Add comments and debug check

TangSiyang2001 · Feb 26, 2024 · ce9e256 · ce9e256
1 parent 075c998
commit ce9e256
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 2 deletions.
diff --git a/cpp/src/arrow/filesystem/s3fs.cc b/cpp/src/arrow/filesystem/s3fs.cc
@@ -2899,9 +2899,12 @@ struct AwsInstance {
       return Status::Invalid("Attempt to initialize S3 after it has been finalized");
     }
     bool newly_initialized = false;
+    // EnsureInitialized() can be called concurrently by FileSystemFromUri,
+    // therefore we need to serialize initialization (GH-39897).
     std::call_once(initialize_flag_, [&]() {
+      bool was_initialized = is_initialized_.exchange(true);
+      DCHECK(!was_initialized);
       DoInitialize(options);
-      is_initialized_.exchange(true);
       newly_initialized = true;
     });
     return newly_initialized;

diff --git a/python/pyarrow/tests/test_fs.py b/python/pyarrow/tests/test_fs.py
@@ -1907,7 +1907,8 @@ def test_s3_finalize_region_resolver():
 
 
 @pytest.mark.s3
-def test_concurrent_fs_init():
+def test_concurrent_s3fs_init():
+    # GH-39897: lazy concurrent initialization of S3 subsystem should not crash
     code = """if 1:
         import threading
         import pytest