mirror of
https://github.com/ClickHouse/ClickHouse.git
synced 2024-10-04 07:30:52 +00:00
67c2e50331
* update presentations * CLICKHOUSE-2936: redirect from clickhouse.yandex.ru and clickhouse.yandex.com * update submodule * lost files * CLICKHOUSE-2981: prefer sphinx docs over original reference * CLICKHOUSE-2981: docs styles more similar to main website + add flags to switch language links * update presentations * Less confusing directory structure (docs -> doc/reference/) * Minify sphinx docs too * Website release script: fail fast + pass docker hash on deploy * Do not underline links in docs * shorter * cleanup docker images * tune nginx config * CLICKHOUSE-3043: get rid of habrastorage links * Lost translation * CLICKHOUSE-2936: temporary client-side redirect * behaves weird in test * put redirect back * CLICKHOUSE-3047: copy docs txts to public too * move to proper file * remove old pages to avoid confusion * Remove reference redirect warning for now * Refresh README.md * Yellow buttons in docs * Use svg flags instead of unicode ones in docs * fix test website instance * Put flags to separate files * wrong flag * Copy Yandex.Metrica introduction from main page to docs * Yet another home page structure change, couple new blocks (CLICKHOUSE-3045) * Update Contacts section * CLICKHOUSE-2849: more detailed legal information * CLICKHOUSE-2978 preparation - split by files * More changes in Contacts block * Tune texts on index page * update presentations * One more benchmark * Add usage sections to index page, adapted from slides * Get the roadmap started, based on slides from last ClickHouse Meetup * CLICKHOUSE-2977: some rendering tuning * Get rid of excessive section in the end of getting started * Make headers linkable * CLICKHOUSE-2981: links to editing reference - https://github.com/yandex/ClickHouse/issues/849 * CLICKHOUSE-2981: fix mobile styles in docs * Ban crawling of duplicating docs * Open some external links in new tab * Ban old docs too * Lots of trivial fixes in english docs * Lots of trivial fixes in russian docs * Remove getting started copies in markdown * Add Yandex.Webmaster * Fix some sphinx warnings * More warnings fixed in english docs * More sphinx warnings fixed * Add code-block:: text * More code-block:: text * These headers look not that well * Better switch between documentation languages * merge use_case.rst into ya_metrika_task.rst * Edit the agg_functions.rst texts * Add lost empty lines * Lost blank lines * Add new logo sizes * update presentations * Next step in migrating to new documentation * Fix all warnings in en reference * Fix all warnings in ru reference * Re-arrange existing reference * Move operation tips to main reference * Fix typos noticed by milovidov@ * Get rid of zookeeper.md * Looks like duplicate of tutorial.html * Fix some mess with html tags in tutorial * No idea why nobody noticed this before, but it was completely not clear whet to get the data * Match code block styling between main and tutorial pages (in favor of the latter) * Get rid of some copypaste in tutorial * Normalize header styles * Move example_datasets to sphinx * Move presentations submodule to website * Move and update README.md * No point in duplicating articles from habrahabr here * Move development-related docs as is for now * doc/reference/ -> docs/ (to match the URL on website) * Adapt links to match the previous commit * Adapt development docs to rst (still lacks translation and strikethrough support) * clean on release * blacklist presentations in gulp * strikethrough support in sphinx * just copy development folder for now * fix weird introduction in style article * Style guide translation (WIP) * Finish style guide translation to English * gulp clean separately * Update year in LICENSE * Initial CONTRIBUTING.md * Fix remaining links to old docs in tutorial * Some tutorial fixes * Typo * Another typo * Update list of authors from yandex-team accoding to git log
87 lines
2.9 KiB
ReStructuredText
87 lines
2.9 KiB
ReStructuredText
Star Schema
|
|
===========
|
|
|
|
Compile dbgen: https://github.com/vadimtk/ssb-dbgen
|
|
|
|
.. code-block:: bash
|
|
|
|
git clone git@github.com:vadimtk/ssb-dbgen.git
|
|
cd ssb-dbgen
|
|
make
|
|
|
|
You will see some warnings. It's Ok.
|
|
|
|
Place ``dbgen`` and ``dists.dss`` to some place with at least 800 GB free space available.
|
|
|
|
Generate data:
|
|
|
|
.. code-block:: bash
|
|
|
|
./dbgen -s 1000 -T c
|
|
./dbgen -s 1000 -T l
|
|
|
|
Create tables in ClickHouse:
|
|
|
|
.. code-block:: sql
|
|
|
|
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());
|
|
|
|
For single-node setup, create just MergeTree tables.
|
|
For Distributed setup, you must configure cluster ``perftest_3shards_1replicas`` in configuration file.
|
|
Then create MergeTree tables on each node and then create Distributed tables.
|
|
|
|
Load data (change customer to customerd in case of distributed setup):
|
|
|
|
.. code-block:: bash
|
|
|
|
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"
|
|
|