- TPC-H
- New TPC Benchmarks for Decision Support and Web Commerce (Poess et. al., 2000)
- TPC-H Analyzed: Hidden Messages and Lessons Learned from an Influential Benchmark (Boncz et. al.), 2013
- Quantifying TPC-H Choke Points and Their Optimizations (Dresseler et. al.), 2020
数据生成与导入
git clone https://github.com/gregrahn/tpch-kit.git
cd tpch-kit/dbgen
make
-s 用于指定缩放因子。例如,使用 -s 100 时,将为表 ‘lineitem’ 生成 6 亿行。
./dbgen -s 100
for i in $(seq 1 8); do
./dbgen -s 100 -C 8 -S $i &
done
wait
| Table | size (in rows) | size (compressed in ClickHouse) |
|---|---|---|
| nation | 25 | 2 kB |
| region | 5 | 1 kB |
| part | 20.000.000 | 895 MB |
| supplier | 1.000.000 | 75 MB |
| partsupp | 80.000.000 | 4.37 GB |
| customer | 15.000.000 | 1.19 GB |
| orders | 150.000.000 | 6.15 GB |
| lineitem | 600.000.000 | 26.69 GB |
system.tables.total_bytes,并基于下方的表定义。)
现在在 ClickHouse 中创建这些表。表定义可在 ClickHouse 软件源中的 init.sql 中找到。
可以按如下方式导入数据:
clickhouse-client --format_csv_delimiter '|' --query "INSERT INTO nation FORMAT CSV" < nation.tbl
clickhouse-client --format_csv_delimiter '|' --query "INSERT INTO region FORMAT CSV" < region.tbl
clickhouse-client --format_csv_delimiter '|' --query "INSERT INTO part FORMAT CSV" < part.tbl
clickhouse-client --format_csv_delimiter '|' --query "INSERT INTO supplier FORMAT CSV" < supplier.tbl
clickhouse-client --format_csv_delimiter '|' --query "INSERT INTO partsupp FORMAT CSV" < partsupp.tbl
clickhouse-client --format_csv_delimiter '|' --query "INSERT INTO customer FORMAT CSV" < customer.tbl
clickhouse-client --format_csv_delimiter '|' --query "INSERT INTO orders FORMAT CSV" < orders.tbl
clickhouse-client --format_csv_delimiter '|' --query "INSERT INTO lineitem FORMAT CSV" < lineitem.tbl
除了使用 tpch-kit 自行生成表之外,您也可以直接从公共 S3 存储桶导入数据。请务必先使用
init.sql 创建空表。-- 规模因子 1
INSERT INTO nation SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/1/nation.tbl', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
INSERT INTO region SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/1/region.tbl', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
INSERT INTO part SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/1/part.tbl', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
INSERT INTO supplier SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/1/supplier.tbl', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
INSERT INTO partsupp SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/1/partsupp.tbl', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
INSERT INTO customer SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/1/customer.tbl', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
INSERT INTO orders SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/1/orders.tbl', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
INSERT INTO lineitem SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/1/lineitem.tbl', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
-- 规模因子 10
INSERT INTO nation SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/10/nation.tbl.zst', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
INSERT INTO region SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/10/region.tbl.zst', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
INSERT INTO part SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/10/part.tbl.zst', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
INSERT INTO supplier SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/10/supplier.tbl.zst', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
INSERT INTO partsupp SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/10/partsupp.tbl.zst', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
INSERT INTO customer SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/10/customer.tbl.zst', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
INSERT INTO orders SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/10/orders.tbl.zst', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
INSERT INTO lineitem SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/10/lineitem.tbl.zst', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
-- 规模因子 100
INSERT INTO nation SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/100/nation.tbl.gz', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
INSERT INTO region SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/100/region.tbl.gz', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
INSERT INTO part SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/100/part.tbl.gz', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
INSERT INTO supplier SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/100/supplier.tbl.gz', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
INSERT INTO partsupp SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/100/partsupp.tbl.gz', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
INSERT INTO customer SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/100/customer.tbl.gz', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
INSERT INTO orders SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/100/orders.tbl.gz', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
INSERT INTO lineitem SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/100/lineitem.tbl.gz', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
查询
settings.json 中的设置。
有关已知问题以及特定查询的说明,请参阅 README。
正确性
除非另有说明,这些查询的结果与官方结果一致。要进行验证,请生成一个缩放
因子 = 1 的 TPC-H 数据库 (dbgen,见上文) ,并与 tpch-kit 中的预期结果进行比较。