andygrove commented on code in PR #256:
URL: https://github.com/apache/arrow-ballista/pull/256#discussion_r976520308
##########
ballista/rust/core/src/execution_plans/shuffle_reader.rs:
##########
@@ -102,29 +107,35 @@ impl ExecutionPlan for ShuffleReaderExec {
fn execute(
&self,
partition: usize,
- _context: Arc<TaskContext>,
+ context: Arc<TaskContext>,
) -> Result<SendableRecordBatchStream> {
- debug!("ShuffleReaderExec::execute({})", partition);
-
- let fetch_time =
- MetricBuilder::new(&self.metrics).subset_time("fetch_time",
partition);
-
- let locations = self.partition[partition].clone();
- let stream = locations.into_iter().map(move |p| {
- let fetch_time = fetch_time.clone();
- futures::stream::once(async move {
- let timer = fetch_time.timer();
- let r = fetch_partition(&p).await;
- timer.done();
-
- r.map_err(|e| ArrowError::ExternalError(Box::new(e)))
- })
- .try_flatten()
- });
+ let task_id = context.task_id().unwrap_or_else(||
partition.to_string());
+ info!("ShuffleReaderExec::execute({})", task_id);
+
+ // TODO make the maximum size configurable, or make it depends on
global memory control
+ let max_request_num = 50usize;
Review Comment:
+1 for making this a config option that is documented in the user guide. I
can help with this in a follow-on PR.
--
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]
