JoelEmmanuelCloud commented on code in PR #76410:
URL: https://github.com/apache/airflow/pull/76410#discussion_r4647903013


##########
airflow-core/src/airflow/jobs/job.py:
##########
@@ -57,6 +57,32 @@ def __str__(self) -> str:
         return self.value
 
 
+# Executors don't run as their own process the way 
SchedulerJob/TriggererJob/DagProcessorJob do, so
+# there is no ExecutorJobRunner to own this constant. The scheduler writes 
rows with this job_type
+# directly when it records an executor's health, reusing the Job table and 
JobState exactly as the
+# other components do instead of introducing a parallel status model.
+EXECUTOR_JOB_TYPE = "ExecutorJob"

Review Comment:
   good catch. jobs check now skips ExecutorJob rows when no --job-type is 
given, same in airflowctl.



##########
airflow-core/src/airflow/api/common/airflow_health.py:
##########
@@ -120,6 +123,53 @@ def _dag_processor_instance_health(job: Job) -> dict[str, 
Any]:
     }
 
 
+@lru_cache
+def _configured_executor_names() -> dict[str, ExecutorName]:
+    """
+    Map every configured executor's health key to its ``ExecutorName``, for 
display purposes.
+
+    Cached for the same reason :func:`_configured_executor_keys` is: the 
configured executors can't
+    change while the process runs.
+    """
+    try:
+        return {repr(name): name for name in 
ExecutorLoader.get_executor_names(validate_teams=False)}
+    except Exception:
+        # A health probe must not fail on malformed executor config; the row's 
own key is still shown.
+        log.warning("Could not read the executor configuration", exc_info=True)
+        return {}
+
+
+def _executor_instance_health(job: Job) -> dict[str, Any]:
+    # job.executor_class is the internal identity key (e.g. 
":CeleryExecutor:"), not the name the user
+    # configured. Reporting the alias or module path they wrote in [core] 
executor instead is a better
+    # user experience; the key itself is only shown as a fallback, e.g. for a 
since-reconfigured executor.
+    name = _configured_executor_names().get(job.executor_class) if 
job.executor_class else None
+    return {
+        **_job_instance_health(job, "latest_executor_heartbeat"),
+        "executor": (name.alias or name.module_path) if name else 
job.executor_class,
+        "team_names": job.team_names,
+        "health_check_result": job.health_check_result,
+    }
+
+
+def _live_scheduler_job_ids() -> set[int]:
+    """Ids of the currently-alive SchedulerJob rows, used to age out a dead 
scheduler's own rows."""
+    return {job.id for job in get_jobs_health(SchedulerJobRunner.job_type) if 
job.is_alive()}
+
+
+def _live_executor_jobs(jobs: list[Job]) -> list[Job]:
+    """
+    Narrow executor rows down to live instances whose owning scheduler is also 
still alive.
+
+    A row can stay technically alive for a little while after its scheduler 
process has already
+    died (its heartbeat hasn't crossed the staleness threshold yet), so 
liveness on the row alone
+    isn't enough; cross-checking the owner avoids briefly reporting a dead 
scheduler's executor as
+    healthy.
+    """
+    live_scheduler_ids = _live_scheduler_job_ids()

Review Comment:
   get_airflow_health now computes the live scheduler ids once from the 
scheduler_jobs it already fetched, and passes that into both calls instead of 
querying again.



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to