mirror of
https://github.com/ClickHouse/ClickHouse.git
synced 2024-11-29 11:02:08 +00:00
8623cb232c
* CLICKHOUSE-4063: less manual html @ index.md * CLICKHOUSE-4063: recommend markdown="1" in README.md * CLICKHOUSE-4003: manually purge custom.css for now * CLICKHOUSE-4064: expand <details> before any print (including to pdf) * CLICKHOUSE-3927: rearrange interfaces/formats.md a bit * CLICKHOUSE-3306: add few http headers * Remove copy-paste introduced in #3392 * Hopefully better chinese fonts #3392 * get rid of tabs @ custom.css * Apply comments and patch from #3384 * Add jdbc.md to ToC and some translation, though it still looks badly incomplete * minor punctuation * Add some backlinks to official website from mirrors that just blindly take markdown sources * Do not make fonts extra light * find . -name '*.md' -type f | xargs -I{} perl -pi -e 's//g' {} * find . -name '*.md' -type f | xargs -I{} perl -pi -e 's/ sql/g' {} * Remove outdated stuff from roadmap.md * Not so light font on front page too * Refactor Chinese formats.md to match recent changes in other languages
3.3 KiB
3.3 KiB
Схема «Звезда»
Компилирование dbgen: https://github.com/vadimtk/ssb-dbgen
git clone git@github.com:vadimtk/ssb-dbgen.git
cd ssb-dbgen
make
В процессе будет некоторое количество предупреждений. Это нормально.
Разместите dbgen
и dists.dss
в какое-либо место с 800Гб свободного дискового пространства.
Генерация данных:
./dbgen -s 1000 -T c
./dbgen -s 1000 -T l
Создание таблиц в ClickHouse:
CREATE TABLE lineorder (
LO_ORDERKEY UInt32,
LO_LINENUMBER UInt8,
LO_CUSTKEY UInt32,
LO_PARTKEY UInt32,
LO_SUPPKEY UInt32,
LO_ORDERDATE Date,
LO_ORDERPRIORITY String,
LO_SHIPPRIORITY UInt8,
LO_QUANTITY UInt8,
LO_EXTENDEDPRICE UInt32,
LO_ORDTOTALPRICE UInt32,
LO_DISCOUNT UInt8,
LO_REVENUE UInt32,
LO_SUPPLYCOST UInt32,
LO_TAX UInt8,
LO_COMMITDATE Date,
LO_SHIPMODE String
)Engine=MergeTree(LO_ORDERDATE,(LO_ORDERKEY,LO_LINENUMBER,LO_ORDERDATE),8192);
CREATE TABLE customer (
C_CUSTKEY UInt32,
C_NAME String,
C_ADDRESS String,
C_CITY String,
C_NATION String,
C_REGION String,
C_PHONE String,
C_MKTSEGMENT String,
C_FAKEDATE Date
)Engine=MergeTree(C_FAKEDATE,(C_CUSTKEY,C_FAKEDATE),8192);
CREATE TABLE part (
P_PARTKEY UInt32,
P_NAME String,
P_MFGR String,
P_CATEGORY String,
P_BRAND String,
P_COLOR String,
P_TYPE String,
P_SIZE UInt8,
P_CONTAINER String,
P_FAKEDATE Date
)Engine=MergeTree(P_FAKEDATE,(P_PARTKEY,P_FAKEDATE),8192);
CREATE TABLE lineorderd AS lineorder ENGINE = Distributed(perftest_3shards_1replicas, default, lineorder, rand());
CREATE TABLE customerd AS customer ENGINE = Distributed(perftest_3shards_1replicas, default, customer, rand());
CREATE TABLE partd AS part ENGINE = Distributed(perftest_3shards_1replicas, default, part, rand());
Для тестирования на одном сервере, используете просто таблицы типа MergeTree.
Для распределённого тестирования, нужно настроить кластер perftest_3shards_1replicas
в конфигурационном файле.
Далее создать MergeTree таблицы на каждом сервере и Distributed таблицу поверх них.
Загрузка данных (нужно поменять customer на customerd в распределённом варианте):
cat customer.tbl | sed 's/$/2000-01-01/' | clickhouse-client --query "INSERT INTO customer FORMAT CSV"
cat lineorder.tbl | clickhouse-client --query "INSERT INTO lineorder FORMAT CSV"