The function had hardcoded --master / --deploy-mode / --queue /
--executor-memory / --executor-cores / --num-executors plus a
`spark_conf` dict for --conf, with no way to pass other flags like
--jars, --py-files, --files, --driver-memory, --name, etc.
Add `extra_args: dict[str, str] | None = None` that emits `--{key}
{value}` pairs, placed after the --conf loop and before the script
path. Default None preserves the existing cmd shape exactly.
Structured (dict) instead of raw list[str] so LLM agents writing
tool-call payloads can't accidentally pack flag+value into a single
string. Key order in the dict is preserved.
Tests: 4 cases — None default, single pair, multiple pairs in order,
no collision with spark_conf. uv run pytest -> 175 passed.
63 lines
2.0 KiB
Python
63 lines
2.0 KiB
Python
# coding=utf-8
|
|
"""
|
|
@Time :2026/6/24
|
|
@Author :tao.chen
|
|
"""
|
|
import subprocess
|
|
|
|
from common.config import settings
|
|
from common.logging import logger
|
|
|
|
|
|
class SparkSubmitError(Exception):
|
|
"""Raised when spark-submit exits with a non-zero return code."""
|
|
|
|
|
|
def build_spark_submit_command(
|
|
*,
|
|
master: str,
|
|
deploy_mode: str,
|
|
script_path: str,
|
|
queue: str,
|
|
executor_memory: str,
|
|
executor_cores: int,
|
|
num_executors: int,
|
|
spark_conf: dict[str, str] | None = None,
|
|
extra_args: dict[str, str] | None = None,
|
|
) -> list[str]:
|
|
# cmd[0] is the Spark CLI binary name, configurable via
|
|
# SPARK_EXECUTOR_SPARK_SUBMIT_BIN. Defaults to 'spark-submit' but
|
|
# can be 'spark2-submit' (mixed-version hosts), 'pyspark' (PySpark
|
|
# entrypoint), or a path to a wrapper script.
|
|
cmd = [
|
|
settings.spark_submit_bin,
|
|
"--master", master,
|
|
"--deploy-mode", deploy_mode,
|
|
"--queue", queue,
|
|
"--executor-memory", executor_memory,
|
|
"--executor-cores", str(executor_cores),
|
|
"--num-executors", str(num_executors),
|
|
]
|
|
for key, value in (spark_conf or {}).items():
|
|
cmd.extend(["--conf", f"{key}={value}"])
|
|
for key, value in (extra_args or {}).items():
|
|
cmd.extend([f"--{key}", str(value)])
|
|
cmd.append(script_path)
|
|
logger.debug(f"build_spark_submit_command -> {cmd}")
|
|
return cmd
|
|
|
|
|
|
def run_spark_submit(cmd: list[str]) -> "subprocess.CompletedProcess[str]":
|
|
logger.debug(f"run_spark_submit exec: {cmd}")
|
|
result = subprocess.run(cmd, capture_output=True, text=True, errors="replace")
|
|
logger.debug(
|
|
f"run_spark_submit done rc={result.returncode} "
|
|
f"stdout_len={len(result.stdout)} stderr_len={len(result.stderr)}"
|
|
)
|
|
if result.returncode != 0:
|
|
logger.error(f"spark-submit failed (rc={result.returncode}): {result.stderr[:500]}")
|
|
raise SparkSubmitError(
|
|
f"spark-submit failed (rc={result.returncode}): {result.stderr}"
|
|
)
|
|
return result
|