bvolpato commented on code in PR #24979:
URL: https://github.com/apache/beam/pull/24979#discussion_r1253183595
##########
sdks/python/apache_beam/io/gcp/bigquery.py:
##########
@@ -1515,11 +1526,41 @@ def process(self, element, *schema_side_inputs):
if not self.with_batched_input:
row_and_insert_id = element[1]
+ row_byte_size = get_deep_size(row_and_insert_id)
+
+ # send large rows that exceed BigQuery insert limits to DLQ
+ if row_byte_size >= self.max_insert_payload_size:
+ row_mb_size = row_byte_size / 1_000_000
+ max_mb_size = self.max_insert_payload_size / 1_000_000
+ error = (
+ f"Received row with size {row_mb_size}MB that exceeds "
+ f"the maximum insert payload size set ({max_mb_size}MB).")
+ return [
+ pvalue.TaggedOutput(
+ BigQueryWriteFn.FAILED_ROWS_WITH_ERRORS,
+ GlobalWindows.windowed_value(
+ (destination, row_and_insert_id[0], error))),
+ pvalue.TaggedOutput(
+ BigQueryWriteFn.FAILED_ROWS,
+ GlobalWindows.windowed_value(
+ (destination, row_and_insert_id[0])))
+ ]
+
+ buffer_byte_size_with_row = (
+ row_byte_size if not self._rows_buffer[destination] else
+ row_byte_size + get_deep_size(self._rows_buffer[destination]))
Review Comment:
In case it wasn't clear, I'm talking about keeping a supporting list like
self._rows_buffer_bytes[destination]
##########
sdks/python/apache_beam/io/gcp/bigquery.py:
##########
@@ -1515,11 +1526,41 @@ def process(self, element, *schema_side_inputs):
if not self.with_batched_input:
row_and_insert_id = element[1]
+ row_byte_size = get_deep_size(row_and_insert_id)
+
+ # send large rows that exceed BigQuery insert limits to DLQ
+ if row_byte_size >= self.max_insert_payload_size:
+ row_mb_size = row_byte_size / 1_000_000
+ max_mb_size = self.max_insert_payload_size / 1_000_000
+ error = (
+ f"Received row with size {row_mb_size}MB that exceeds "
+ f"the maximum insert payload size set ({max_mb_size}MB).")
+ return [
+ pvalue.TaggedOutput(
+ BigQueryWriteFn.FAILED_ROWS_WITH_ERRORS,
+ GlobalWindows.windowed_value(
+ (destination, row_and_insert_id[0], error))),
+ pvalue.TaggedOutput(
+ BigQueryWriteFn.FAILED_ROWS,
+ GlobalWindows.windowed_value(
+ (destination, row_and_insert_id[0])))
+ ]
+
+ buffer_byte_size_with_row = (
+ row_byte_size if not self._rows_buffer[destination] else
+ row_byte_size + get_deep_size(self._rows_buffer[destination]))
Review Comment:
In case it wasn't clear, I'm talking about keeping a supporting list like
```
self._rows_buffer_bytes[destination]
```
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
