Files
mcp-server/spark_executor/core/spark_submit.py
T
Claude 5c7dcf57cc feat: structured DEBUG/INFO logging via loguru
- common/logging.py: improve format to timestamp|LEVEL|module:func:line - message
- core/ layer: DEBUG log every subprocess invocation (cmd, rc, byte counts),
  JSON load/dump events, parsed application_id. ERROR log on failures.
- tools/ layer: DEBUG log every public tool entry with key parameters,
  INFO log on business outcomes (saved/submitted/killed/...).
- New tests/unit/test_logging.py: capture loguru output via in-memory sink
  and assert DEBUG + INFO messages are emitted for representative flows.
2026-06-24 15:02:54 +08:00

55 lines
1.5 KiB
Python

# coding=utf-8
"""
@Time :2026/6/24
@Author :tao.chen
"""
import subprocess
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,
) -> list[str]:
cmd = [
"spark-submit",
"--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}"])
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