From dc7911fd58f1f8d0e2c56dc42103adad22c6e97d Mon Sep 17 00:00:00 2001
From: Colin Thomas <33940547+colinthomas-z80@users.noreply.github.com>
Date: Fri, 6 Sep 2024 09:13:00 -0400
Subject: [PATCH] TaskVineExecutor: write function data to temp directory
 (#3592)

This moves the working directory for TaskVine executor function data to a directory in /tmp

These files were previously written adjacent to the logging in the working directory. They may be written in excess when running a large number of tasks.
---
 parsl/executors/taskvine/executor.py | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/parsl/executors/taskvine/executor.py b/parsl/executors/taskvine/executor.py
index 2e1efb211f..a15a444d2c 100644
--- a/parsl/executors/taskvine/executor.py
+++ b/parsl/executors/taskvine/executor.py
@@ -3,6 +3,7 @@
 high-throughput system for delegating Parsl tasks to thousands of remote machines
 """
 
+import getpass
 import hashlib
 import inspect
 import itertools
@@ -18,6 +19,7 @@
 import threading
 import uuid
 from concurrent.futures import Future
+from datetime import datetime
 from typing import List, Literal, Optional, Union
 
 # Import other libraries
@@ -215,9 +217,9 @@ def __create_data_and_logging_dirs(self):
 
         # Create directories for data and results
         log_dir = os.path.join(run_dir, self.label)
-        self._function_data_dir = os.path.join(run_dir, self.label, "function_data")
         os.makedirs(log_dir)
-        os.makedirs(self._function_data_dir)
+        tmp_prefix = f'{self.label}-{getpass.getuser()}-{datetime.now().strftime("%Y%m%d%H%M%S%f")}-'
+        self._function_data_dir = tempfile.TemporaryDirectory(prefix=tmp_prefix)
 
         # put TaskVine logs outside of a Parsl run as TaskVine caches between runs while
         # Parsl does not.
@@ -227,7 +229,7 @@ def __create_data_and_logging_dirs(self):
 
         # factory logs go with manager logs regardless
         self.factory_config.scratch_dir = self.manager_config.vine_log_dir
-        logger.debug(f"Function data directory: {self._function_data_dir}, log directory: {log_dir}")
+        logger.debug(f"Function data directory: {self._function_data_dir.name}, log directory: {log_dir}")
         logger.debug(
             f"TaskVine manager log directory: {self.manager_config.vine_log_dir}, "
             f"factory log directory: {self.factory_config.scratch_dir}")
@@ -293,7 +295,7 @@ def _path_in_task(self, executor_task_id, *path_components):
             'map': Pickled file with a dict between local parsl names, and remote taskvine names.
         """
         task_dir = "{:04d}".format(executor_task_id)
-        return os.path.join(self._function_data_dir, task_dir, *path_components)
+        return os.path.join(self._function_data_dir.name, task_dir, *path_components)
 
     def submit(self, func, resource_specification, *args, **kwargs):
         """Processes the Parsl app by its arguments and submits the function