Claude
1c9e4a321d
Hardcoding 'spark-submit' as cmd[0] in build_spark_submit_command
breaks for hosts where:
- both Spark 1.x and 2.x/3.x are installed and 'spark-submit' resolves
to the wrong one (use 'spark2-submit' or 'spark3-submit' explicitly)
- the user wants to launch via the PySpark entrypoint ('pyspark')
- a custom wrapper script sits on PATH (e.g. a credentials-injecting
'spark-submit-wrapper')
New env var SPARK_EXECUTOR_SPARK_SUBMIT_BIN. Default is 'spark-submit'
(preserves the current behavior for everyone). Override in .env /
docker-compose.yml to change.
common/config.py:
- new Settings.spark_submit_bin field
- env-var resolution in from_env() with default 'spark-submit'
- included in reload() so tests work
spark_executor/core/spark_submit.py:
- cmd[0] reads settings.spark_submit_bin (was hardcoded 'spark-submit')
.env.example: new section with the override and example values.
docker-compose.yml: forwards the var with the standard 'spark-submit'
default.
Tests: 2 new (settings.spark_submit_bin='spark2-submit', ='pyspark')
plus existing tests updated to use the settings-restore fixture so
mutations don't leak between tests.
165/163 still pass.
138 lines
4.4 KiB
Python
138 lines
4.4 KiB
Python
# coding=utf-8
|
|
from unittest.mock import MagicMock, patch
|
|
|
|
import pytest
|
|
|
|
from common import config
|
|
from spark_executor.core.spark_submit import (
|
|
SparkSubmitError,
|
|
build_spark_submit_command,
|
|
run_spark_submit,
|
|
)
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _restore_settings():
|
|
snapshot = config.Settings(
|
|
data_dir=config.settings.data_dir,
|
|
jobs_dir=config.settings.jobs_dir,
|
|
log_dir=config.settings.log_dir,
|
|
yarn_resource_manager_url=config.settings.yarn_resource_manager_url,
|
|
log_level=config.settings.log_level,
|
|
spark_submit_bin=config.settings.spark_submit_bin,
|
|
)
|
|
yield
|
|
config.settings.data_dir = snapshot.data_dir
|
|
config.settings.jobs_dir = snapshot.jobs_dir
|
|
config.settings.log_dir = snapshot.log_dir
|
|
config.settings.yarn_resource_manager_url = snapshot.yarn_resource_manager_url
|
|
config.settings.log_level = snapshot.log_level
|
|
config.settings.spark_submit_bin = snapshot.spark_submit_bin
|
|
|
|
|
|
def test_build_command_uses_provided_master_and_deploy_mode():
|
|
cmd = build_spark_submit_command(
|
|
master="yarn",
|
|
deploy_mode="cluster",
|
|
script_path="/tmp/jobs/job_001.py",
|
|
queue="default",
|
|
executor_memory="4G",
|
|
executor_cores=2,
|
|
num_executors=2,
|
|
)
|
|
assert cmd[:2] == ["spark-submit", "--master"] # default binary
|
|
assert "yarn" in cmd
|
|
assert "cluster" in cmd
|
|
assert "--queue" in cmd and "default" in cmd
|
|
assert "--executor-memory" in cmd and "4G" in cmd
|
|
assert "--executor-cores" in cmd and "2" in cmd
|
|
assert "--num-executors" in cmd and "2" in cmd
|
|
assert cmd[-1] == "/tmp/jobs/job_001.py"
|
|
|
|
|
|
def test_build_command_supports_standalone_master():
|
|
cmd = build_spark_submit_command(
|
|
master="spark://master:7077",
|
|
deploy_mode="client",
|
|
script_path="/tmp/j.py",
|
|
queue="default",
|
|
executor_memory="1G",
|
|
executor_cores=1,
|
|
num_executors=1,
|
|
)
|
|
assert "spark://master:7077" in cmd
|
|
assert "client" in cmd
|
|
|
|
|
|
def test_build_command_appends_spark_conf_entries():
|
|
cmd = build_spark_submit_command(
|
|
master="yarn",
|
|
deploy_mode="cluster",
|
|
script_path="/tmp/j.py",
|
|
queue="default",
|
|
executor_memory="4G",
|
|
executor_cores=2,
|
|
num_executors=2,
|
|
spark_conf={"spark.sql.shuffle.partitions": "200", "spark.executor.memoryOverhead": "1G"},
|
|
)
|
|
# every k=v is emitted as --conf k=v
|
|
assert "--conf" in cmd
|
|
assert "spark.sql.shuffle.partitions=200" in cmd
|
|
assert "spark.executor.memoryOverhead=1G" in cmd
|
|
# script_path is still last
|
|
assert cmd[-1] == "/tmp/j.py"
|
|
|
|
|
|
def test_build_command_uses_settings_spark_submit_bin():
|
|
"""The Spark CLI binary is env-configurable via settings.spark_submit_bin
|
|
(env var SPARK_EXECUTOR_SPARK_SUBMIT_BIN). Default is 'spark-submit';
|
|
override to 'spark2-submit', 'pyspark', etc. for mixed-version hosts."""
|
|
config.settings.spark_submit_bin = "spark2-submit"
|
|
cmd = build_spark_submit_command(
|
|
master="yarn",
|
|
deploy_mode="cluster",
|
|
script_path="/tmp/j.py",
|
|
queue="default",
|
|
executor_memory="4G",
|
|
executor_cores=2,
|
|
num_executors=2,
|
|
)
|
|
assert cmd[0] == "spark2-submit"
|
|
|
|
|
|
def test_build_command_supports_pyspark_binary():
|
|
config.settings.spark_submit_bin = "pyspark"
|
|
cmd = build_spark_submit_command(
|
|
master="yarn",
|
|
deploy_mode="cluster",
|
|
script_path="/tmp/j.py",
|
|
queue="default",
|
|
executor_memory="4G",
|
|
executor_cores=2,
|
|
num_executors=2,
|
|
)
|
|
assert cmd[0] == "pyspark"
|
|
|
|
|
|
def test_run_spark_submit_returns_completed_process(monkeypatch):
|
|
fake = MagicMock()
|
|
fake.returncode = 0
|
|
fake.stderr = "Submitted application application_1\n"
|
|
with patch("spark_executor.core.spark_submit.subprocess.run", return_value=fake) as m:
|
|
result = run_spark_submit(["spark-submit", "/tmp/x.py"])
|
|
assert result is fake
|
|
m.assert_called_once()
|
|
# capture_output=True and text=True must be set
|
|
kwargs = m.call_args.kwargs
|
|
assert kwargs["capture_output"] is True
|
|
assert kwargs["text"] is True
|
|
|
|
|
|
def test_run_spark_submit_raises_on_nonzero_return():
|
|
fake = MagicMock()
|
|
fake.returncode = 1
|
|
fake.stderr = "boom"
|
|
with patch("spark_executor.core.spark_submit.subprocess.run", return_value=fake):
|
|
with pytest.raises(SparkSubmitError, match="spark-submit failed"):
|
|
run_spark_submit(["spark-submit", "/tmp/x.py"])
|