum number of times to wait for the job run to finish.
Defaults to None, which will poll until the job is *not* in a pending, submitted, or running state.
:param tags: The tags assigned to job runs.
Defaults to None
"""

template_fields: Sequence[str] = (
Expand All @@ -160,6 +162,7 @@ def __init__(
aws_conn_id: str = "aws_default",
poll_interval: int = 30,
max_tries: Optional[int] = None,
tags: Optional[dict] = None,
**kwargs: Any,
) -> None:
super().__init__(**kwargs)
Expand All @@ -173,6 +176,7 @@ def __init__(
self.client_request_token = client_request_token or str(uuid4())
self.poll_interval = poll_interval
self.max_tries = max_tries
self.tags = tags
self.job_id: Optional[str] = None

@cached_property
Expand All @@ -192,6 +196,7 @@ def execute(self, context: 'Context') -> Optional[str]:
self.job_driver,
self.configuration_overrides,
self.client_request_token,
self.tags,
)
query_status = self.hook.poll_query_status(self.job_id, self.max_tries, self.poll_interval)

Expand Down