From fe35eb30d1b2a0ea774c36b28f40cfa5a78f8259 Mon Sep 17 00:00:00 2001
From: Markus Mohrhard <markusm@dug.com>
Date: Sat, 11 Jan 2020 02:09:03 +0800
Subject: [PATCH] make iterating over sys.modules threadsafe

Despite creating a copy through list(sys.modules.items()) there
is a possible race condition if another thread is adding to sys.modules

  File "x/lib/python3.7/pickle.py", line 774, in save_tuple
    save(element)
  File "x/lib/python3.7/pickle.py", line 549, in save
    self.save_reduce(obj=obj, *rv)
  File "x/lib/python3.7/pickle.py", line 637, in save_reduce
    save(func)
  File "x/lib/python3.7/pickle.py", line 518, in save
    self.save_global(obj)
  File "x/lib/python3.7/site-packages/cloudpickle/cloudpickle.py", line 876, in save_global
    elif not _is_global(obj, name=name):
  File "x/lib/python3.7/site-packages/cloudpickle/cloudpickle.py", line 174, in _is_global
    module_name = _whichmodule(obj, name)
  File "x/lib/python3.7/site-packages/cloudpickle/cloudpickle.py", line 156, in _whichmodule
    for module_name, module in list(sys.modules.items()):
RuntimeError: dictionary changed size during iteration
---
 CHANGES.md                 | 4 ++++
 cloudpickle/cloudpickle.py | 7 ++++---
 2 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/CHANGES.md b/CHANGES.md
index 94dcc014f..79043afe4 100644
--- a/CHANGES.md
+++ b/CHANGES.md
@@ -1,6 +1,10 @@
 1.2.3
 =====
 
+- Fix a bug when a thread imports a module while cloudpickle iterates
+  over the module list
+  ([PR #322](https://github.com/cloudpipe/cloudpickle/pull/322)).
+
 1.2.2
 =====
 
diff --git a/cloudpickle/cloudpickle.py b/cloudpickle/cloudpickle.py
index 1d4c85cbe..fc0372be0 100644
--- a/cloudpickle/cloudpickle.py
+++ b/cloudpickle/cloudpickle.py
@@ -151,9 +151,10 @@ def _whichmodule(obj, name):
     module_name = getattr(obj, '__module__', None)
     if module_name is not None:
         return module_name
-    # Protect the iteration by using a list copy of sys.modules against dynamic
-    # modules that trigger imports of other modules upon calls to getattr.
-    for module_name, module in list(sys.modules.items()):
+    # Protect the iteration by using a copy of sys.modules against dynamic
+    # modules that trigger imports of other modules upon calls to getattr or
+    # other threads importing at the same time.
+    for module_name, module in sys.modules.copy().items():
         if module_name == '__main__' or module is None:
             continue
         try: