Skip to content

Implement EMR job cancelling #1075

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
feast-ci-bot merged 1 commit into from
Oct 20, 2020
Merged

Implement EMR job cancelling #1075

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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: 2 additions & 1 deletion sdk/python/feast/pyspark/launchers/aws/emr.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@
SUCCEEDED_STEP_STATES,
TERMINAL_STEP_STATES,
EmrJobRef,
_cancel_job,
_get_job_state,
_historical_retrieval_step,
_load_new_cluster_template,
Expand Down Expand Up @@ -63,7 +64,7 @@ def get_status(self) -> SparkJobStatus:
raise Exception("Invalid EMR state")

def cancel(self):
raise NotImplementedError
_cancel_job(self._emr_client, self._job_ref)


class EmrRetrievalJob(EmrJobMixin, RetrievalJob):
Expand Down
32 changes: 12 additions & 20 deletions sdk/python/feast/pyspark/launchers/aws/emr_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -240,6 +240,9 @@ def _get_stream_to_online_job(emr_client, table_name: str) -> List[JobInfo]:


class EmrJobRef(NamedTuple):
""" EMR job reference. step_id can be None when using on-demand clusters, in that case each
cluster has only one step """

cluster_id: str
step_id: Optional[str]

Expand Down Expand Up @@ -304,28 +307,17 @@ def _wait_for_step_state(
)


def _cancel_job(emr_client, job_type: str, table_name: str):
"""
Cancel a EMR job.
"""
jobs = list_jobs(
emr_client, job_type=job_type, table_name=table_name, active_only=True
)

for job in jobs:
emr_client.cancel_steps(ClusterId=job.cluster_id, StepIds=[job.step_id])

for job in jobs:
_wait_for_job_state(
emr_client, EmrJobRef(job.cluster_id, job.step_id), TERMINAL_STEP_STATES, 90
)
def _cancel_job(emr_client, job: EmrJobRef):
if job.step_id is None:
step_id = _get_first_step_id(emr_client, job.cluster_id)
else:
step_id = job.step_id

emr_client.cancel_steps(ClusterId=job.cluster_id, StepIds=[step_id])

def stop_stream_to_online(emr_client, table_name: str):
"""
Stop offline-to-online ingestion job for the table.
"""
_cancel_job(emr_client, STREAM_TO_ONLINE_JOB_TYPE, table_name)
_wait_for_job_state(
emr_client, EmrJobRef(job.cluster_id, step_id), TERMINAL_STEP_STATES, 180
)


def _upload_dataframe(s3prefix: str, df: pandas.DataFrame) -> str:
Expand Down