xudong963 opened a new pull request, #15761:
URL: https://github.com/apache/datafusion/pull/15761
## Which issue does this PR close?
<!--
We generally require a GitHub issue to be filed for all bug fixes and
enhancements and this helps us generate change logs for our releases. You can
link an issue to this PR using the GitHub syntax. For example `Closes #123`
indicates that this PR will close issue #123.
-->
- Closes #.
## Rationale for this change
<!--
Why are you proposing this change? If this is already explained clearly in
the issue then this section is not needed.
Explaining clearly why changes are proposed helps reviewers understand your
changes and offer better suggestions for fixes.
-->
In our prod, we found that the `optimize_projection` is slow when the number
of columns is large, and `is_projection_unnecessary` is a bottleneck. After
checking the method, I found we can improve it.
Here is the benchmark:
### Result
v1 is the old and v2 is the optimized version
```
Projection Optimization/v1_one_non_trivial
time: [92.212 µs 93.578 µs 95.428 µs]
Found 16 outliers among 100 measurements (16.00%)
2 (2.00%) high mild
14 (14.00%) high severe
Projection Optimization/v2_one_non_trivial
time: [242.52 ns 248.62 ns 256.51 ns]
Found 9 outliers among 100 measurements (9.00%)
4 (4.00%) high mild
5 (5.00%) high severe
```
### Benchmark code
1000 exprs in Projection, and one of them is non-trival expr.
```rust
use arrow::datatypes::{DataType, Field, Schema};
use criterion::{criterion_group, criterion_main, Criterion};
use datafusion_expr::{binary_expr, col,Operator, Expr, LogicalPlan,
table_scan};
use datafusion_optimizer::optimize_projections::{is_projection_unnecessary,
is_projection_unnecessary_v2};
pub fn test_table_scan_fields() -> Vec<Field> {
vec![
Field::new("a", DataType::UInt32, false),
Field::new("b", DataType::UInt32, false),
Field::new("c", DataType::UInt32, false),
]
}
pub fn test_table_scan_with_name(name: &str) ->
datafusion_common::Result<LogicalPlan> {
let schema = Schema::new(test_table_scan_fields());
table_scan(Some(name), &schema, None)?.build()
}
/// some tests share a common table
pub fn test_table_scan() -> datafusion_common::Result<LogicalPlan> {
test_table_scan_with_name("test")
}
fn create_mixed_expressions(count: usize) -> Vec<Expr> {
let mut exprs = Vec::with_capacity(count);
for i in 0..count {
// Most expressions are just column references
if i != count / 2 {
match i % 3 {
0 => exprs.push(col("a")),
1 => exprs.push(col("b")),
_ => exprs.push(col("c")),
}
} else {
// One non-trivial expression (binary operation)
exprs.push(binary_expr(col("a"), Operator::Plus, col("b")));
}
}
exprs
}
fn benchmark_projections(c: &mut Criterion) {
let input_plan = test_table_scan().unwrap();
let one_non_trivial = create_mixed_expressions(1000);
let mut group = c.benchmark_group("Projection Optimization");
// Benchmark with one non-trivial expression
group.bench_function("v1_one_non_trivial", |b| {
b.iter(|| is_projection_unnecessary(&input_plan, &one_non_trivial));
});
group.bench_function("v2_one_non_trivial", |b| {
b.iter(|| is_projection_unnecessary_v2(&input_plan,
&one_non_trivial));
});
group.finish();
}
criterion_group!(benches, benchmark_projections);
criterion_main!(benches);
```
## What changes are included in this PR?
<!--
There is no need to duplicate the description in the issue here but it is
sometimes worth providing a summary of the individual changes in this PR.
-->
## Are these changes tested?
<!--
We typically require tests for all PRs in order to:
1. Prevent the code from being accidentally broken by subsequent changes
2. Serve as another way to document the expected behavior of the code
If tests are not included in your PR, please explain why (for example, are
they covered by existing tests)?
-->
Yes
## Are there any user-facing changes?
<!--
If there are user-facing changes then we may require documentation to be
updated before approving the PR.
-->
<!--
If there are any breaking changes to public APIs, please add the `api
change` label.
-->
--
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]
