Skip to content

scan: make LazyScanStream initialization non-blocking #5906

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

Open
godnight10061 wants to merge 6 commits into
base: develop
Choose a base branch
from
+302 −21
Open

scan: make LazyScanStream initialization non-blocking #5906

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
9bf6ce2
fix: avoid blocking scan preparation in poll
godnight10061 Jan 9, 2026
d5c6d07
test: reuse crate test session helpers
godnight10061 Jan 10, 2026
67f1dd0
test: rename SESSION to SCAN_SESSION
godnight10061 Jan 10, 2026
1f416f2
test: avoid assuming row order in schema evolution
godnight10061 Jan 11, 2026
4fae8fe
Merge branch 'develop' into fix/5899-clickbench-regression
joseph-isaacs Jan 14, 2026
5d5b799
fix: reduce blocking work in LazyScanStream
godnight10061 Jan 14, 2026
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
13 changes: 7 additions & 6 deletions vortex-datafusion/tests/schema_evolution.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@ use datafusion::datasource::listing::ListingTableConfig;
use datafusion::execution::SessionStateBuilder;
use datafusion::execution::context::SessionContext;
use datafusion_common::assert_batches_eq;
use datafusion_common::assert_batches_sorted_eq;
use datafusion_common::create_array;
use datafusion_common::record_batch;
use datafusion_datasource::ListingTableUrl;
Expand Down Expand Up @@ -149,11 +150,11 @@ async fn test_filter_with_schema_evolution() {
"| a | b |",
"+-------+---+",
"| one | |",
"| two | |",
"| three | |",
"| two | |",
"+-------+---+",
];
assert_batches_eq!(expected, &result);
assert_batches_sorted_eq!(expected, &result);
}

#[tokio::test]
Expand Down Expand Up @@ -246,14 +247,14 @@ async fn test_filter_schema_evolution_order() {

// a field: present in both files
// b field: only present in file2, file1 fills with nulls
assert_batches_eq!(
assert_batches_sorted_eq!(
&[
"+---+------+",
"| a | b |",
"+---+------+",
"| 3 | |",
"| 5 | |",
"| 4 | four |",
"| 5 | |",
"| 6 | six |",
"+---+------+",
],
Expand Down Expand Up @@ -351,7 +352,7 @@ async fn test_filter_schema_evolution_struct_fields() {
// Scan all the records, NULLs are filled in for nested optional fields.
let full_scan = df.collect().await.unwrap();

assert_batches_eq!(
assert_batches_sorted_eq!(
&[
"+--------------+-----------------------------+",
"| hostname | payload |",
Expand Down Expand Up @@ -385,7 +386,7 @@ async fn test_filter_schema_evolution_struct_fields() {
.await
.unwrap();

assert_batches_eq!(
assert_batches_sorted_eq!(
&[
"+--------------+-----------------------------+",
"| hostname | payload |",
Expand Down
4 changes: 2 additions & 2 deletions vortex-scan/src/arrow.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -128,7 +128,7 @@ mod tests {
use vortex_error::VortexResult;

use super::*;
use crate::test::SESSION;
use crate::test::SCAN_SESSION;

fn create_test_struct_array() -> VortexResult<ArrayRef> {
// Create Arrow arrays
Expand Down Expand Up @@ -166,7 +166,7 @@ mod tests {
let vortex_array = create_test_struct_array()?;
let schema = create_arrow_schema();
let data_type = DataType::Struct(schema.fields().clone());
let mut ctx = SESSION.create_execution_ctx();
let mut ctx = SCAN_SESSION.create_execution_ctx();

let batch = to_record_batch(vortex_array, &data_type, &mut ctx)?;
assert_eq!(batch.num_columns(), 2);
Expand Down
Loading