def _update_last_index_token(self, new_index_token: str) -> None:
"""
This function updates the last_index_token in the following scenarios:
1. last_complete_step >= last_index_token_step :
this means that the token isn't pointing to the latest completed step
2. number of steps available ( complete or incomplete ) - (last_completed_step+1) > window_size_limit:
we maintain a window to stop querying for older steps that have not completed.
if the total number of steps, we are querying for completion is greater than our window_size_limit
we update the last_index_token and last_complete_step by (window_size_limit // 2)
:param new_index_token:
:return:None
"""
if self.last_index_token is None:
last_index_token_step = 0
else:
last_index_token_step = IndexFileLocationUtils.parse_step_from_index_file_name(
self.last_index_token)
# Case 1: This case is not satisfied when all workers in a
# distributed training job have not written a step
if self.last_complete_step >= last_index_token_step:
prefix = IndexFileLocationUtils.get_prefix_from_index_file(
new_index_token)
# sort lexicographically and select the last worker
last_worker = sorted(list(self.worker_set))[-1]
# below converts worker_name to serialized workerName
# if it's a tf device, else no effect
last_worker_serialized = serialize_tf_device(last_worker)
self.last_index_token = IndexFileLocationUtils.get_index_key_for_step(
prefix, self.last_complete_step, last_worker_serialized)
self.logger.debug(
f"Updated last index token to:{self.last_index_token}")
# Case 2: This case is satisfied if the number of incomplete steps
# is greater than the INCOMPLETE_STEP_WAIT_WINDOW
available_step = self._global_to_mode.keys()
if (len(available_step) - (self.last_complete_step + 1) >
self._incomplete_wait_for_step_window):
prefix = IndexFileLocationUtils.get_prefix_from_index_file(
new_index_token)
last_worker = sorted(list(self.worker_set))[-1]
# below converts worker_name to serialized workerName
# if it's a tf device, else no effect
last_worker_serialized = serialize_tf_device(last_worker)
self.last_index_token = IndexFileLocationUtils.get_index_key_for_step(
prefix,
self.last_complete_step +
(self._incomplete_wait_for_step_window // 2),
last_worker_serialized,
)
self.last_complete_step = IndexFileLocationUtils.parse_step_from_index_file_name(
self.last_index_token)
self.logger.info(
f"Waiting for: {len(available_step) - (self.last_complete_step + 1)} Steps. \n"
f"INCOMPLETE_STEP_WAIT_WINDOW: {self._incomplete_wait_for_step_window}. \n"
f"Marking the last {self._incomplete_wait_for_step_window // 2} incomplete steps as complete"
f"Updating last_index_token to: {self.last_index_token}. \n"
f"Updating last_complete_step to: {self.last_complete_step}. ")
def test_get_prefix_from_index_file():
local_index_filepath = "/opt/ml/testing/run_1/index/000000000/000000000000_worker_0.json"
prefix = IndexFileLocationUtils.get_prefix_from_index_file(local_index_filepath)
assert prefix == "/opt/ml/testing/run_1"
s3_index_filepath = (
"s3://bucket-that-does-not-exist/run_1/index/000000000/000000000000_worker_0.json"
)
prefix = IndexFileLocationUtils.get_prefix_from_index_file(s3_index_filepath)
assert prefix == "s3://bucket-that-does-not-exist/run_1"