Skip to content

[test](mtmv) Inject stats to external table to make external table case stable #59721

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

Merged
morrySnow merged 1 commit into from
Jan 15, 2026
Merged

[test](mtmv) Inject stats to external table to make external table case stable #59721

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
42 changes: 7 additions & 35 deletions regression-test/data/external_table_p2/hudi/hudi_mtmv/test_hudi_olap_rewrite_mtmv.out
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,44 +1,16 @@
-- This file is automatically generated. You should know what you did if you want to edit this
-- !refresh_one_partition --
20250121171615893 20250121171615893_0_0 20250121171615893_3_1 par=a 58eabd3f-1996-4cb6-83e4-56fd11cb4e7d-0_0-30-108_20250121171615893.parquet 5 5 a \N \N
20250121171615893 20250121171615893_0_1 20250121171615893_5_0 par=a 58eabd3f-1996-4cb6-83e4-56fd11cb4e7d-0_0-30-108_20250121171615893.parquet 7 7 a \N \N
20250121171615893 20250121171615893_0_2 20250121171615893_7_0 par=a 58eabd3f-1996-4cb6-83e4-56fd11cb4e7d-0_0-30-108_20250121171615893.parquet 9 9 a \N \N
20250121171615893 20250121171615893_0_3 20250121171615893_0_0 par=a 58eabd3f-1996-4cb6-83e4-56fd11cb4e7d-0_0-30-108_20250121171615893.parquet 1 1 a 1 2
20250121171615893 20250121171615893_0_4 20250121171615893_2_0 par=a 58eabd3f-1996-4cb6-83e4-56fd11cb4e7d-0_0-30-108_20250121171615893.parquet 3 3 a \N \N
a 5

-- !refresh_one_partition_rewrite --
20250121171615893 20250121171615893_0_0 20250121171615893_3_1 par=a 58eabd3f-1996-4cb6-83e4-56fd11cb4e7d-0_0-30-108_20250121171615893.parquet 5 5 a \N \N
20250121171615893 20250121171615893_0_1 20250121171615893_5_0 par=a 58eabd3f-1996-4cb6-83e4-56fd11cb4e7d-0_0-30-108_20250121171615893.parquet 7 7 a \N \N
20250121171615893 20250121171615893_0_2 20250121171615893_7_0 par=a 58eabd3f-1996-4cb6-83e4-56fd11cb4e7d-0_0-30-108_20250121171615893.parquet 9 9 a \N \N
20250121171615893 20250121171615893_0_3 20250121171615893_0_0 par=a 58eabd3f-1996-4cb6-83e4-56fd11cb4e7d-0_0-30-108_20250121171615893.parquet 1 1 a 1 2
20250121171615893 20250121171615893_0_4 20250121171615893_2_0 par=a 58eabd3f-1996-4cb6-83e4-56fd11cb4e7d-0_0-30-108_20250121171615893.parquet 3 3 a \N \N
20250121171615893 20250121171615893_1_0 20250121171615893_4_0 par=b 7f98e9ac-bd11-48fd-ac80-9ca6dc1ddb34-0_1-30-109_20250121171615893.parquet 6 6 b \N \N
20250121171615893 20250121171615893_1_1 20250121171615893_6_0 par=b 7f98e9ac-bd11-48fd-ac80-9ca6dc1ddb34-0_1-30-109_20250121171615893.parquet 8 8 b \N \N
20250121171615893 20250121171615893_1_2 20250121171615893_1_0 par=b 7f98e9ac-bd11-48fd-ac80-9ca6dc1ddb34-0_1-30-109_20250121171615893.parquet 2 2 b \N \N
20250121171615893 20250121171615893_1_3 20250121171615893_3_0 par=b 7f98e9ac-bd11-48fd-ac80-9ca6dc1ddb34-0_1-30-109_20250121171615893.parquet 4 4 b \N \N
20250121171615893 20250121171615893_1_4 20250121171615893_7_1 par=b 7f98e9ac-bd11-48fd-ac80-9ca6dc1ddb34-0_1-30-109_20250121171615893.parquet 10 10 b \N \N
a 5
b 5

-- !refresh_auto --
20250121171615893 20250121171615893_0_0 20250121171615893_3_1 par=a 58eabd3f-1996-4cb6-83e4-56fd11cb4e7d-0_0-30-108_20250121171615893.parquet 5 5 a \N \N
20250121171615893 20250121171615893_0_1 20250121171615893_5_0 par=a 58eabd3f-1996-4cb6-83e4-56fd11cb4e7d-0_0-30-108_20250121171615893.parquet 7 7 a \N \N
20250121171615893 20250121171615893_0_2 20250121171615893_7_0 par=a 58eabd3f-1996-4cb6-83e4-56fd11cb4e7d-0_0-30-108_20250121171615893.parquet 9 9 a \N \N
20250121171615893 20250121171615893_0_3 20250121171615893_0_0 par=a 58eabd3f-1996-4cb6-83e4-56fd11cb4e7d-0_0-30-108_20250121171615893.parquet 1 1 a 1 2
20250121171615893 20250121171615893_0_4 20250121171615893_2_0 par=a 58eabd3f-1996-4cb6-83e4-56fd11cb4e7d-0_0-30-108_20250121171615893.parquet 3 3 a \N \N
20250121171615893 20250121171615893_1_0 20250121171615893_4_0 par=b 7f98e9ac-bd11-48fd-ac80-9ca6dc1ddb34-0_1-30-109_20250121171615893.parquet 6 6 b \N \N
20250121171615893 20250121171615893_1_1 20250121171615893_6_0 par=b 7f98e9ac-bd11-48fd-ac80-9ca6dc1ddb34-0_1-30-109_20250121171615893.parquet 8 8 b \N \N
20250121171615893 20250121171615893_1_2 20250121171615893_1_0 par=b 7f98e9ac-bd11-48fd-ac80-9ca6dc1ddb34-0_1-30-109_20250121171615893.parquet 2 2 b \N \N
20250121171615893 20250121171615893_1_3 20250121171615893_3_0 par=b 7f98e9ac-bd11-48fd-ac80-9ca6dc1ddb34-0_1-30-109_20250121171615893.parquet 4 4 b \N \N
20250121171615893 20250121171615893_1_4 20250121171615893_7_1 par=b 7f98e9ac-bd11-48fd-ac80-9ca6dc1ddb34-0_1-30-109_20250121171615893.parquet 10 10 b \N \N
a 5
b 5

-- !refresh_all_partition_rewrite --
20250121171615893 20250121171615893_0_0 20250121171615893_3_1 par=a 58eabd3f-1996-4cb6-83e4-56fd11cb4e7d-0_0-30-108_20250121171615893.parquet 5 5 a \N \N
20250121171615893 20250121171615893_0_1 20250121171615893_5_0 par=a 58eabd3f-1996-4cb6-83e4-56fd11cb4e7d-0_0-30-108_20250121171615893.parquet 7 7 a \N \N
20250121171615893 20250121171615893_0_2 20250121171615893_7_0 par=a 58eabd3f-1996-4cb6-83e4-56fd11cb4e7d-0_0-30-108_20250121171615893.parquet 9 9 a \N \N
20250121171615893 20250121171615893_0_3 20250121171615893_0_0 par=a 58eabd3f-1996-4cb6-83e4-56fd11cb4e7d-0_0-30-108_20250121171615893.parquet 1 1 a 1 2
20250121171615893 20250121171615893_0_4 20250121171615893_2_0 par=a 58eabd3f-1996-4cb6-83e4-56fd11cb4e7d-0_0-30-108_20250121171615893.parquet 3 3 a \N \N
20250121171615893 20250121171615893_1_0 20250121171615893_4_0 par=b 7f98e9ac-bd11-48fd-ac80-9ca6dc1ddb34-0_1-30-109_20250121171615893.parquet 6 6 b \N \N
20250121171615893 20250121171615893_1_1 20250121171615893_6_0 par=b 7f98e9ac-bd11-48fd-ac80-9ca6dc1ddb34-0_1-30-109_20250121171615893.parquet 8 8 b \N \N
20250121171615893 20250121171615893_1_2 20250121171615893_1_0 par=b 7f98e9ac-bd11-48fd-ac80-9ca6dc1ddb34-0_1-30-109_20250121171615893.parquet 2 2 b \N \N
20250121171615893 20250121171615893_1_3 20250121171615893_3_0 par=b 7f98e9ac-bd11-48fd-ac80-9ca6dc1ddb34-0_1-30-109_20250121171615893.parquet 4 4 b \N \N
20250121171615893 20250121171615893_1_4 20250121171615893_7_1 par=b 7f98e9ac-bd11-48fd-ac80-9ca6dc1ddb34-0_1-30-109_20250121171615893.parquet 10 10 b \N \N
a 5
b 5

83 changes: 78 additions & 5 deletions regression-test/suites/external_table_p2/hudi/hudi_mtmv/test_hudi_olap_rewrite_mtmv.groovy
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,7 @@ suite("test_hudi_olap_rewrite_mtmv", "p2,external,hudi,external_remote,external_
String props = context.config.otherConfigs.get("hudiEmrCatalog")

sql """set materialized_view_rewrite_enable_contain_external_table=true;"""
String mvSql = "SELECT * FROM ${catalogName}.`hudi_mtmv_regression_test`.hudi_table_1 a left join ${tableName} b on a.id=b.user_id;";
String mvSql = "SELECT par, count(*) FROM ${catalogName}.`hudi_mtmv_regression_test`.hudi_table_1 a left join ${tableName} b on a.id=b.user_id group by par;";

sql """drop catalog if exists ${catalogName}"""
sql """CREATE CATALOG if not exists ${catalogName} PROPERTIES (
Expand All @@ -55,6 +55,82 @@ suite("test_hudi_olap_rewrite_mtmv", "p2,external,hudi,external_remote,external_

sql """analyze table ${catalogName}.`hudi_mtmv_regression_test`.hudi_table_1 with sync"""
sql """alter table ${catalogName}.`hudi_mtmv_regression_test`.hudi_table_1 modify column par set stats ('row_count'='10');"""
sql """
alter table ${catalogName}.hudi_mtmv_regression_test.hudi_table_1
modify column age set stats (
"ndv"="10",
"num_nulls"="0",
"min_value"="1",
"max_value"="10",
"row_count"="10"
);
"""

sql """
alter table ${catalogName}.hudi_mtmv_regression_test.hudi_table_1
modify column _hoodie_record_key set stats (
"ndv"="10",
"num_nulls"="0",
"min_value"="20250121171615893_0_0",
"max_value"="20250121171615893_7_1",
"row_count"="10"
);
"""

sql """
alter table ${catalogName}.hudi_mtmv_regression_test.hudi_table_1
modify column id set stats (
"ndv"="10",
"num_nulls"="0",
"min_value"="1",
"max_value"="10",
"row_count"="10"
);
"""

sql """
alter table ${catalogName}.hudi_mtmv_regression_test.hudi_table_1
modify column _hoodie_file_name set stats (
"ndv"="2",
"num_nulls"="0",
"min_value"="58eabd3f-1996-4cb6-83e4-56fd11cb4e7d-0_0-30-108_20250121171615893.parquet",
"max_value"="7f98e9ac-bd11-48fd-ac80-9ca6dc1ddb34-0_1-30-109_20250121171615893.parquet",
"row_count"="10"
);
"""

sql """
alter table ${catalogName}.hudi_mtmv_regression_test.hudi_table_1
modify column _hoodie_partition_path set stats (
"ndv"="2",
"num_nulls"="0",
"min_value"="par=a",
"max_value"="par=b",
"row_count"="10"
);
"""

sql """
alter table ${catalogName}.hudi_mtmv_regression_test.hudi_table_1
modify column _hoodie_commit_seqno set stats (
"ndv"="10",
"num_nulls"="0",
"min_value"="20250121171615893_0_0",
"max_value"="20250121171615893_1_4",
"row_count"="10"
);
"""

sql """
alter table ${catalogName}.hudi_mtmv_regression_test.hudi_table_1
modify column _hoodie_commit_time set stats (
"ndv"="1",
"num_nulls"="0",
"min_value"="20250121171615893",
"max_value"="20250121171615893",
"row_count"="10"
);
"""

sql """drop materialized view if exists ${mvName};"""

Expand All @@ -79,15 +155,12 @@ suite("test_hudi_olap_rewrite_mtmv", "p2,external,hudi,external_remote,external_
waitingMTMVTaskFinishedByMvName(mvName)
order_qt_refresh_one_partition "SELECT * FROM ${mvName} "

def explainOnePartition = sql """ explain ${mvSql} """
logger.info("explainOnePartition: " + explainOnePartition.toString())
assertTrue(explainOnePartition.toString().contains("VUNION"))
order_qt_refresh_one_partition_rewrite "${mvSql}"

mv_rewrite_success("${mvSql}", "${mvName}")

// select p_b should not rewrite
mv_not_part_in("SELECT * FROM ${catalogName}.`hudi_mtmv_regression_test`.hudi_table_1 a left join ${tableName} b on a.id=b.user_id where a.par='b';", "${mvName}")
mv_not_part_in("SELECT par, count(*) FROM ${catalogName}.`hudi_mtmv_regression_test`.hudi_table_1 a left join ${tableName} b on a.id=b.user_id where a.par='b' group by par;", "${mvName}")

//refresh auto
sql """
Expand Down