alamb commented on a change in pull request #538:
URL: https://github.com/apache/arrow-datafusion/pull/538#discussion_r649259579
##########
File path: datafusion/src/physical_plan/repartition.rs
##########
@@ -132,132 +160,33 @@ impl ExecutionPlan for RepartitionExec {
// being read yet. This may cause high memory usage if the
next operator is
// reading output partitions in order rather than
concurrently. One workaround
// for this would be to add spill-to-disk capabilities.
- let (sender, receiver) =
tokio::sync::mpsc::unbounded_channel::<
- Option<ArrowResult<RecordBatch>>,
- >();
+ let (sender, receiver) =
+
mpsc::unbounded_channel::<Option<ArrowResult<RecordBatch>>>();
channels.insert(partition, (sender, receiver));
}
// Use fixed random state
let random = ahash::RandomState::with_seeds(0, 0, 0, 0);
// launch one async task per *input* partition
for i in 0..num_input_partitions {
- let random_state = random.clone();
Review comment:
All of this code was moved to `pull_from_input`
--
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:
us...@infra.apache.org
