ihji commented on a change in pull request #12754:
URL: https://github.com/apache/beam/pull/12754#discussion_r483457312
##########
File path: sdks/python/apache_beam/io/gcp/bigquery.py
##########
@@ -1198,8 +1209,34 @@ def process(self, element, *schema_side_inputs):
return self._flush_all_batches()
def finish_bundle(self):
+ current_millis = int(time.time() * 1000)
+ if BigQueryWriteFn.LATENCY_LOGGING_LOCK.acquire(False):
+ try:
+ if (BigQueryWriteFn.LATENCY_LOGGING_HISTOGRAM.total_count() > 0 and
+ (current_millis -
+ BigQueryWriteFn.LATENCY_LOGGING_LAST_REPORTED_MILLIS) >
+ self._latency_logging_frequency * 1000):
+ self._log_percentiles()
+ BigQueryWriteFn.LATENCY_LOGGING_HISTOGRAM.clear()
+ BigQueryWriteFn.LATENCY_LOGGING_LAST_REPORTED_MILLIS = current_millis
+ finally:
+ BigQueryWriteFn.LATENCY_LOGGING_LOCK.release()
return self._flush_all_batches()
+ @classmethod
+ def _log_percentiles(cls):
+ # Note that the total count and each percentile value may not be correlated
+ # each other. Histogram releases lock between each percentile calculation
+ # so additional latencies could be added anytime.
+ # pylint: disable=round-builtin
+ _LOGGER.info(
Review comment:
Changed to atomic logging with the internal lock.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
