alamb commented on code in PR #11345:
URL: https://github.com/apache/datafusion/pull/11345#discussion_r1672096842
##########
datafusion/core/src/datasource/file_format/parquet.rs:
##########
@@ -895,16 +912,23 @@ async fn send_arrays_to_col_writers(
fn spawn_rg_join_and_finalize_task(
column_writer_tasks: Vec<ColumnWriterTask>,
rg_rows: usize,
+ pool: &Arc<dyn MemoryPool>,
) -> SpawnedTask<RBStreamSerializeResult> {
+ let mut rg_reservation =
+
MemoryConsumer::new("ParquetSink(SerializedRowGroupWriter)").register(pool);
+
SpawnedTask::spawn(async move {
let num_cols = column_writer_tasks.len();
let mut finalized_rg = Vec::with_capacity(num_cols);
for task in column_writer_tasks.into_iter() {
- let writer = task.join_unwind().await?;
+ let (writer, col_reservation) = task.join_unwind().await?;
+ let encoded_size = writer.get_estimated_total_bytes();
+ rg_reservation.grow(encoded_size);
+ drop(col_reservation);
Review Comment:
I don't think the explicit `drop` is needed -- it will be dropped
automatically by the compiler when `col_reservation` goes out of scope on the
next line
--
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: github-unsubscr...@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For additional commands, e-mail: github-h...@datafusion.apache.org
