Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Minor refactor to reduce duplicate code #659

Merged
merged 2 commits into from
Feb 13, 2023
Merged

Minor refactor to reduce duplicate code #659

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
155a02f
Minor refactor to reduce duplicate code
andygrove Feb 8, 2023
bd06b5f
Merge remote-tracking branch 'apache/main' into minor-cleanup
andygrove Feb 12, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
53 changes: 17 additions & 36 deletions ballista/scheduler/src/planner.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,8 +16,6 @@
// under the License.

//! Distributed query execution
//!
//! This code is EXPERIMENTAL and still under development
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I guess we're official now :)


use std::collections::HashMap;
use std::sync::Arc;
Expand Down Expand Up @@ -84,7 +82,6 @@ impl DistributedPlanner {
job_id: &'a str,
execution_plan: Arc<dyn ExecutionPlan>,
) -> Result<PartialQueryStageResult> {
// async move {
// recurse down and replace children
if execution_plan.children().is_empty() {
return Ok((execution_plan, vec![]));
Expand All @@ -109,17 +106,7 @@ impl DistributedPlanner {
children[0].clone(),
None,
)?;
let unresolved_shuffle = Arc::new(UnresolvedShuffleExec::new(
shuffle_writer.stage_id(),
shuffle_writer.schema(),
shuffle_writer.output_partitioning().partition_count(),
shuffle_writer
.shuffle_output_partitioning()
.map(|p| p.partition_count())
.unwrap_or_else(|| {
shuffle_writer.output_partitioning().partition_count()
}),
));
let unresolved_shuffle = create_unresolved_shuffle(&shuffle_writer);
stages.push(shuffle_writer);
Ok((
with_new_children_if_necessary(execution_plan, vec![unresolved_shuffle])?,
Expand All @@ -135,17 +122,7 @@ impl DistributedPlanner {
children[0].clone(),
None,
)?;
let unresolved_shuffle = Arc::new(UnresolvedShuffleExec::new(
shuffle_writer.stage_id(),
shuffle_writer.schema(),
shuffle_writer.output_partitioning().partition_count(),
shuffle_writer
.shuffle_output_partitioning()
.map(|p| p.partition_count())
.unwrap_or_else(|| {
shuffle_writer.output_partitioning().partition_count()
}),
));
let unresolved_shuffle = create_unresolved_shuffle(&shuffle_writer);
stages.push(shuffle_writer);
Ok((
with_new_children_if_necessary(execution_plan, vec![unresolved_shuffle])?,
Expand All @@ -162,17 +139,7 @@ impl DistributedPlanner {
children[0].clone(),
Some(repart.partitioning().to_owned()),
)?;
let unresolved_shuffle = Arc::new(UnresolvedShuffleExec::new(
shuffle_writer.stage_id(),
shuffle_writer.schema(),
shuffle_writer.output_partitioning().partition_count(),
shuffle_writer
.shuffle_output_partitioning()
.map(|p| p.partition_count())
.unwrap_or_else(|| {
shuffle_writer.output_partitioning().partition_count()
}),
));
let unresolved_shuffle = create_unresolved_shuffle(&shuffle_writer);
stages.push(shuffle_writer);
Ok((unresolved_shuffle, stages))
}
Expand Down Expand Up @@ -202,6 +169,20 @@ impl DistributedPlanner {
}
}

fn create_unresolved_shuffle(
shuffle_writer: &ShuffleWriterExec,
) -> Arc<UnresolvedShuffleExec> {
Arc::new(UnresolvedShuffleExec::new(
shuffle_writer.stage_id(),
shuffle_writer.schema(),
shuffle_writer.output_partitioning().partition_count(),
shuffle_writer
.shuffle_output_partitioning()
.map(|p| p.partition_count())
.unwrap_or_else(|| shuffle_writer.output_partitioning().partition_count()),
))
}

/// Returns the unresolved shuffles in the execution plan
pub fn find_unresolved_shuffles(
plan: &Arc<dyn ExecutionPlan>,
Expand Down