Incorrect rows in inline fetch result

src/databricks/sql/auth/retry.py

@@ -32,6 +32,7 @@ class CommandType(Enum):
     CLOSE_SESSION = "CloseSession"
     CLOSE_OPERATION = "CloseOperation"
     GET_OPERATION_STATUS = "GetOperationStatus"
+    FETCH_RESULTS_INLINE_FETCH_NEXT = "FetchResultsInline_FETCH_NEXT"
     OTHER = "Other"
 
     @classmethod
@@ -362,6 +363,12 @@ def should_retry(self, method: str, status_code: int) -> Tuple[bool, str]:
         if status_code == 501:
             raise NonRecoverableNetworkError("Received code 501 from server.")
 
+        if self.command_type == CommandType.FETCH_RESULTS_INLINE_FETCH_NEXT:
+            return (
+                False,
+                "FetchResults in INLINE mode with FETCH_NEXT orientation are not idempotent and is not retried",
+            )
+
         # Request failed and this method is not retryable. We only retry POST requests.
         if not self._is_method_retryable(method):
             return False, "Only POST requests are retried"

src/databricks/sql/thrift_backend.py

@@ -156,6 +156,8 @@ def __init__(
         )
 
         # Cloud fetch
+        self._use_cloud_fetch = kwargs.get("use_cloud_fetch", True)
+
         self.max_download_threads = kwargs.get("max_download_threads", 10)
 
         self._ssl_options = ssl_options
@@ -374,6 +376,18 @@ def attempt_request(attempt):
 
                 # These three lines are no-ops if the v3 retry policy is not in use
                 if self.enable_v3_retries:
+                    # Not to retry when FetchResults in INLINE mode when it has orientation as FETCH_NEXT as it is not idempotent
+                    if (
+                        this_method_name == "FetchResults"
+                        and self._use_cloud_fetch == False
+                    ):
+                        this_method_name += (
+                            "Inline_"
+                            + ttypes.TFetchOrientation._VALUES_TO_NAMES[
+                                request.orientation
+                            ]
+                        )
+
                     this_command_type = CommandType.get(this_method_name)
                     self._transport.set_retry_command_type(this_command_type)
                     self._transport.startRetryTimer()
@@ -1046,8 +1060,8 @@ def fetch_results(
 
         resp = self.make_request(self._client.FetchResults, req)
         if resp.results.startRowOffset > expected_row_start_offset:
-            logger.warning(
-                "Expected results to start from {} but they instead start at {}".format(
+            raise DataError(
+                "fetch_results failed due to inconsistency in the state between the client and the server. Expected results to start from {} but they instead start at {}, some result batches must have been skipped".format(
                     expected_row_start_offset, resp.results.startRowOffset
                 )
             )

tests/unit/test_retry.py

@@ -84,3 +84,9 @@ def test_sleep__retry_after_present(self, t_mock, retry_policy, error_history):
         retry_policy.history = [error_history, error_history, error_history]
         retry_policy.sleep(HTTPResponse(status=503, headers={"Retry-After": "3"}))
         t_mock.assert_called_with(3)
+
+    def test_not_retryable__fetch_results_orientation_fetch_next(self, retry_policy):
+        HTTP_STATUS_CODES = [200, 429, 503, 504]
+        retry_policy.command_type = CommandType.FETCH_RESULTS_INLINE_FETCH_NEXT
+        for status_code in HTTP_STATUS_CODES:
+            assert not retry_policy.is_retry("METHOD_NAME", status_code=status_code)