[SIMPL-30451] Add distributed-execution service with guide and reference implementations

Canonical location for documentation, example workflows and reference service implementations covering distributed execution patterns. Covers AC1-AC4: execution-target selection, decision support, readiness checks and code-level linkage. Tightly coupled jobs and the loosely coupled subprocess transport are verified by the test suite; the Kubernetes pipes transport is implemented but not yet cluster-run and is marked as such in the guide.

Changelog: added
This commit is contained in:
ILay
2026-08-26 18:07:06 +02:00
commit 43dbb81a95
32 changed files with 4071 additions and 0 deletions

View File

@@ -0,0 +1,59 @@
"""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 never fans out beyond the run worker.
assert len(summary["contributing_hosts"]) == 1
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>"