NoahKusaba commented on code in PR #2579:
URL:
https://github.com/apache/datafusion-ballista/pull/2579#discussion_r4277860948
##########
ballista/core/src/execution_plans/sort_shuffle/buffer.rs:
##########
@@ -129,58 +129,78 @@ mod tests {
use datafusion::arrow::datatypes::{DataType, Field, Schema};
use std::sync::Arc;
- fn create_test_schema() -> SchemaRef {
+ fn schema() -> SchemaRef {
Arc::new(Schema::new(vec![Field::new("a", DataType::Int32, false)]))
}
- fn create_test_batch(schema: &SchemaRef, values: Vec<i32>) -> RecordBatch {
- let array = Int32Array::from(values);
- RecordBatch::try_new(schema.clone(), vec![Arc::new(array)]).unwrap()
+ fn batch(values: Vec<i32>) -> RecordBatch {
+ RecordBatch::try_new(schema(),
vec![Arc::new(Int32Array::from(values))]).unwrap()
+ }
+
+ /// Each partition `drain` visits, with its batches.
+ fn drain(bb: &mut BufferedBatches) -> Vec<(usize, Vec<RecordBatch>)> {
+ let mut out = vec![];
+ bb.drain(|p, batches| {
+ out.push((p, batches.collect::<Result<_>>()?));
+ Ok(())
+ })
+ .unwrap();
+ out
+ }
+
+ fn index_bytes(bb: &BufferedBatches) -> usize {
+ bb.indices
+ .iter()
+ .map(|v| v.capacity() * size_of::<(u32, u32)>())
+ .sum()
}
#[test]
- fn buffered_batches_pushes_and_partitions_indices() {
- let schema = create_test_schema();
- let mut bb = BufferedBatches::new(3, schema.clone());
+ fn drains_each_partition_in_arrival_order_and_batch_size() {
+ let mut bb = BufferedBatches::new(3, schema(), 2);
Review Comment:
That makes sense, i set batch_size to 3 in the latest commit.
Thanks for the review :smile:
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
