[opt](tools) update tools schema (#36114)

pick from master #35873

Update tpcds tools table customer_demographics's bucket column as its
primary key column, avoid performance issue due to data skew.
This commit is contained in:
xzj7019
2024-06-19 12:23:48 +08:00
committed by GitHub
parent 97ac46d2be
commit df22344550
4 changed files with 4 additions and 4 deletions

View File

@ -27,7 +27,7 @@ CREATE TABLE IF NOT EXISTS customer_demographics (
cd_dep_college_count integer
)
DUPLICATE KEY(cd_demo_sk)
DISTRIBUTED BY HASH(cd_gender) BUCKETS 12
DISTRIBUTED BY HASH(cd_demo_sk) BUCKETS 12
PROPERTIES (
"replication_num" = "1"
);

View File

@ -27,7 +27,7 @@ CREATE TABLE IF NOT EXISTS customer_demographics (
cd_dep_college_count integer
)
DUPLICATE KEY(cd_demo_sk)
DISTRIBUTED BY HASH(cd_gender) BUCKETS 12
DISTRIBUTED BY HASH(cd_demo_sk) BUCKETS 12
PROPERTIES (
"replication_num" = "1"
);

View File

@ -27,7 +27,7 @@ CREATE TABLE IF NOT EXISTS customer_demographics (
cd_dep_college_count integer
)
DUPLICATE KEY(cd_demo_sk)
DISTRIBUTED BY HASH(cd_gender) BUCKETS 12
DISTRIBUTED BY HASH(cd_demo_sk) BUCKETS 12
PROPERTIES (
"replication_num" = "1"
);

View File

@ -27,7 +27,7 @@ CREATE TABLE IF NOT EXISTS customer_demographics (
cd_dep_college_count integer
)
DUPLICATE KEY(cd_demo_sk)
DISTRIBUTED BY HASH(cd_gender) BUCKETS 12
DISTRIBUTED BY HASH(cd_demo_sk) BUCKETS 12
PROPERTIES (
"replication_num" = "1"
);