Before: SPARK_EXECUTOR_DATA_DIR, SPARK_EXECUTOR_JOBS_DIR, and
YARN_RESOURCE_MANAGER_URL were each read directly via os.environ.get()
inside the module that used them. Log level was hardcoded DEBUG in
common/logging.py. There was no single file showing what the full set
of env vars the app reads is.
After: common/config.py defines a single Settings dataclass that
reads all env vars at import time and exposes them as fields on a
module-level singleton. App code uses "from common.config import
settings; settings.data_dir" etc. New SPARK_EXECUTOR_LOG_LEVEL env
var controls stderr + info file verbosity (debug file always gets full
DEBUG).
Improvements:
- One file lists every env var the app reads (was: grep the codebase)
- Tests can monkeypatch fields on the settings singleton directly
instead of monkeypatching the env + reloading
- Adding a new env var means adding one field in config.py, not
editing 3+ call sites
- settings.reload() method for tests that prefer env-var style
Out of scope (kept where they are):
- GUNICORN_* env vars live in gunicorn.conf.py (gunicorn concept)
- PYTHONUNBUFFERED in Dockerfile (Python runtime flag)
- SPARK_SUBMIT_OPTS not in config (JVM flag, not Python)
Test changes:
- test_job_writer.py: settings.jobs_dir instead of monkeypatching
SPARK_EXECUTOR_JOBS_DIR
- test_yarn_client.py: settings.yarn_resource_manager_url instead of
monkeypatching YARN_RESOURCE_MANAGER_URL
- test_generate_tool.py: same as job_writer
- Each test file gets an autouse fixture that snapshots+restores
settings so one test mutation does not leak into the next
116/116 still pass. Live verified: SPARK_EXECUTOR_LOG_LEVEL=INFO
suppresses DEBUG loguru output as expected.
151 lines
5.1 KiB
Python
151 lines
5.1 KiB
Python
# coding=utf-8
|
|
from unittest.mock import patch
|
|
|
|
import httpx
|
|
import pytest
|
|
|
|
from common import config
|
|
from spark_executor.core.yarn_client import (
|
|
YarnConfigError,
|
|
YarnError,
|
|
get_application_logs,
|
|
get_application_status,
|
|
kill_application,
|
|
)
|
|
|
|
|
|
RM = "http://rm:8088"
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _restore_settings():
|
|
"""Each test gets a clean copy of `settings` so env-var-style overrides
|
|
in one test don't leak into the next."""
|
|
snapshot = config.Settings(
|
|
data_dir=config.settings.data_dir,
|
|
jobs_dir=config.settings.jobs_dir,
|
|
yarn_resource_manager_url=config.settings.yarn_resource_manager_url,
|
|
log_level=config.settings.log_level,
|
|
)
|
|
yield
|
|
config.settings.data_dir = snapshot.data_dir
|
|
config.settings.jobs_dir = snapshot.jobs_dir
|
|
config.settings.yarn_resource_manager_url = snapshot.yarn_resource_manager_url
|
|
config.settings.log_level = snapshot.log_level
|
|
|
|
|
|
def _resp(status: int, *, json_data=None, text: str | None = None) -> httpx.Response:
|
|
if json_data is not None:
|
|
return httpx.Response(status, json=json_data)
|
|
return httpx.Response(status, text=text or "")
|
|
|
|
|
|
# --- get_application_status ---
|
|
|
|
def test_status_parses_app_state():
|
|
fake = _resp(200, json_data={"app": {"id": "application_1", "state": "RUNNING"}})
|
|
with patch("spark_executor.core.yarn_client.httpx.request", return_value=fake) as m:
|
|
state, raw = get_application_status("application_1", RM)
|
|
assert state == "RUNNING"
|
|
assert "RUNNING" in raw
|
|
args = m.call_args.args
|
|
assert args == ("GET", f"{RM}/ws/v1/cluster/apps/application_1")
|
|
|
|
|
|
def test_status_raises_on_404():
|
|
with patch("spark_executor.core.yarn_client.httpx.request", return_value=_resp(404)):
|
|
with pytest.raises(YarnError, match="not found"):
|
|
get_application_status("application_x", RM)
|
|
|
|
|
|
def test_status_raises_on_5xx():
|
|
with patch(
|
|
"spark_executor.core.yarn_client.httpx.request",
|
|
return_value=_resp(503, text="upstream down"),
|
|
):
|
|
with pytest.raises(YarnError, match="503"):
|
|
get_application_status("application_1", RM)
|
|
|
|
|
|
def test_status_raises_when_state_field_missing():
|
|
fake = _resp(200, json_data={"app": {"id": "application_1"}})
|
|
with patch("spark_executor.core.yarn_client.httpx.request", return_value=fake):
|
|
with pytest.raises(YarnError, match="Could not parse YARN state"):
|
|
get_application_status("application_1", RM)
|
|
|
|
|
|
def test_status_requires_rm_url():
|
|
config.settings.yarn_resource_manager_url = None
|
|
with pytest.raises(YarnConfigError):
|
|
get_application_status("application_1", None)
|
|
|
|
|
|
def test_status_falls_back_to_settings_yarn_rm_url():
|
|
config.settings.yarn_resource_manager_url = "http://env-rm:8088"
|
|
fake = _resp(200, json_data={"app": {"state": "FINISHED"}})
|
|
with patch("spark_executor.core.yarn_client.httpx.request", return_value=fake) as m:
|
|
state, _ = get_application_status("application_1", None)
|
|
assert state == "FINISHED"
|
|
assert "env-rm:8088" in m.call_args.args[1]
|
|
|
|
|
|
def test_status_rejects_non_http_url():
|
|
with pytest.raises(YarnConfigError, match="must start with"):
|
|
get_application_status("application_1", "rm:8088")
|
|
|
|
|
|
# --- get_application_logs ---
|
|
|
|
def test_logs_returns_text():
|
|
fake = _resp(200, text="log line 1\nlog line 2\n")
|
|
with patch("spark_executor.core.yarn_client.httpx.request", return_value=fake) as m:
|
|
out = get_application_logs("application_1", RM)
|
|
assert out == "log line 1\nlog line 2\n"
|
|
assert m.call_args.args == ("GET", f"{RM}/ws/v1/cluster/apps/application_1/aggregated-logs")
|
|
|
|
|
|
def test_logs_raises_on_404_with_explanation():
|
|
with patch("spark_executor.core.yarn_client.httpx.request", return_value=_resp(404)):
|
|
with pytest.raises(YarnError, match="log-aggregation-enable"):
|
|
get_application_logs("application_1", RM)
|
|
|
|
|
|
def test_logs_raises_on_5xx():
|
|
with patch(
|
|
"spark_executor.core.yarn_client.httpx.request",
|
|
return_value=_resp(500, text="boom"),
|
|
):
|
|
with pytest.raises(YarnError):
|
|
get_application_logs("application_1", RM)
|
|
|
|
|
|
# --- kill_application ---
|
|
|
|
def test_kill_sends_put_with_killed_state():
|
|
fake = _resp(200, json_data={"app": {"state": "KILLED"}})
|
|
with patch("spark_executor.core.yarn_client.httpx.request", return_value=fake) as m:
|
|
kill_application("application_1", RM)
|
|
args = m.call_args.args
|
|
assert args == ("PUT", f"{RM}/ws/v1/cluster/apps/application_1/state")
|
|
assert m.call_args.kwargs["json"] == {"state": "KILLED"}
|
|
|
|
|
|
def test_kill_raises_on_5xx():
|
|
with patch(
|
|
"spark_executor.core.yarn_client.httpx.request",
|
|
return_value=_resp(403, text="forbidden"),
|
|
):
|
|
with pytest.raises(YarnError, match="403"):
|
|
kill_application("application_1", RM)
|
|
|
|
|
|
# --- connection errors ---
|
|
|
|
def test_status_wraps_httpx_errors_as_yarn_error():
|
|
with patch(
|
|
"spark_executor.core.yarn_client.httpx.request",
|
|
side_effect=httpx.ConnectError("connection refused"),
|
|
):
|
|
with pytest.raises(YarnError, match="connection failed"):
|
|
get_application_status("application_1", RM)
|