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

feat: dist plan optimize part 2 #2543

Merged
merged 6 commits into from
Oct 9, 2023
Merged

feat: dist plan optimize part 2 #2543

Show file tree
Hide file tree
Changes from 5 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
ab943ed
allow udf and scalar fn
waynexia Sep 28, 2023
244e51c
put CountWildcardRule before dist planner
waynexia Oct 7, 2023
6073432
Merge branch 'dev' into opt-query-att-2
waynexia Oct 8, 2023
d1c9813
bump datafusion to fix first_value/last_value
waynexia Oct 8, 2023
45a134d
update sqlness result
waynexia Oct 8, 2023
2b84393
use retain instead
waynexia Oct 8, 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
18 changes: 9 additions & 9 deletions Cargo.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

14 changes: 7 additions & 7 deletions Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,13 +68,13 @@ arrow-schema = { version = "43.0", features = ["serde"] }
async-stream = "0.3"
async-trait = "0.1"
chrono = { version = "0.4", features = ["serde"] }
datafusion = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "c0b0fca548e99d020c76e1a1cd7132aab26000e1" }
datafusion-common = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "c0b0fca548e99d020c76e1a1cd7132aab26000e1" }
datafusion-expr = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "c0b0fca548e99d020c76e1a1cd7132aab26000e1" }
datafusion-optimizer = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "c0b0fca548e99d020c76e1a1cd7132aab26000e1" }
datafusion-physical-expr = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "c0b0fca548e99d020c76e1a1cd7132aab26000e1" }
datafusion-sql = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "c0b0fca548e99d020c76e1a1cd7132aab26000e1" }
datafusion-substrait = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "c0b0fca548e99d020c76e1a1cd7132aab26000e1" }
datafusion = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "b6f3b28b6fe91924cc8dd3d83726b766f2a706ec" }
datafusion-common = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "b6f3b28b6fe91924cc8dd3d83726b766f2a706ec" }
datafusion-expr = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "b6f3b28b6fe91924cc8dd3d83726b766f2a706ec" }
datafusion-optimizer = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "b6f3b28b6fe91924cc8dd3d83726b766f2a706ec" }
datafusion-physical-expr = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "b6f3b28b6fe91924cc8dd3d83726b766f2a706ec" }
datafusion-sql = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "b6f3b28b6fe91924cc8dd3d83726b766f2a706ec" }
datafusion-substrait = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "b6f3b28b6fe91924cc8dd3d83726b766f2a706ec" }
derive_builder = "0.12"
futures = "0.3"
futures-util = "0.3"
Expand Down
6 changes: 3 additions & 3 deletions src/query/src/dist_plan/commutativity.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -140,7 +140,9 @@ impl Categorizer {
| Expr::Negative(_)
| Expr::Between(_)
| Expr::Sort(_)
| Expr::Exists(_) => Commutativity::Commutative,
| Expr::Exists(_)
| Expr::ScalarFunction(_)
| Expr::ScalarUDF(_) => Commutativity::Commutative,

Expr::Like(_)
| Expr::SimilarTo(_)
Expand All @@ -150,8 +152,6 @@ impl Categorizer {
| Expr::Case(_)
| Expr::Cast(_)
| Expr::TryCast(_)
| Expr::ScalarFunction(_)
| Expr::ScalarUDF(_)
| Expr::AggregateFunction(_)
| Expr::WindowFunction(_)
| Expr::AggregateUDF(_)
Expand Down
18 changes: 17 additions & 1 deletion src/query/src/query_engine/state.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,8 @@ use datafusion::physical_optimizer::PhysicalOptimizerRule;
use datafusion::physical_plan::ExecutionPlan;
use datafusion::physical_planner::{DefaultPhysicalPlanner, ExtensionPlanner, PhysicalPlanner};
use datafusion_expr::LogicalPlan as DfLogicalPlan;
use datafusion_optimizer::analyzer::Analyzer;
use datafusion_optimizer::analyzer::count_wildcard_rule::CountWildcardRule;
use datafusion_optimizer::analyzer::{Analyzer, AnalyzerRule};
use datafusion_optimizer::optimizer::Optimizer;
use promql::extension_plan::PromExtensionPlanner;
use substrait::extension_serializer::ExtensionSerializer;
Expand Down Expand Up @@ -88,6 +89,8 @@ impl QueryEngineState {
}
analyzer.rules.insert(0, Arc::new(TypeConversionRule));
analyzer.rules.insert(0, Arc::new(StringNormalizationRule));
Self::remove_analyzer_rule(&mut analyzer.rules, CountWildcardRule {}.name());
killme2008 marked this conversation as resolved.
Show resolved Hide resolved
analyzer.rules.insert(0, Arc::new(CountWildcardRule {}));
let mut optimizer = Optimizer::new();
optimizer.rules.push(Arc::new(OrderHintRule));

Expand Down Expand Up @@ -132,6 +135,19 @@ impl QueryEngineState {
}
}

fn remove_analyzer_rule(rules: &mut Vec<Arc<dyn AnalyzerRule + Send + Sync>>, name: &str) {
let mut index_to_move = None;
for (i, rule) in rules.iter().enumerate() {
if rule.name() == name {
index_to_move = Some(i);
break;
}
}
if let Some(index) = index_to_move {
let _ = rules.remove(index);
}
}

fn remove_physical_optimize_rule(
rules: &mut Vec<Arc<dyn PhysicalOptimizerRule + Send + Sync>>,
name: &str,
Expand Down
11 changes: 2 additions & 9 deletions tests/cases/distributed/explain/single_partition.result
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,15 +12,8 @@ EXPLAIN SELECT COUNT(*) FROM single_partition;
+-+-+
| plan_type_| plan_|
+-+-+
| logical_plan_| Aggregate: groupBy=[[]], aggr=[[COUNT(UInt8(1))]]_|
|_|_Projection:_|
|_|_MergeScan [is_placeholder=false]_|
| physical_plan | AggregateExec: mode=Final, gby=[], aggr=[COUNT(UInt8(1))]_|
|_|_CoalescePartitionsExec_|
|_|_AggregateExec: mode=Partial, gby=[], aggr=[COUNT(UInt8(1))]_|
|_|_RepartitionExec: partitioning=REDACTED
|_|_ProjectionExec: expr=[]_|
|_|_MergeScanExec: REDACTED
| logical_plan_| MergeScan [is_placeholder=false]_|
| physical_plan | MergeScanExec: REDACTED
|_|_|
+-+-+

Expand Down
Loading