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

chore(planner): refine project set cardinality #16944

Merged
merged 4 commits into from
Nov 26, 2024
Merged

chore(planner): refine project set cardinality #16944

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
3e75782
chore(planner): refine project set cardinality
Dousir9 Nov 26, 2024
ad0ad0d
chore(test): update sqllogictest
Dousir9 Nov 26, 2024
2b344df
chore(test): update sqllogictest
Dousir9 Nov 26, 2024
86d62f6
Merge branch 'main' into refine_project_set_cardinality
Dousir9 Nov 26, 2024
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
2 changes: 2 additions & 0 deletions src/query/sql/src/planner/plans/project_set.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,8 @@ impl ProjectSet {
pub fn derive_project_set_stats(&self, input_stat: &mut StatInfo) -> Result<Arc<StatInfo>> {
// ProjectSet is set-returning functions, precise_cardinality set None
input_stat.statistics.precise_cardinality = None;
// We assume that the SRF function will expand by at least x3 per row.
input_stat.cardinality *= 3.0;
Ok(Arc::new(input_stat.clone()))
}
}
Expand Down
43 changes: 40 additions & 3 deletions tests/sqllogictests/suites/mode/standalone/explain/project_set.test
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,7 @@ AggregateFinal
├── estimated rows: 1.00
└── ProjectSet
├── output columns: [unnest(fold_count.id (#0)) (#2)]
├── estimated rows: 1.00
├── estimated rows: 3.00
├── set returning functions: unnest(fold_count.id (#0))
└── TableScan
├── table: default.default.fold_count
Expand Down Expand Up @@ -54,7 +54,7 @@ explain select number from (select unnest([1,2,3]), number from numbers(10)) t
----
ProjectSet
├── output columns: [numbers.number (#0), unnest([1, 2, 3]) (#1)]
├── estimated rows: 10.00
├── estimated rows: 30.00
├── set returning functions: unnest([1, 2, 3])
└── TableScan
├── table: default.system.numbers
Expand All @@ -71,7 +71,7 @@ explain select number from (select unnest([1,2,3,number]), number from numbers(1
----
ProjectSet
├── output columns: [numbers.number (#0), unnest(array(1, 2, 3, numbers.number (#0))) (#1)]
├── estimated rows: 10.00
├── estimated rows: 30.00
├── set returning functions: unnest(CAST(array(1, 2, 3, numbers.number (#0)) AS Array(UInt64 NULL)))
└── TableScan
├── table: default.system.numbers
Expand Down Expand Up @@ -131,5 +131,42 @@ EvalScalar
├── push downs: [filters: [], limit: NONE]
└── estimated rows: 0.00

query T
explain select * from (select unnest([1,2,3]), number from numbers(10)) t1(a) inner join (select * from numbers(15)) t2(a) on t1.a = t2.a;
----
HashJoin
├── output columns: [numbers.number (#0), a (#2), numbers.number (#3)]
├── join type: INNER
├── build keys: [CAST(t2.a (#3) AS UInt64 NULL)]
├── probe keys: [CAST(t1.a (#2) AS UInt64 NULL)]
├── filters: []
├── estimated rows: 450.00
├── TableScan(Build)
│ ├── table: default.system.numbers
│ ├── output columns: [number (#3)]
│ ├── read rows: 15
│ ├── read size: < 1 KiB
│ ├── partitions total: 1
│ ├── partitions scanned: 1
│ ├── push downs: [filters: [], limit: NONE]
│ └── estimated rows: 15.00
└── EvalScalar(Probe)
├── output columns: [numbers.number (#0), a (#2)]
├── expressions: [get(1)(unnest([1, 2, 3]) (#1))]
├── estimated rows: 30.00
└── ProjectSet
├── output columns: [numbers.number (#0), unnest([1, 2, 3]) (#1)]
├── estimated rows: 30.00
├── set returning functions: unnest([1, 2, 3])
└── TableScan
├── table: default.system.numbers
├── output columns: [number (#0)]
├── read rows: 10
├── read size: < 1 KiB
├── partitions total: 1
├── partitions scanned: 1
├── push downs: [filters: [], limit: NONE]
└── estimated rows: 10.00

statement ok
drop database project_set
10 changes: 5 additions & 5 deletions ...ictests/suites/mode/standalone/explain/push_down_filter/push_down_filter_project_set.test
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,14 +14,14 @@ explain select name, json_path_query(details, '$.features.*') as all_features, j
EvalScalar
├── output columns: [products.name (#0), all_features (#3), first_feature (#4)]
├── expressions: [get(1)(json_path_query(products.details (#1), '$.features.*') (#2)), json_path_query_first(products.details (#1), '$.features.*')]
├── estimated rows: 0.12
├── estimated rows: 0.36
└── Filter
├── output columns: [products.name (#0), products.details (#1), json_path_query(products.details (#1), '$.features.*') (#2)]
├── filters: [is_true(TRY_CAST(get(1)(json_path_query(products.details (#1), '$.features.*') (#2)) AS String NULL) = '512GB')]
├── estimated rows: 0.12
├── estimated rows: 0.36
└── ProjectSet
├── output columns: [products.name (#0), products.details (#1), json_path_query(products.details (#1), '$.features.*') (#2)]
├── estimated rows: 0.60
├── estimated rows: 1.80
├── set returning functions: json_path_query(products.details (#1), '$.features.*')
└── Filter
├── output columns: [products.name (#0), products.details (#1)]
Expand Down Expand Up @@ -49,10 +49,10 @@ explain select name, json_path_query(details, '$.features.*') as all_features, j
EvalScalar
├── output columns: [products.name (#0), all_features (#3), first_feature (#4)]
├── expressions: [get(1)(json_path_query(products.details (#1), '$.features.*') (#2)), json_path_query_first(products.details (#1), '$.features.*')]
├── estimated rows: 0.60
├── estimated rows: 1.80
└── ProjectSet
├── output columns: [products.name (#0), products.details (#1), json_path_query(products.details (#1), '$.features.*') (#2)]
├── estimated rows: 0.60
├── estimated rows: 1.80
├── set returning functions: json_path_query(products.details (#1), '$.features.*')
└── Filter
├── output columns: [products.name (#0), products.details (#1)]
Expand Down
43 changes: 40 additions & 3 deletions tests/sqllogictests/suites/mode/standalone/explain_native/project_set.test
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,7 @@ AggregateFinal
├── estimated rows: 1.00
└── ProjectSet
├── output columns: [unnest(fold_count.id (#0)) (#2)]
├── estimated rows: 1.00
├── estimated rows: 3.00
├── set returning functions: unnest(fold_count.id (#0))
└── TableScan
├── table: default.default.fold_count
Expand Down Expand Up @@ -54,7 +54,7 @@ explain select number from (select unnest([1,2,3]), number from numbers(10)) t
----
ProjectSet
├── output columns: [numbers.number (#0), unnest([1, 2, 3]) (#1)]
├── estimated rows: 10.00
├── estimated rows: 30.00
├── set returning functions: unnest([1, 2, 3])
└── TableScan
├── table: default.system.numbers
Expand All @@ -71,7 +71,7 @@ explain select number from (select unnest([1,2,3,number]), number from numbers(1
----
ProjectSet
├── output columns: [numbers.number (#0), unnest(array(1, 2, 3, numbers.number (#0))) (#1)]
├── estimated rows: 10.00
├── estimated rows: 30.00
├── set returning functions: unnest(CAST(array(1, 2, 3, numbers.number (#0)) AS Array(UInt64 NULL)))
└── TableScan
├── table: default.system.numbers
Expand All @@ -83,5 +83,42 @@ ProjectSet
├── push downs: [filters: [], limit: NONE]
└── estimated rows: 10.00

query T
explain select * from (select unnest([1,2,3]), number from numbers(10)) t1(a) inner join (select * from numbers(15)) t2(a) on t1.a = t2.a;
----
HashJoin
├── output columns: [numbers.number (#0), a (#2), numbers.number (#3)]
├── join type: INNER
├── build keys: [CAST(t2.a (#3) AS UInt64 NULL)]
├── probe keys: [CAST(t1.a (#2) AS UInt64 NULL)]
├── filters: []
├── estimated rows: 450.00
├── TableScan(Build)
│ ├── table: default.system.numbers
│ ├── output columns: [number (#3)]
│ ├── read rows: 15
│ ├── read size: < 1 KiB
│ ├── partitions total: 1
│ ├── partitions scanned: 1
│ ├── push downs: [filters: [], limit: NONE]
│ └── estimated rows: 15.00
└── EvalScalar(Probe)
├── output columns: [numbers.number (#0), a (#2)]
├── expressions: [get(1)(unnest([1, 2, 3]) (#1))]
├── estimated rows: 30.00
└── ProjectSet
├── output columns: [numbers.number (#0), unnest([1, 2, 3]) (#1)]
├── estimated rows: 30.00
├── set returning functions: unnest([1, 2, 3])
└── TableScan
├── table: default.system.numbers
├── output columns: [number (#0)]
├── read rows: 10
├── read size: < 1 KiB
├── partitions total: 1
├── partitions scanned: 1
├── push downs: [filters: [], limit: NONE]
└── estimated rows: 10.00

statement ok
drop database project_set
10 changes: 5 additions & 5 deletions .../suites/mode/standalone/explain_native/push_down_filter/push_down_filter_project_set.test
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,14 +14,14 @@ explain select name, json_path_query(details, '$.features.*') as all_features, j
EvalScalar
├── output columns: [products.name (#0), all_features (#3), first_feature (#4)]
├── expressions: [get(1)(json_path_query(products.details (#1), '$.features.*') (#2)), json_path_query_first(products.details (#1), '$.features.*')]
├── estimated rows: 0.12
├── estimated rows: 0.36
└── Filter
├── output columns: [products.name (#0), products.details (#1), json_path_query(products.details (#1), '$.features.*') (#2)]
├── filters: [is_true(TRY_CAST(get(1)(json_path_query(products.details (#1), '$.features.*') (#2)) AS String NULL) = '512GB')]
├── estimated rows: 0.12
├── estimated rows: 0.36
└── ProjectSet
├── output columns: [products.name (#0), products.details (#1), json_path_query(products.details (#1), '$.features.*') (#2)]
├── estimated rows: 0.60
├── estimated rows: 1.80
├── set returning functions: json_path_query(products.details (#1), '$.features.*')
└── TableScan
├── table: default.default.products
Expand All @@ -45,10 +45,10 @@ explain select name, json_path_query(details, '$.features.*') as all_features, j
EvalScalar
├── output columns: [products.name (#0), all_features (#3), first_feature (#4)]
├── expressions: [get(1)(json_path_query(products.details (#1), '$.features.*') (#2)), json_path_query_first(products.details (#1), '$.features.*')]
├── estimated rows: 0.60
├── estimated rows: 1.80
└── ProjectSet
├── output columns: [products.name (#0), products.details (#1), json_path_query(products.details (#1), '$.features.*') (#2)]
├── estimated rows: 0.60
├── estimated rows: 1.80
├── set returning functions: json_path_query(products.details (#1), '$.features.*')
└── TableScan
├── table: default.default.products
Expand Down