antban commented on code in PR #53016:
URL: https://github.com/apache/spark/pull/53016#discussion_r2537540831
##########
python/pyspark/util.py:
##########
@@ -917,6 +918,67 @@ def default_api_mode() -> str:
return "classic"
+class _FaulthandlerHelper:
+ def __init__(self) -> None:
+ self._log_path: Optional[str] = None
+ self._log_file: Optional[TextIO] = None
+ self._periodic_dump = False
+
+ def start(self) -> None:
+ if self._log_path:
+ raise Exception("Fault handler is already registered. No second
registration allowed")
+ self._log_path = os.environ.get("PYTHON_FAULTHANDLER_DIR", None)
+ traceback_dump_interval_seconds = os.environ.get(
+ "PYTHON_TRACEBACK_DUMP_INTERVAL_SECONDS", None
+ )
+ if self._log_path:
+ self._log_path = os.path.join(self._log_path, str(os.getpid()))
+ self._log_file = open(self._log_path, "w")
+
+ faulthandler.enable(file=self._log_file)
+
+ if (
+ traceback_dump_interval_seconds is not None
+ and int(traceback_dump_interval_seconds) > 0
+ ):
+ self._periodic_dump = True
+
faulthandler.dump_traceback_later(int(traceback_dump_interval_seconds),
repeat=True)
+
+ def stop(self) -> None:
+ if self._periodic_dump:
+ faulthandler.cancel_dump_traceback_later()
+ self._periodic_dump = False
+ if self._log_path:
+ faulthandler.disable()
+ if self._log_file:
+ self._log_file.close()
+ self._log_file = None
+ try:
+ os.remove(self._log_path)
+ finally:
+ self._log_path = None
+
+ def with_faulthandler(self, func: Callable) -> Callable:
+ """
+ Registers fault handler for the duration of function execution.
+ After function execution is over the faulthandler registration is
cleaned as well,
+ including any files created for the integration.
+ """
+
+ @functools.wraps(func)
+ def wrapper(*args: Any, **kwargs: Any) -> Any:
+ try:
+ self.start()
+ return func(*args, **kwargs)
+ finally:
+ self.stop()
+
+ return wrapper
+
+
+with_fault_handler = _FaulthandlerHelper().with_faulthandler
Review Comment:
with_faulthandler
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
