Fix FsspecFileIO.get_fs thread safety

`FsspecFileIO.get_fs` can be called by multiple threads when `ExecutorFactory`
is used (for example by `DataScan.plan_files`).

The base class of `fsspec` filesystem objects, `fsspec.spec.AbstractFileSystem`,
internally caches instances through the `fsspec.spec._Cached` metaclass.
The caching key used includes `threading.get_ident()`, making entries
thread-local:
https://github.com/fsspec/filesystem_spec/blame/f84b99f0d1f079f990db1a219b74df66ab3e7160/fsspec/spec.py#L71

The `FsspecFileIO.get_fs` LRU cache (around `FsspecFileIO._get_fs`) breaks
the thread-locality of the filesystem instances as it will return the
same instance for different threads.

One consequence of this is that for `s3fs.S3FileSystem`, HTTP connection
pooling no longer occurs per thread (as is normal with `aiobotocore`), as
the `aiobotocore` client object (containing the `aiohttp.ClientSession`)
is stored on the `s3fs.S3FileSystem`.

This change addresses this by making the `FsspecFileIO.get_fs` cache
thread-local.

Author: lwfitzgerald

pyiceberg/io/fsspec.py

@@ -20,6 +20,7 @@
 import json
 import logging
 import os
+import threading
 from copy import copy
 from functools import lru_cache, partial
 from typing import (
@@ -370,7 +371,7 @@ class FsspecFileIO(FileIO):
     def __init__(self, properties: Properties):
         self._scheme_to_fs = {}
         self._scheme_to_fs.update(SCHEME_TO_FS)
-        self.get_fs: Callable[[str], AbstractFileSystem] = lru_cache(self._get_fs)
+        self._thread_locals = threading.local()
         super().__init__(properties=properties)
 
     def new_input(self, location: str) -> FsspecInputFile:
@@ -416,6 +417,13 @@ def delete(self, location: Union[str, InputFile, OutputFile]) -> None:
         fs = self.get_fs(uri.scheme)
         fs.rm(str_location)
 
+    def get_fs(self, scheme: str) -> AbstractFileSystem:
+        """Get a filesystem for a specific scheme, cached per thread."""
+        if not hasattr(self._thread_locals, "get_fs_cached"):
+            self._thread_locals.get_fs_cached = lru_cache(self._get_fs)
+
+        return self._thread_locals.get_fs_cached(scheme)
+
     def _get_fs(self, scheme: str) -> AbstractFileSystem:
         """Get a filesystem for a specific scheme."""
         if scheme not in self._scheme_to_fs:
@@ -425,10 +433,10 @@ def _get_fs(self, scheme: str) -> AbstractFileSystem:
     def __getstate__(self) -> Dict[str, Any]:
         """Create a dictionary of the FsSpecFileIO fields used when pickling."""
         fileio_copy = copy(self.__dict__)
-        fileio_copy["get_fs"] = None
+        del fileio_copy["_thread_locals"]
         return fileio_copy
 
     def __setstate__(self, state: Dict[str, Any]) -> None:
         """Deserialize the state into a FsSpecFileIO instance."""
         self.__dict__ = state
-        self.get_fs = lru_cache(self._get_fs)
+        self._thread_locals = threading.local()

tests/io/test_fsspec.py

@@ -18,6 +18,7 @@
 import os
 import pickle
 import tempfile
+import threading
 import uuid
 from unittest import mock
 
@@ -54,6 +55,36 @@ def test_fsspec_local_fs_can_create_path_without_parent_dir(fsspec_fileio: Fsspe
             pytest.fail("Failed to write to file without parent directory")
 
 
+def test_fsspec_get_fs_instance_per_thread_caching(fsspec_fileio: FsspecFileIO) -> None:
+    """Test that filesystem instances are cached per-thread by `FsspecFileIO.get_fs`"""
+    fs_instances = []
+
+    def get_fs_instance() -> None:
+        # Call twice to ensure caching within the same thread
+        for _ in range(2):
+            fs_instances.append(fsspec_fileio.get_fs("file"))
+
+    threads = [
+        # Differing names required on the threads to ensure distinct `threading.get_ident()` values
+        # as this is used as part of the `fsspec.spec.AbstractFileSystem` cache key.
+        threading.Thread(target=get_fs_instance, name="test-thread-1"),
+        threading.Thread(target=get_fs_instance, name="test-thread-2"),
+    ]
+
+    threads[0].start()
+    threads[0].join()
+
+    threads[1].start()
+    threads[1].join()
+
+    # Same thread, same instance
+    assert fs_instances[0] is fs_instances[1]
+    assert fs_instances[2] is fs_instances[3]
+
+    # Different threads, different instances
+    assert fs_instances[0] is not fs_instances[2]
+
+
 @pytest.mark.s3
 def test_fsspec_new_input_file(fsspec_fileio: FsspecFileIO) -> None:
     """Test creating a new input file from a fsspec file-io"""