Skip to content

Commit

Permalink
add regression case: disable join reorder if there are invalid stats
Browse files Browse the repository at this point in the history
  • Loading branch information
@englefly
englefly committed Nov 8, 2024
1 parent d3d8a21 commit 5b3dfde
Show file tree
Hide file tree
Showing 2 changed files with 95 additions and 83 deletions.
46 changes: 46 additions & 0 deletions regression-test/data/nereids_p0/stats/invalid_stats.out
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,46 @@
-- This file is automatically generated. You should know what you did if you want to edit this
-- !reorder_1 --
PhysicalResultSink
--PhysicalProject
----hashJoin[INNER_JOIN broadcast] hashCondition=((region.r_regionkey = nation.n_regionkey)) otherCondition=()
------PhysicalProject
--------PhysicalOlapScan[nation]
------PhysicalProject
--------PhysicalOlapScan[region]

-- !ndv_min_max_invalid --
PhysicalResultSink
--PhysicalProject
----hashJoin[INNER_JOIN broadcast] hashCondition=((region.r_regionkey = nation.n_regionkey)) otherCondition=()
------PhysicalProject
--------PhysicalOlapScan[region]
------PhysicalProject
--------PhysicalOlapScan[nation]

-- !reorder_2 --
PhysicalResultSink
--PhysicalProject
----hashJoin[INNER_JOIN broadcast] hashCondition=((region.r_regionkey = nation.n_regionkey)) otherCondition=()
------PhysicalProject
--------PhysicalOlapScan[nation]
------PhysicalProject
--------PhysicalOlapScan[region]

-- !order_3 --
PhysicalResultSink
--PhysicalProject
----hashJoin[INNER_JOIN broadcast] hashCondition=((region.r_regionkey = nation.n_regionkey)) otherCondition=()
------PhysicalProject
--------PhysicalOlapScan[nation]
------PhysicalProject
--------PhysicalOlapScan[region]

-- !ndv_row_invalid --
PhysicalResultSink
--PhysicalProject
----hashJoin[INNER_JOIN broadcast] hashCondition=((region.r_regionkey = nation.n_regionkey)) otherCondition=()
------PhysicalProject
--------PhysicalOlapScan[region]
------PhysicalProject
--------PhysicalOlapScan[nation]

132 changes: 49 additions & 83 deletions regression-test/suites/nereids_p0/stats/invalid_stats.groovy
View file
Original file line number Diff line number Diff line change
Expand Up @@ -16,96 +16,62 @@
// under the License.

suite("invalid_stats") {
// multi_sql """
// set global enable_auto_analyze=false;
// SET enable_nereids_planner=true;
// SET enable_fallback_to_original_planner=false;
// set disable_nereids_rules=PRUNE_EMPTY_PARTITION;
multi_sql """
set global enable_auto_analyze=false;
SET enable_nereids_planner=true;
SET enable_fallback_to_original_planner=false;
set disable_nereids_rules=PRUNE_EMPTY_PARTITION;
// drop table if exists region;
// CREATE TABLE region (
// r_regionkey int NOT NULL,
// r_name VARCHAR(25) NOT NULL,
// r_comment VARCHAR(152)
// )ENGINE=OLAP
// DUPLICATE KEY(`r_regionkey`)
// COMMENT "OLAP"
// DISTRIBUTED BY HASH(`r_regionkey`) BUCKETS 1
// PROPERTIES (
// "replication_num" = "1"
// );
drop table if exists region;
CREATE TABLE region (
r_regionkey int NOT NULL,
r_name VARCHAR(25) NOT NULL,
r_comment VARCHAR(152)
)ENGINE=OLAP
DUPLICATE KEY(`r_regionkey`)
COMMENT "OLAP"
DISTRIBUTED BY HASH(`r_regionkey`) BUCKETS 1
PROPERTIES (
"replication_num" = "1"
);
// drop table if exists nation;
// CREATE TABLE `nation` (
// `n_nationkey` int(11) NOT NULL,
// `n_name` varchar(25) NOT NULL,
// `n_regionkey` int(11) NOT NULL,
// `n_comment` varchar(152) NULL
// ) ENGINE=OLAP
// DUPLICATE KEY(`N_NATIONKEY`)
// COMMENT "OLAP"
// DISTRIBUTED BY HASH(`N_NATIONKEY`) BUCKETS 1
// PROPERTIES (
// "replication_num" = "1"
// );
// alter table nation modify column n_nationkey set stats ('ndv'='25', 'num_nulls'='0', 'min_value'='0', 'max_value'='24', 'row_count'='25');
drop table if exists nation;
CREATE TABLE `nation` (
`n_nationkey` int(11) NOT NULL,
`n_name` varchar(25) NOT NULL,
`n_regionkey` int(11) NOT NULL,
`n_comment` varchar(152) NULL
) ENGINE=OLAP
DUPLICATE KEY(`N_NATIONKEY`)
COMMENT "OLAP"
DISTRIBUTED BY HASH(`N_NATIONKEY`) BUCKETS 1
PROPERTIES (
"replication_num" = "1"
);
alter table nation modify column n_nationkey set stats ('ndv'='25', 'num_nulls'='0', 'min_value'='0', 'max_value'='24', 'row_count'='25');
// alter table nation modify column n_regionkey set stats ('ndv'='5', 'num_nulls'='0', 'min_value'='0', 'max_value'='4', 'row_count'='25');
alter table region modify column r_regionkey set stats ('ndv'='5', 'num_nulls'='0', 'min_value'='0', 'max_value'='4', 'row_count'='5');
// """
"""

// explain {
// sql "select * from region"
// notContains("join reorder with unknown column statistics")
// }

// explain {
// sql "select * from region where r_regionkey=1"
// contains("join reorder with unknown column statistics")
// }

// explain {
// sql "select r_regionkey from region group by r_regionkey"
// contains("join reorder with unknown column statistics")
// }

// explain {
// sql "select r_regionkey from region join nation on r_regionkey=n_regionkey"
// contains("join reorder with unknown column statistics")
// }

// sql "alter table region modify column r_regionkey set stats ('ndv'='5', 'num_nulls'='0', 'min_value'='0', 'max_value'='4', 'row_count'='5');"
qt_reorder_1 "explain shape plan select r_regionkey from region join nation on r_regionkey=n_regionkey"

sql "alter table region modify column r_regionkey set stats ('ndv'='0', 'num_nulls'='0', 'min_value'='0', 'max_value'='4', 'row_count'='0');"

// explain {
// sql "select * from region where r_regionkey=1"
// notContains("join reorder with unknown column statistics")
// }

// explain {
// sql "select r_regionkey from region group by r_regionkey"
// notContains("join reorder with unknown column statistics")
// }

// explain {
// sql "select r_regionkey from region join nation on r_regionkey=n_regionkey"
// notContains("join reorder with unknown column statistics")
// }
// r_regionkey stats invalid: ndv=0, but min or max is not null
qt_ndv_min_max_invalid "explain shape plan select r_regionkey from region join nation on r_regionkey=n_regionkey"

// inject normal stats and check join order is nation-region
sql "alter table region modify column r_regionkey set stats ('ndv'='5', 'num_nulls'='0', 'min_value'='0', 'max_value'='4', 'row_count'='5');"

qt_reorder_2 "explain shape plan select r_regionkey from region join nation on r_regionkey=n_regionkey"

// explain {
// sql "select r_name from region join nation on r_regionkey=n_regionkey"
// notContains("join reorder with unknown column statistics")
// }
// r_regionkey stats invalid: ndv > 10*row
sql "alter table region modify column r_regionkey set stats ('ndv'='10', 'num_nulls'='0', 'min_value'='0', 'max_value'='4', 'row_count'='1');"
qt_order_3 "explain shape plan select r_regionkey from region join nation on r_regionkey=n_regionkey"

sql "alter table region modify column r_regionkey set stats ('ndv'='11', 'num_nulls'='0', 'min_value'='0', 'max_value'='4', 'row_count'='1');"
qt_ndv_row_invalid "explain shape plan select r_regionkey from region join nation on r_regionkey=n_regionkey"

// explain {
// sql """
// select r_name
// from (select r_name, r_regionkey + 1 x from region) T join nation on T.x=n_regionkey
// """
// notContains("join reorder with unknown column statistics")
// }
}
// disable jo: alter table region modify column r_regionkey set stats ('ndv'='0', 'num_nulls'='0', 'min_value'='0', 'max_value'='4', 'row_count'='0');
// disable jo: alter table region modify column r_regionkey set stats ('ndv'='11', 'num_nulls'='0', 'min_value'='0', 'max_value'='4', 'row_count'='1');

// alter table region modify column r_regionkey set stats ('ndv'='10', 'num_nulls'='0', 'min_value'='0', 'max_value'='4', 'row_count'='1');

0 comments on commit 5b3dfde

Please sign in to comment.