ccc2e94c2a
The reference graph processed every work unit inside a single op, so exactly one worker was ever reported regardless of executor. That made the guide's claim that k8s_job_executor yields several distinct contributing_hosts false, and left the reference implementations unable to demonstrate the executor choice at all. generate_work_units is now a DynamicOut and both graphs map over it, so one step is created per unit and the loosely coupled pattern dispatches one external workload per unit. Evidence is split into contributing_workers (host and pid, differs per process) and contributing_hosts (differs only across machines), because the previous single field could not distinguish multiprocess fan-out from no fan-out. Tests now assert the mapped step keys rather than a host count, since execute_in_process ignores executor_def and cannot prove executor behaviour on its own. Adds a Windows note: multiprocess_executor did not complete during authoring and left orphaned processes. Changelog: fixed
68 lines
2.2 KiB
Python
68 lines
2.2 KiB
Python
"""Verifies that execution-target linkage is what the guide claims it is."""
|
|
|
|
import pytest
|
|
|
|
from distributed_execution.preflight import check_env_vars, describe_pod_identity
|
|
from distributed_execution.repository import defs
|
|
from distributed_execution.tightly_coupled.jobs import (
|
|
tightly_coupled_in_process_job,
|
|
tightly_coupled_k8s_job,
|
|
tightly_coupled_local_job,
|
|
)
|
|
|
|
EXPECTED_JOBS = {
|
|
"tightly_coupled_in_process_job",
|
|
"tightly_coupled_local_job",
|
|
"tightly_coupled_k8s_job",
|
|
}
|
|
|
|
|
|
def test_repository_registers_tightly_coupled_jobs():
|
|
names = {job.name for job in defs.jobs}
|
|
assert EXPECTED_JOBS <= names
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
("job", "expected_executor"),
|
|
[
|
|
(tightly_coupled_in_process_job, "in_process"),
|
|
(tightly_coupled_local_job, "multiprocess"),
|
|
(tightly_coupled_k8s_job, "k8s_job"),
|
|
],
|
|
)
|
|
def test_each_job_declares_its_execution_target(job, expected_executor):
|
|
assert job.tags["execution_target"] == "tightly_coupled"
|
|
assert job.tags["executor"] == expected_executor
|
|
|
|
|
|
def test_in_process_job_runs_end_to_end():
|
|
result = tightly_coupled_in_process_job.execute_in_process()
|
|
|
|
assert result.success
|
|
summary = result.output_for_node("summarise_results")
|
|
assert summary["units"] == 4
|
|
assert summary["total"] == 14 # 0 + 1 + 4 + 9
|
|
# In-process execution keeps every step in the run worker's own process.
|
|
assert len(summary["contributing_workers"]) == 1
|
|
|
|
|
|
def test_work_units_fan_out_into_one_step_each():
|
|
result = tightly_coupled_in_process_job.execute_in_process()
|
|
|
|
mapped = result.output_for_node("process_work_unit")
|
|
# Without this the executor choice would be meaningless: one step cannot span pods.
|
|
assert set(mapped) == {"unit_0", "unit_1", "unit_2", "unit_3"}
|
|
|
|
|
|
def test_env_var_check_reports_missing_names():
|
|
result = check_env_vars(("DEFINITELY_NOT_SET_12345",))
|
|
|
|
assert result["passed"] is False
|
|
assert result["missing"] == ["DEFINITELY_NOT_SET_12345"]
|
|
|
|
|
|
def test_pod_identity_falls_back_outside_kubernetes(monkeypatch):
|
|
monkeypatch.delenv("DAGSTER_K8S_PIPELINE_RUN_NAMESPACE", raising=False)
|
|
|
|
assert describe_pod_identity()["namespace"] == "<not-in-kubernetes>"
|