sdk/python: ObjectFileReader minor follow-up fixes

rkoo19 · rkoo19 · commit 197f8661be65 · 2025-05-16T11:17:24.000-07:00
Signed-off-by: Ryan Koo &lt;rbk65@cornell.edu&gt;
diff --git a/python/CHANGELOG.md b/python/CHANGELOG.md
@@ -8,7 +8,11 @@ We structure this changelog in accordance with [Keep a Changelog](https://keepac
 
 ## Unreleased
 
-## [1.13.7] - 2025-05-15
+### Changed
+
+- Improve `ObjectFileReader` logging to include the full exception details and traceback when retrying and resuming.
+
+## [1.13.8] - 2025-05-15
 
 ### Added
 
diff --git a/python/aistore/sdk/obj/obj_file/utils.py b/python/aistore/sdk/obj/obj_file/utils.py
@@ -59,12 +59,13 @@ def handle_broken_stream(
     resume_total = increment_resume(resume_total, max_resume, err)
     obj_path = content_iterator.client.path
     logger.warning(
-        "Chunked encoding error while reading '%s': (%s), retrying %d/%d",
+        "Error while reading '%s', retrying %d/%d",
         obj_path,
-        err,
         resume_total,
         max_resume,
+        exc_info=err,
     )
+
     # Create a new iterator from the last read position
     new_iter = content_iterator.iter(offset=resume_position)
     return new_iter, resume_total
diff --git a/python/aistore/sdk/obj/object_reader.py b/python/aistore/sdk/obj/object_reader.py
@@ -98,8 +98,8 @@ def as_file(
         """
         Create a read-only, non-seekable `ObjectFileReader` instance for streaming object data in chunks.
         This file-like object primarily implements the `read()` method to retrieve data sequentially,
-        with automatic retry/resumption in case of stream interruptions (e.g. `ChunkedEncodingError`,
-        `ConnectionError`) or timeouts (e.g. `ReadTimeout`, `ConnectTimeout`).
+        with automatic retry/resumption in case of unexpected stream interruptions (e.g. `ChunkedEncodingError`,
+        `ConnectionError`) or timeouts (e.g. `ReadTimeout`).
 
         Args:
             buffer_size (int, optional): Currently unused; retained for backward compatibility and future
diff --git a/python/tests/perf/object_file/obj-file-reader-stress-test.py b/python/tests/perf/object_file/obj-file-reader-stress-test.py
@@ -59,7 +59,7 @@ def test_with_interruptions(
 
     # Perform ObjectFileReader read
     downloaded_data, resume_total = obj_file_reader_read(
-        object_reader, READ_SIZE, BUFFER_SIZE, MAX_RESUME
+        object_reader, READ_SIZE, MAX_RESUME
     )
 
     end_time = time.time()
diff --git a/python/tests/perf/object_file/utils.py b/python/tests/perf/object_file/utils.py
@@ -48,13 +48,11 @@ def create_and_put_objects(bucket: Bucket, obj_size: int, num_objects: int) -> N
 
 
 def obj_file_reader_read(
-    object_reader: ObjectReader, read_size: int, buffer_size: int, max_resume: int
+    object_reader: ObjectReader, read_size: int, max_resume: int
 ) -> Tuple[bytes, int]:
     """Reads via ObjectFileReader instantiated from provided ObjectReader. Returns the downloaded data and total number of resumes."""
     result = bytearray()
-    with object_reader.as_file(
-        buffer_size=buffer_size, max_resume=max_resume
-    ) as obj_file:
+    with object_reader.as_file(max_resume=max_resume) as obj_file:
         while True:
             data = obj_file.read(read_size)
             if not data:

Original file line number	Diff line number	Diff line change
`@@ -59,7 +59,7 @@ def test_with_interruptions(`
`59`	`59`
`60`	`60`	`# Perform ObjectFileReader read`
`61`	`61`	`downloaded_data, resume_total = obj_file_reader_read(`
`62`		`- object_reader, READ_SIZE, BUFFER_SIZE, MAX_RESUME`
	`62`	`+ object_reader, READ_SIZE, MAX_RESUME`
`63`	`63`	`)`
`64`	`64`
`65`	`65`	`end_time = time.time()`