Skip to content

Extract OTEL span set attrs logic in one place in the scheduler #43787

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
dstandish merged 1 commit into from
Nov 7, 2024
Merged

Extract OTEL span set attrs logic in one place in the scheduler #43787

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
59 changes: 30 additions & 29 deletions airflow/jobs/scheduler_job_runner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -804,35 +804,7 @@ def process_executor_events(
)

with Trace.start_span_from_taskinstance(ti=ti) as span:
span.set_attribute("category", "scheduler")
span.set_attribute("task_id", ti.task_id)
span.set_attribute("dag_id", ti.dag_id)
span.set_attribute("state", ti.state)
if ti.state == TaskInstanceState.FAILED:
span.set_attribute("error", True)
span.set_attribute("start_date", str(ti.start_date))
span.set_attribute("end_date", str(ti.end_date))
span.set_attribute("duration", ti.duration)
span.set_attribute("executor_config", str(ti.executor_config))
span.set_attribute("execution_date", str(ti.execution_date))
span.set_attribute("hostname", ti.hostname)
span.set_attribute("log_url", ti.log_url)
span.set_attribute("operator", str(ti.operator))
span.set_attribute("try_number", ti.try_number)
span.set_attribute("executor_state", state)
span.set_attribute("pool", ti.pool)
span.set_attribute("queue", ti.queue)
span.set_attribute("priority_weight", ti.priority_weight)
span.set_attribute("queued_dttm", str(ti.queued_dttm))
span.set_attribute("queued_by_job_id", ti.queued_by_job_id)
span.set_attribute("pid", ti.pid)
if span.is_recording():
if ti.queued_dttm:
span.add_event(name="queued", timestamp=datetime_to_nano(ti.queued_dttm))
if ti.start_date:
span.add_event(name="started", timestamp=datetime_to_nano(ti.start_date))
if ti.end_date:
span.add_event(name="ended", timestamp=datetime_to_nano(ti.end_date))
cls._set_span_attrs__process_executor_events(span, state, ti)
if conf.has_option("traces", "otel_task_log_event") and conf.getboolean(
"traces", "otel_task_log_event"
):
Expand Down Expand Up @@ -916,6 +888,35 @@ def process_executor_events(

return len(event_buffer)

@classmethod
def _set_span_attrs__process_executor_events(cls, span, state, ti):
span.set_attribute("category", "scheduler")
span.set_attribute("task_id", ti.task_id)
span.set_attribute("dag_id", ti.dag_id)
span.set_attribute("state", ti.state)
if ti.state == TaskInstanceState.FAILED:
span.set_attribute("error", True)
span.set_attribute("start_date", str(ti.start_date))
span.set_attribute("end_date", str(ti.end_date))
span.set_attribute("duration", ti.duration)
span.set_attribute("executor_config", str(ti.executor_config))
span.set_attribute("execution_date", str(ti.execution_date))
span.set_attribute("hostname", ti.hostname)
span.set_attribute("log_url", ti.log_url)
span.set_attribute("operator", str(ti.operator))
span.set_attribute("try_number", ti.try_number)
span.set_attribute("executor_state", state)
span.set_attribute("pool", ti.pool)
span.set_attribute("queue", ti.queue)
span.set_attribute("priority_weight", ti.priority_weight)
span.set_attribute("queued_dttm", str(ti.queued_dttm))
span.set_attribute("queued_by_job_id", ti.queued_by_job_id)
span.set_attribute("pid", ti.pid)
if span.is_recording():
span.add_event(name="queued", timestamp=datetime_to_nano(ti.queued_dttm))
span.add_event(name="started", timestamp=datetime_to_nano(ti.start_date))
span.add_event(name="ended", timestamp=datetime_to_nano(ti.end_date))

def _execute(self) -> int | None:
from airflow.dag_processing.manager import DagFileProcessorAgent

Expand Down
6 changes: 4 additions & 2 deletions airflow/utils/dates.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,8 @@
}


def datetime_to_nano(datetime) -> int:
def datetime_to_nano(datetime) -> int | None:
"""Convert datetime to nanoseconds."""
return int(datetime.timestamp() * 1000000000)
if datetime:
return int(datetime.timestamp() * 1000000000)
return None