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.
118 lines
4.6 KiB
Python
118 lines
4.6 KiB
Python
# coding=utf-8
|
|
"""
|
|
@Time :2026/6/24
|
|
@Author :tao.chen
|
|
|
|
Single source of truth for environment-driven application configuration.
|
|
|
|
Why this module exists: every prior `os.environ.get("SPARK_EXECUTOR_*")`
|
|
was scattered across `connection_store.py`, `pending_store.py`,
|
|
`yarn_client.py`, `job_writer.py`. The same env var name appeared in
|
|
multiple files, and there was no single place to see "what's
|
|
configurable?". This file is that place.
|
|
|
|
All application code should:
|
|
from common.config import settings
|
|
... settings.data_dir / settings.yarn_resource_manager_url / ...
|
|
|
|
...rather than `os.environ.get(...)` directly. This way:
|
|
- The env var name appears in exactly one place.
|
|
- Ops can audit the full config surface from one file.
|
|
- Tests can monkeypatch fields on the `settings` singleton directly
|
|
(more reliable than monkeypatching env + reloading).
|
|
|
|
NOT in this module:
|
|
- Gunicorn-specific env vars (workers, threads, bind, timeout) live in
|
|
gunicorn.conf.py because they configure gunicorn, not the app.
|
|
- `PYTHONUNBUFFERED` — Python runtime flag, set in Dockerfile.
|
|
- `SPARK_SUBMIT_OPTS` — JVM flags, not Python config; users pass them
|
|
to spark-submit directly.
|
|
"""
|
|
import os
|
|
from dataclasses import dataclass
|
|
|
|
|
|
@dataclass
|
|
class Settings:
|
|
"""Application settings loaded from environment variables at import time.
|
|
|
|
Mutable so tests can reassign fields directly. For tests that use
|
|
`monkeypatch.setenv(...)`, call `settings.reload()` to re-read from
|
|
the (now-patched) environment.
|
|
"""
|
|
|
|
# --- Data persistence (./data/ in dev, /var/lib/... in prod) ---
|
|
data_dir: str = "./data"
|
|
|
|
# --- Job files (LLM-generated PySpark) ---
|
|
# Defaults to <data_dir>/jobs; can be pointed at a larger disk via
|
|
# SPARK_EXECUTOR_JOBS_DIR (e.g. /var/spark-jobs on a big-disk host).
|
|
jobs_dir: str = ""
|
|
|
|
# --- Loguru file sinks ---
|
|
# Base directory for loguru file output. Debug and info subdirs are
|
|
# derived as <log_dir>/debug and <log_dir>/info. Defaults to
|
|
# <data_dir>/logs; override via SPARK_EXECUTOR_LOG_DIR to put logs
|
|
# on a dedicated volume (e.g. /var/log/spark-executor).
|
|
log_dir: str = ""
|
|
|
|
# --- YARN REST client (fallback for Job.yarn_rm_url snapshot) ---
|
|
# Set in the env OR per-Connection via save_connection.
|
|
yarn_resource_manager_url: str | None = None
|
|
|
|
# --- Loguru ---
|
|
# Controls stderr verbosity and the info-level file sink. The debug
|
|
# file sink always captures DEBUG (full audit trail).
|
|
log_level: str = "DEBUG"
|
|
|
|
# --- Spark CLI binary name ---
|
|
# The program name used in cmd[0] when invoking the Spark client.
|
|
# Defaults to 'spark-submit' (the standard Spark 2.x / 3.x / 4.x CLI).
|
|
# Override via SPARK_EXECUTOR_SPARK_SUBMIT_BIN for:
|
|
# - 'spark2-submit' on a system where both Spark 1.x and 2.x are
|
|
# installed and spark-submit points to the wrong one
|
|
# - a custom wrapper script (e.g. '/usr/local/bin/spark-submit-wrapper')
|
|
# - 'pyspark' if you want to launch via the PySpark entrypoint
|
|
# The binary is resolved against $PATH (set by docker-entrypoint.sh).
|
|
spark_submit_bin: str = "spark-submit"
|
|
|
|
@classmethod
|
|
def from_env(cls) -> "Settings":
|
|
data_dir = os.environ.get("SPARK_EXECUTOR_DATA_DIR", "./data")
|
|
jobs_dir = os.environ.get(
|
|
"SPARK_EXECUTOR_JOBS_DIR", os.path.join(data_dir, "jobs")
|
|
)
|
|
log_dir = os.environ.get(
|
|
"SPARK_EXECUTOR_LOG_DIR", os.path.join(data_dir, "logs")
|
|
)
|
|
return cls(
|
|
data_dir=data_dir,
|
|
jobs_dir=jobs_dir,
|
|
log_dir=log_dir,
|
|
# `or None` collapses empty string to None for the URL fallback
|
|
yarn_resource_manager_url=os.environ.get("YARN_RESOURCE_MANAGER_URL") or None,
|
|
log_level=os.environ.get("SPARK_EXECUTOR_LOG_LEVEL", "DEBUG"),
|
|
spark_submit_bin=os.environ.get(
|
|
"SPARK_EXECUTOR_SPARK_SUBMIT_BIN", "spark-submit"
|
|
),
|
|
)
|
|
|
|
def reload(self) -> "Settings":
|
|
"""Re-read from environment, mutate in place, return self (chainable).
|
|
|
|
Useful in tests that `monkeypatch.setenv(...)` and want the
|
|
singleton to pick up the new value without a re-import.
|
|
"""
|
|
fresh = self.from_env()
|
|
self.data_dir = fresh.data_dir
|
|
self.jobs_dir = fresh.jobs_dir
|
|
self.log_dir = fresh.log_dir
|
|
self.yarn_resource_manager_url = fresh.yarn_resource_manager_url
|
|
self.log_level = fresh.log_level
|
|
self.spark_submit_bin = fresh.spark_submit_bin
|
|
return self
|
|
|
|
|
|
# Module-level singleton. Loaded once at import time.
|
|
settings = Settings.from_env()
|