mirror of
https://github.com/ClickHouse/ClickHouse.git
synced 2024-09-20 16:50:48 +00:00
Merge branch 'feature_multiple_disks' of https://github.com/filimonov/ClickHouse into filimonov-feature_multiple_disks
This commit is contained in:
commit
d6b1035301
@ -114,7 +114,7 @@ class ClickHouseCluster:
|
||||
cmd += " client"
|
||||
return cmd
|
||||
|
||||
def add_instance(self, name, config_dir=None, main_configs=[], user_configs=[], macros={}, with_zookeeper=False, with_mysql=False, with_kafka=False, clickhouse_path_dir=None, with_odbc_drivers=False, with_postgres=False, with_hdfs=False, with_mongo=False, hostname=None, env_variables={}, image="yandex/clickhouse-integration-test", stay_alive=False, ipv4_address=None, ipv6_address=None, with_installed_binary=False):
|
||||
def add_instance(self, name, config_dir=None, main_configs=[], user_configs=[], macros={}, with_zookeeper=False, with_mysql=False, with_kafka=False, clickhouse_path_dir=None, with_odbc_drivers=False, with_postgres=False, with_hdfs=False, with_mongo=False, hostname=None, env_variables={}, image="yandex/clickhouse-integration-test", stay_alive=False, ipv4_address=None, ipv6_address=None, with_installed_binary=False, tmpfs=[]):
|
||||
"""Add an instance to the cluster.
|
||||
|
||||
name - the name of the instance directory and the value of the 'instance' macro in ClickHouse.
|
||||
@ -135,7 +135,7 @@ class ClickHouseCluster:
|
||||
self.zookeeper_config_path, with_mysql, with_kafka, with_mongo, self.base_configs_dir, self.server_bin_path,
|
||||
self.odbc_bridge_bin_path, clickhouse_path_dir, with_odbc_drivers, hostname=hostname,
|
||||
env_variables=env_variables, image=image, stay_alive=stay_alive, ipv4_address=ipv4_address, ipv6_address=ipv6_address,
|
||||
with_installed_binary=with_installed_binary)
|
||||
with_installed_binary=with_installed_binary, tmpfs=tmpfs)
|
||||
|
||||
self.instances[name] = instance
|
||||
if ipv4_address is not None or ipv6_address is not None:
|
||||
@ -395,6 +395,10 @@ class ClickHouseCluster:
|
||||
instance.client = None
|
||||
|
||||
|
||||
def open_bash_shell(self, instance_name):
|
||||
os.system(' '.join(self.base_cmd + ['exec', instance_name, '/bin/bash']))
|
||||
|
||||
|
||||
def get_kazoo_client(self, zoo_instance_name):
|
||||
zk = KazooClient(hosts=self.get_instance_ip(zoo_instance_name))
|
||||
zk.start()
|
||||
@ -435,6 +439,7 @@ services:
|
||||
{odbc_bridge_volume}
|
||||
{odbc_ini_path}
|
||||
entrypoint: {entrypoint_cmd}
|
||||
tmpfs: {tmpfs}
|
||||
cap_add:
|
||||
- SYS_PTRACE
|
||||
depends_on: {depends_on}
|
||||
@ -456,7 +461,7 @@ class ClickHouseInstance:
|
||||
self, cluster, base_path, name, custom_config_dir, custom_main_configs, custom_user_configs, macros,
|
||||
with_zookeeper, zookeeper_config_path, with_mysql, with_kafka, with_mongo, base_configs_dir, server_bin_path, odbc_bridge_bin_path,
|
||||
clickhouse_path_dir, with_odbc_drivers, hostname=None, env_variables={}, image="yandex/clickhouse-integration-test",
|
||||
stay_alive=False, ipv4_address=None, ipv6_address=None, with_installed_binary=False):
|
||||
stay_alive=False, ipv4_address=None, ipv6_address=None, with_installed_binary=False, tmpfs=[]):
|
||||
|
||||
self.name = name
|
||||
self.base_cmd = cluster.base_cmd[:]
|
||||
@ -464,6 +469,7 @@ class ClickHouseInstance:
|
||||
self.cluster = cluster
|
||||
self.hostname = hostname if hostname is not None else self.name
|
||||
|
||||
self.tmpfs = tmpfs[:]
|
||||
self.custom_config_dir = p.abspath(p.join(base_path, custom_config_dir)) if custom_config_dir else None
|
||||
self.custom_main_config_paths = [p.abspath(p.join(base_path, c)) for c in custom_main_configs]
|
||||
self.custom_user_config_paths = [p.abspath(p.join(base_path, c)) for c in custom_user_configs]
|
||||
@ -806,6 +812,7 @@ class ClickHouseInstance:
|
||||
configs_dir=configs_dir,
|
||||
config_d_dir=config_d_dir,
|
||||
db_dir=db_dir,
|
||||
tmpfs=str(self.tmpfs),
|
||||
logs_dir=logs_dir,
|
||||
depends_on=str(depends_on),
|
||||
user=os.getuid(),
|
||||
|
@ -3,11 +3,11 @@
|
||||
<test_cluster>
|
||||
<shard>
|
||||
<replica>
|
||||
<host>ch1</host>
|
||||
<host>node1</host>
|
||||
<port>9000</port>
|
||||
</replica>
|
||||
<replica>
|
||||
<host>ch2</host>
|
||||
<host>node2</host>
|
||||
<port>9000</port>
|
||||
</replica>
|
||||
</shard>
|
@ -2,30 +2,33 @@
|
||||
|
||||
<storage_configuration>
|
||||
<disks>
|
||||
<default> <!-- path for deafult disk is provided in main config -->
|
||||
<!--default> <! - - path for default disk is provided in main config - - >
|
||||
<keep_free_space_bytes>0</keep_free_space_bytes>
|
||||
</default>
|
||||
<jbod1>
|
||||
<path>/jbod1/</path> <!-- trailing slash is mandatory -->
|
||||
</default-->
|
||||
<mainstorage>
|
||||
<path>/mainstorage/</path><!-- trailing slash is mandatory -->
|
||||
<keep_free_space_bytes>1000000</keep_free_space_bytes>
|
||||
</mainstorage>
|
||||
<jbod1>
|
||||
<path>/jbod1/</path>
|
||||
<keep_free_space_bytes>10000000</keep_free_space_bytes>
|
||||
</jbod1>
|
||||
<jbod2>
|
||||
<path>/jbod2/</path>
|
||||
<keep_free_space_bytes>1000000</keep_free_space_bytes>
|
||||
<keep_free_space_bytes>10000000</keep_free_space_bytes>
|
||||
</jbod2>
|
||||
<external>
|
||||
<path>/external/</path>
|
||||
<keep_free_space_bytes>1000000</keep_free_space_bytes>
|
||||
<keep_free_space_bytes>10000000</keep_free_space_bytes>
|
||||
</external>
|
||||
</disks>
|
||||
|
||||
<schemas>
|
||||
<!-- default: store on jbod1-->
|
||||
<policies>
|
||||
<!-- default: store on mainstorage -->
|
||||
<default>
|
||||
<volume>
|
||||
<disk>jbod1</disk>
|
||||
<max_data_part_size_bytes>10000000</max_data_part_size_bytes>
|
||||
<!-- Q: how it will behave if the only disk has max_data_part_size_bytes limitation? -->
|
||||
<disk>mainstorage</disk>
|
||||
<max_data_part_size_bytes>20000000</max_data_part_size_bytes>
|
||||
</volume>
|
||||
</default>
|
||||
|
||||
@ -34,15 +37,15 @@
|
||||
<volume>
|
||||
<!-- names for the volumes should be added to allow moving parts between volumed with DDL commands -->
|
||||
<disk>default</disk>
|
||||
<max_data_part_size_bytes>10000000</max_data_part_size_bytes>
|
||||
<max_data_part_size_bytes>2000000</max_data_part_size_bytes>
|
||||
</volume>
|
||||
<volume>
|
||||
<disk>external</disk>
|
||||
<max_data_part_size_bytes>100000000</max_data_part_size_bytes>
|
||||
<max_data_part_size_bytes>20000000</max_data_part_size_bytes>
|
||||
</volume>
|
||||
</default_disk_with_external>
|
||||
|
||||
<!-- store on JBOD by default (round-robin), store bif parts on external -->
|
||||
<!-- store on JBOD by default (round-robin), store big parts on external -->
|
||||
<jbod_with_external>
|
||||
<volume>
|
||||
<disk>jbod1</disk>
|
||||
@ -52,11 +55,23 @@
|
||||
</volume>
|
||||
<volume>
|
||||
<disk>external</disk>
|
||||
<!-- max_data_part_size_bytes>10000000</max_data_part_size_bytes -->
|
||||
<!--max_data_part_size_bytes>30000000</max_data_part_size_bytes-->
|
||||
</volume>
|
||||
</jbod_with_external>
|
||||
|
||||
</schemas>
|
||||
<mainstorage_only>
|
||||
<volume>
|
||||
<disk>mainstorage</disk>
|
||||
<max_data_part_size_bytes>9000000</max_data_part_size_bytes>
|
||||
</volume>
|
||||
<volume>
|
||||
<disk>external</disk>
|
||||
<max_data_part_size_bytes>20000000</max_data_part_size_bytes>
|
||||
</volume>
|
||||
</mainstorage_only>
|
||||
|
||||
|
||||
</policies>
|
||||
|
||||
</storage_configuration>
|
||||
|
232
dbms/tests/integration/test_multiple_disks/test.py
Normal file
232
dbms/tests/integration/test_multiple_disks/test.py
Normal file
@ -0,0 +1,232 @@
|
||||
import time
|
||||
import pytest
|
||||
import os
|
||||
|
||||
from helpers.cluster import ClickHouseCluster
|
||||
|
||||
cluster = ClickHouseCluster(__file__)
|
||||
|
||||
node1 = cluster.add_instance('node1',
|
||||
config_dir='configs',
|
||||
with_zookeeper=True,
|
||||
tmpfs=['/jbod1:size=40M', '/jbod2:size=40M', '/external:size=200M'],
|
||||
macros={"shard": 0, "replica": 1} )
|
||||
|
||||
node2 = cluster.add_instance('node2',
|
||||
config_dir='configs',
|
||||
with_zookeeper=True,
|
||||
tmpfs=['/jbod1:size=40M', '/jbod2:size=40M', '/external:size=200M'],
|
||||
macros={"shard": 0, "replica": 2} )
|
||||
|
||||
#node2 = cluster.add_instance('node2', main_configs=['configs/remote_servers.xml', 'configs/credentials1.xml'], with_zookeeper=True)
|
||||
|
||||
@pytest.fixture(scope="module")
|
||||
|
||||
def test_cluster():
|
||||
try:
|
||||
cluster.start()
|
||||
yield cluster
|
||||
|
||||
finally:
|
||||
cluster.shutdown()
|
||||
|
||||
def test_run_shell(test_cluster):
|
||||
test_cluster.open_bash_shell('node1')
|
||||
|
||||
#################################
|
||||
# root@node1:/# clickhouse client -m
|
||||
# ClickHouse client version 19.8.1.536.
|
||||
# Connecting to localhost:9000 as user default.
|
||||
# Connected to ClickHouse server version 19.8.1 revision 54420.
|
||||
|
||||
# node1 :) select * from system.disks;
|
||||
|
||||
|
||||
|
||||
# def test_same_credentials(same_credentials_cluster):
|
||||
# node1.query("insert into test_table values ('2017-06-16', 111, 0)")
|
||||
# time.sleep(1)
|
||||
|
||||
# assert node1.query("SELECT id FROM test_table order by id") == '111\n'
|
||||
# assert node2.query("SELECT id FROM test_table order by id") == '111\n'
|
||||
|
||||
# node2.query("insert into test_table values ('2017-06-17', 222, 1)")
|
||||
# time.sleep(1)
|
||||
|
||||
# assert node1.query("SELECT id FROM test_table order by id") == '111\n222\n'
|
||||
# assert node2.query("SELECT id FROM test_table order by id") == '111\n222\n'
|
||||
|
||||
|
||||
# node3 = cluster.add_instance('node3', main_configs=['configs/remote_servers.xml', 'configs/no_credentials.xml'], with_zookeeper=True)
|
||||
# node4 = cluster.add_instance('node4', main_configs=['configs/remote_servers.xml', 'configs/no_credentials.xml'], with_zookeeper=True)
|
||||
|
||||
# @pytest.fixture(scope="module")
|
||||
# def no_credentials_cluster():
|
||||
# try:
|
||||
# cluster.start()
|
||||
|
||||
# _fill_nodes([node3, node4], 2)
|
||||
|
||||
# yield cluster
|
||||
|
||||
# finally:
|
||||
# cluster.shutdown()
|
||||
|
||||
|
||||
# def test_no_credentials(no_credentials_cluster):
|
||||
# node3.query("insert into test_table values ('2017-06-18', 111, 0)")
|
||||
# time.sleep(1)
|
||||
|
||||
# assert node3.query("SELECT id FROM test_table order by id") == '111\n'
|
||||
# assert node4.query("SELECT id FROM test_table order by id") == '111\n'
|
||||
|
||||
# node4.query("insert into test_table values ('2017-06-19', 222, 1)")
|
||||
# time.sleep(1)
|
||||
|
||||
# assert node3.query("SELECT id FROM test_table order by id") == '111\n222\n'
|
||||
# assert node4.query("SELECT id FROM test_table order by id") == '111\n222\n'
|
||||
|
||||
# node5 = cluster.add_instance('node5', main_configs=['configs/remote_servers.xml', 'configs/credentials1.xml'], with_zookeeper=True)
|
||||
# node6 = cluster.add_instance('node6', main_configs=['configs/remote_servers.xml', 'configs/credentials2.xml'], with_zookeeper=True)
|
||||
|
||||
# @pytest.fixture(scope="module")
|
||||
# def different_credentials_cluster():
|
||||
# try:
|
||||
# cluster.start()
|
||||
|
||||
# _fill_nodes([node5, node6], 3)
|
||||
|
||||
# yield cluster
|
||||
|
||||
# finally:
|
||||
# cluster.shutdown()
|
||||
|
||||
# def test_different_credentials(different_credentials_cluster):
|
||||
# node5.query("insert into test_table values ('2017-06-20', 111, 0)")
|
||||
# time.sleep(1)
|
||||
|
||||
# assert node5.query("SELECT id FROM test_table order by id") == '111\n'
|
||||
# assert node6.query("SELECT id FROM test_table order by id") == ''
|
||||
|
||||
# node6.query("insert into test_table values ('2017-06-21', 222, 1)")
|
||||
# time.sleep(1)
|
||||
|
||||
# assert node5.query("SELECT id FROM test_table order by id") == '111\n'
|
||||
# assert node6.query("SELECT id FROM test_table order by id") == '222\n'
|
||||
|
||||
# node7 = cluster.add_instance('node7', main_configs=['configs/remote_servers.xml', 'configs/credentials1.xml'], with_zookeeper=True)
|
||||
# node8 = cluster.add_instance('node8', main_configs=['configs/remote_servers.xml', 'configs/no_credentials.xml'], with_zookeeper=True)
|
||||
|
||||
# @pytest.fixture(scope="module")
|
||||
# def credentials_and_no_credentials_cluster():
|
||||
# try:
|
||||
# cluster.start()
|
||||
|
||||
# _fill_nodes([node7, node8], 4)
|
||||
|
||||
# yield cluster
|
||||
|
||||
# finally:
|
||||
# cluster.shutdown()
|
||||
|
||||
# def test_credentials_and_no_credentials(credentials_and_no_credentials_cluster):
|
||||
# node7.query("insert into test_table values ('2017-06-21', 111, 0)")
|
||||
# time.sleep(1)
|
||||
|
||||
# assert node7.query("SELECT id FROM test_table order by id") == '111\n'
|
||||
# assert node8.query("SELECT id FROM test_table order by id") == ''
|
||||
|
||||
# node8.query("insert into test_table values ('2017-06-22', 222, 1)")
|
||||
# time.sleep(1)
|
||||
|
||||
# assert node7.query("SELECT id FROM test_table order by id") == '111\n'
|
||||
# assert node8.query("SELECT id FROM test_table order by id") == '222\n'
|
||||
|
||||
'''
|
||||
## Test stand for multiple disks feature
|
||||
|
||||
Currently for namual tests, can be easily scripted to be the part of inntergration tests.
|
||||
|
||||
To run you need to have docker & docker-compose.
|
||||
|
||||
```
|
||||
(Check makefile)
|
||||
make run
|
||||
make ch1_shell
|
||||
> clickhouse-client
|
||||
|
||||
make logs # Ctrl+C
|
||||
make cleup
|
||||
```
|
||||
|
||||
### basic
|
||||
|
||||
* allows to configure multiple disks & folumes & shemas
|
||||
* clickhouse check that all disks are write-accessible
|
||||
* clickhouse can create a table with provided storagepolicy
|
||||
|
||||
### one volume-one disk custom storagepolicy
|
||||
|
||||
* clickhouse puts data to correct folder when storagepolicy is used
|
||||
* clickhouse can do merges / detach / attach / freeze on that folder
|
||||
|
||||
### one volume-multiple disks storagepolicy (JBOD scenario)
|
||||
|
||||
* clickhouse uses round-robin to place new parts
|
||||
* clickhouse can do merges / detach / attach / freeze on that folder
|
||||
|
||||
### two volumes-one disk per volume (fast expensive / slow cheap storage)
|
||||
|
||||
* clickhouse uses round-robin to place new parts
|
||||
* clickhouse can do merges / detach / attach / freeze on that folder
|
||||
* clickhouse put parts to different volumes depending on part size
|
||||
|
||||
### use 'default' storagepolicy for tables created without storagepolicy provided.
|
||||
|
||||
|
||||
# ReplicatedMergeTree
|
||||
|
||||
....
|
||||
|
||||
For all above:
|
||||
clickhouse respect free space limitation setting.
|
||||
ClickHouse writes important disk-related information to logs.
|
||||
|
||||
## Queries
|
||||
|
||||
```
|
||||
CREATE TABLE table_with_storage_policy_default (id UInt64) Engine=MergeTree() ORDER BY (id);
|
||||
|
||||
select name, data_paths, storage_policy from system.tables where name='table_with_storage_policy_default';
|
||||
"table_with_storage_policy_default","['/mainstorage/default/table_with_storage_policy_default/']","default"
|
||||
|
||||
INSERT INTO table_with_storage_policy_default SELECT rand64() FROM numbers(100);
|
||||
CREATE TABLE table_with_storage_policy_default_explicit (id UInt64) Engine=MergeTree() ORDER BY (id) SETTINGS storage_table_with_storage_policy_name='default';
|
||||
CREATE TABLE table_with_storage_policy_default_disk_with_external (id UInt64) Engine=MergeTree() ORDER BY (id) SETTINGS storage_table_with_storage_policy_name='default_disk_with_external';
|
||||
CREATE TABLE table_with_storage_policy_jbod_with_external (id UInt64) Engine=MergeTree() ORDER BY (id) SETTINGS storage_table_with_storage_policy_name='jbod_with_external';
|
||||
|
||||
CREATE TABLE replicated_table_with_storage_policy_default (id UInt64) Engine=ReplicatedMergeTree('/clickhouse/tables/{database}/{table}', '{replica}') ORDER BY (id);
|
||||
CREATE TABLE replicated_table_with_storage_policy_default_explicit (id UInt64) Engine=ReplicatedMergeTree('/clickhouse/tables/{database}/{table}', '{replica}') ORDER BY (id) SETTINGS storage_table_with_storage_policy_name='default';
|
||||
CREATE TABLE replicated_table_with_storage_policy_default_disk_with_external (id UInt64) Engine=ReplicatedMergeTree('/clickhouse/tables/{database}/{table}', '{replica}') ORDER BY (id) SETTINGS storage_table_with_storage_policy_name='default_disk_with_external';
|
||||
CREATE TABLE replicated_table_with_storage_policy_jbod_with_external (id UInt64) Engine=ReplicatedMergeTree('/clickhouse/tables/{database}/{table}', '{replica}') ORDER BY (id) SETTINGS storage_table_with_storage_policy_name='jbod_with_external';
|
||||
```
|
||||
|
||||
|
||||
## Extra acceptance criterias
|
||||
|
||||
* hardlinks problems. Thouse stetements should be able to work properly (or give a proper feedback) on multidisk scenarios
|
||||
* ALTER TABLE ... UPDATE
|
||||
* ALTER TABLE ... TABLE
|
||||
* ALTER TABLE ... MODIFY COLUMN ...
|
||||
* ALTER TABLE ... CLEAR COLUMN
|
||||
* ALTER TABLE ... REPLACE PARTITION ...
|
||||
* Maintainance - system tables show proper values:
|
||||
* system.parts
|
||||
* system.tables
|
||||
* system.part_log (target disk?)
|
||||
* New system table
|
||||
* system.volumes
|
||||
* system.disks
|
||||
* system.storagepolicys
|
||||
* chown / create needed disk folders in docker
|
||||
'''
|
@ -1,42 +0,0 @@
|
||||
docker_compose_version := $(shell echo $$(uname -s)-$$(uname -m))
|
||||
|
||||
run:
|
||||
docker-compose up -d
|
||||
|
||||
install_docker:
|
||||
@echo ""
|
||||
@echo "Please remember that you need to call it with sudo!!"
|
||||
@echo "^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^"
|
||||
@echo ""
|
||||
-curl -sSL https://get.docker.com | bash
|
||||
-usermod -aG docker $${USER}
|
||||
@echo "$${USER} has been added to docker group. Please relogin"
|
||||
|
||||
install_docker_compose:
|
||||
@echo ""
|
||||
@echo "Please remember that you need to call it with sudo!!"
|
||||
@echo "^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^"
|
||||
@echo ""
|
||||
-curl -L "https://github.com/docker/compose/releases/download/1.23.2/docker-compose-$(docker_compose_version)" -o /usr/local/bin/docker-compose
|
||||
-chmod +x /usr/local/bin/docker-compose
|
||||
|
||||
ch1_shell:
|
||||
docker-compose exec ch1 bash
|
||||
|
||||
ch2_shell:
|
||||
docker-compose exec ch2 bash
|
||||
|
||||
stop:
|
||||
docker-compose down
|
||||
|
||||
logs:
|
||||
docker-compose logs -f
|
||||
|
||||
cleanup:
|
||||
docker-compose down --rmi local --remove-orphans -v
|
||||
|
||||
cleanup_all:
|
||||
docker container stop $$(docker container ls -a -q)
|
||||
docker system prune --volumes
|
||||
docker image prune --all
|
||||
|
@ -1,83 +0,0 @@
|
||||
## Test stand for multiple disks feature
|
||||
|
||||
Currently for namual tests, can be easily scripted to be the part of inntergration tests.
|
||||
|
||||
To run you need to have docker & docker-compose.
|
||||
|
||||
```
|
||||
(Check makefile)
|
||||
make run
|
||||
make ch1_shell
|
||||
> clickhouse-client
|
||||
|
||||
make logs # Ctrl+C
|
||||
make cleup
|
||||
```
|
||||
|
||||
### basic
|
||||
|
||||
* allows to configure multiple disks & folumes & shemas
|
||||
* clickhouse check that all disks are write-accessible
|
||||
* clickhouse can create a table with provided schema
|
||||
|
||||
### one volume-one disk custom schema
|
||||
|
||||
* clickhouse puts data to correct folder when schema is used
|
||||
* clickhouse can do merges / detach / attach / freeze on that folder
|
||||
|
||||
### one volume-multiple disks schema (JBOD scenario)
|
||||
|
||||
* clickhouse uses round-robin to place new parts
|
||||
* clickhouse can do merges / detach / attach / freeze on that folder
|
||||
|
||||
### two volumes-one disk per volume (fast expensive / slow cheap storage)
|
||||
|
||||
* clickhouse uses round-robin to place new parts
|
||||
* clickhouse can do merges / detach / attach / freeze on that folder
|
||||
* clickhouse put parts to different volumes depending on part size
|
||||
|
||||
### use 'default' schema for tables created without schema provided.
|
||||
|
||||
|
||||
# ReplicatedMergeTree
|
||||
|
||||
....
|
||||
|
||||
For all above:
|
||||
clickhouse respect free space limitation setting.
|
||||
ClickHouse writes important disk-related information to logs.
|
||||
|
||||
## Queries
|
||||
|
||||
```
|
||||
CREATE TABLE schema_default (id UInt64) Engine=MergeTree() ORDER BY (id);
|
||||
|
||||
INSERT INTO schema_default SELECT * FROM numbers(1);
|
||||
CREATE TABLE schema_default_explicit (id UInt64) Engine=MergeTree() ORDER BY (id) SETTINGS storage_schema_name='default';
|
||||
CREATE TABLE schema_default_disk_with_external (id UInt64) Engine=MergeTree() ORDER BY (id) SETTINGS storage_schema_name='default_disk_with_external';
|
||||
CREATE TABLE schema_jbod_with_external (id UInt64) Engine=MergeTree() ORDER BY (id) SETTINGS storage_schema_name='jbod_with_external';
|
||||
|
||||
CREATE TABLE replicated_schema_default (id UInt64) Engine=ReplicatedMergeTree('/clickhouse/tables/{database}/{table}', '{replica}') ORDER BY (id);
|
||||
CREATE TABLE replicated_schema_default_explicit (id UInt64) Engine=ReplicatedMergeTree('/clickhouse/tables/{database}/{table}', '{replica}') ORDER BY (id) SETTINGS storage_schema_name='default';
|
||||
CREATE TABLE replicated_schema_default_disk_with_external (id UInt64) Engine=ReplicatedMergeTree('/clickhouse/tables/{database}/{table}', '{replica}') ORDER BY (id) SETTINGS storage_schema_name='default_disk_with_external';
|
||||
CREATE TABLE replicated_schema_jbod_with_external (id UInt64) Engine=ReplicatedMergeTree('/clickhouse/tables/{database}/{table}', '{replica}') ORDER BY (id) SETTINGS storage_schema_name='jbod_with_external';
|
||||
```
|
||||
|
||||
|
||||
## Extra acceptance criterias
|
||||
|
||||
* hardlinks problems. Thouse stetements should be able to work properly (or give a proper feedback) on multidisk scenarios
|
||||
* ALTER TABLE ... UPDATE
|
||||
* ALTER TABLE ... TABLE
|
||||
* ALTER TABLE ... MODIFY COLUMN ...
|
||||
* ALTER TABLE ... CLEAR COLUMN
|
||||
* ALTER TABLE ... REPLACE PARTITION ...
|
||||
* Maintainance - system tables show proper values:
|
||||
* system.parts
|
||||
* system.tables
|
||||
* system.part_log (target disk?)
|
||||
* New system table
|
||||
* system.volumes
|
||||
* system.disks
|
||||
* system.schemas
|
||||
* chown / create needed disk folders in docker
|
@ -1,7 +0,0 @@
|
||||
<yandex>
|
||||
<macros>
|
||||
<cluster>test_cluster</cluster>
|
||||
<shard>0</shard>
|
||||
<replica>ch1</replica>
|
||||
</macros>
|
||||
</yandex>
|
@ -1,7 +0,0 @@
|
||||
<yandex>
|
||||
<macros>
|
||||
<cluster>test_cluster</cluster>
|
||||
<shard>0</shard>
|
||||
<replica>ch2</replica>
|
||||
</macros>
|
||||
</yandex>
|
@ -1,8 +0,0 @@
|
||||
<yandex>
|
||||
<zookeeper>
|
||||
<node>
|
||||
<host>zookeeper</host>
|
||||
<port>2181</port>
|
||||
</node>
|
||||
</zookeeper>
|
||||
</yandex>
|
@ -1,52 +0,0 @@
|
||||
version: '3'
|
||||
|
||||
services:
|
||||
zookeeper:
|
||||
image: zookeeper
|
||||
networks:
|
||||
- 001_miltiple_disks
|
||||
|
||||
ch1:
|
||||
image: yandex/clickhouse-server
|
||||
hostname: ch1
|
||||
depends_on:
|
||||
- "zookeeper"
|
||||
networks:
|
||||
- 001_miltiple_disks
|
||||
tmpfs:
|
||||
- /jbod1:size=40M
|
||||
- /jbod2:size=40M
|
||||
- /external:size=200M
|
||||
volumes:
|
||||
- ./config/conf.d:/etc/clickhouse-server/conf.d
|
||||
- ./config/ch1.metrika.xml:/etc/metrika.xml
|
||||
# TODO: hacky, but "cheap" - don't need to rebuild docker image.
|
||||
# for CI & tests automation should be done another way, not relying on build path
|
||||
- ../../../../build/dbms/programs/clickhouse:/usr/bin/clickhouse
|
||||
- ./test_setup:/test_setup
|
||||
entrypoint: ['/test_setup/entrypoint.sh']
|
||||
|
||||
|
||||
ch2:
|
||||
image: yandex/clickhouse-server
|
||||
hostname: ch2
|
||||
depends_on:
|
||||
- "zookeeper"
|
||||
networks:
|
||||
- 001_miltiple_disks
|
||||
tmpfs:
|
||||
- /jbod1:size=40M
|
||||
- /jbod2:size=40M
|
||||
- /external:size=200M
|
||||
volumes:
|
||||
- ./config/conf.d:/etc/clickhouse-server/conf.d
|
||||
- ./config/ch2.metrika.xml:/etc/metrika.xml
|
||||
# TODO: hacky, but "cheap" - don't need to rebuild docker image.
|
||||
# for CI & tests automation should be done another way, not relying on build path
|
||||
- ../../../../build/dbms/programs/clickhouse:/usr/bin/clickhouse
|
||||
- ./test_setup:/test_setup
|
||||
entrypoint: ['/test_setup/entrypoint.sh']
|
||||
|
||||
|
||||
networks:
|
||||
001_miltiple_disks:
|
@ -1,9 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
if [ -f /etc/clickhouse-server/conf.d/container_maintanence_mode.flag ]; then
|
||||
echo "Starting container in maintanence mode. It will sleep unless you shutdown it"
|
||||
sleep infinity
|
||||
else
|
||||
chown -R clickhouse:clickhouse /jbod1 /jbod2 /external
|
||||
/test_setup/wait-for-it.sh zookeeper:2181 --timeout=0 --strict -- /entrypoint.sh
|
||||
fi
|
@ -1,182 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
# Use this script to test if a given TCP host/port are available
|
||||
|
||||
# The MIT License (MIT)
|
||||
# Copyright (c) 2016 Giles Hall
|
||||
# See https://github.com/vishnubob/wait-for-it/blob/master/LICENSE
|
||||
|
||||
WAITFORIT_cmdname=${0##*/}
|
||||
|
||||
echoerr() { if [[ $WAITFORIT_QUIET -ne 1 ]]; then echo "$@" 1>&2; fi }
|
||||
|
||||
usage()
|
||||
{
|
||||
cat << USAGE >&2
|
||||
Usage:
|
||||
$WAITFORIT_cmdname host:port [-s] [-t timeout] [-- command args]
|
||||
-h HOST | --host=HOST Host or IP under test
|
||||
-p PORT | --port=PORT TCP port under test
|
||||
Alternatively, you specify the host and port as host:port
|
||||
-s | --strict Only execute subcommand if the test succeeds
|
||||
-q | --quiet Don't output any status messages
|
||||
-t TIMEOUT | --timeout=TIMEOUT
|
||||
Timeout in seconds, zero for no timeout
|
||||
-- COMMAND ARGS Execute command with args after the test finishes
|
||||
USAGE
|
||||
exit 1
|
||||
}
|
||||
|
||||
wait_for()
|
||||
{
|
||||
if [[ $WAITFORIT_TIMEOUT -gt 0 ]]; then
|
||||
echoerr "$WAITFORIT_cmdname: waiting $WAITFORIT_TIMEOUT seconds for $WAITFORIT_HOST:$WAITFORIT_PORT"
|
||||
else
|
||||
echoerr "$WAITFORIT_cmdname: waiting for $WAITFORIT_HOST:$WAITFORIT_PORT without a timeout"
|
||||
fi
|
||||
WAITFORIT_start_ts=$(date +%s)
|
||||
while :
|
||||
do
|
||||
if [[ $WAITFORIT_ISBUSY -eq 1 ]]; then
|
||||
nc -z $WAITFORIT_HOST $WAITFORIT_PORT
|
||||
WAITFORIT_result=$?
|
||||
else
|
||||
(echo > /dev/tcp/$WAITFORIT_HOST/$WAITFORIT_PORT) >/dev/null 2>&1
|
||||
WAITFORIT_result=$?
|
||||
fi
|
||||
if [[ $WAITFORIT_result -eq 0 ]]; then
|
||||
WAITFORIT_end_ts=$(date +%s)
|
||||
echoerr "$WAITFORIT_cmdname: $WAITFORIT_HOST:$WAITFORIT_PORT is available after $((WAITFORIT_end_ts - WAITFORIT_start_ts)) seconds"
|
||||
break
|
||||
fi
|
||||
sleep 1
|
||||
done
|
||||
return $WAITFORIT_result
|
||||
}
|
||||
|
||||
wait_for_wrapper()
|
||||
{
|
||||
# In order to support SIGINT during timeout: http://unix.stackexchange.com/a/57692
|
||||
if [[ $WAITFORIT_QUIET -eq 1 ]]; then
|
||||
timeout $WAITFORIT_BUSYTIMEFLAG $WAITFORIT_TIMEOUT $0 --quiet --child --host=$WAITFORIT_HOST --port=$WAITFORIT_PORT --timeout=$WAITFORIT_TIMEOUT &
|
||||
else
|
||||
timeout $WAITFORIT_BUSYTIMEFLAG $WAITFORIT_TIMEOUT $0 --child --host=$WAITFORIT_HOST --port=$WAITFORIT_PORT --timeout=$WAITFORIT_TIMEOUT &
|
||||
fi
|
||||
WAITFORIT_PID=$!
|
||||
trap "kill -INT -$WAITFORIT_PID" INT
|
||||
wait $WAITFORIT_PID
|
||||
WAITFORIT_RESULT=$?
|
||||
if [[ $WAITFORIT_RESULT -ne 0 ]]; then
|
||||
echoerr "$WAITFORIT_cmdname: timeout occurred after waiting $WAITFORIT_TIMEOUT seconds for $WAITFORIT_HOST:$WAITFORIT_PORT"
|
||||
fi
|
||||
return $WAITFORIT_RESULT
|
||||
}
|
||||
|
||||
# process arguments
|
||||
while [[ $# -gt 0 ]]
|
||||
do
|
||||
case "$1" in
|
||||
*:* )
|
||||
WAITFORIT_hostport=(${1//:/ })
|
||||
WAITFORIT_HOST=${WAITFORIT_hostport[0]}
|
||||
WAITFORIT_PORT=${WAITFORIT_hostport[1]}
|
||||
shift 1
|
||||
;;
|
||||
--child)
|
||||
WAITFORIT_CHILD=1
|
||||
shift 1
|
||||
;;
|
||||
-q | --quiet)
|
||||
WAITFORIT_QUIET=1
|
||||
shift 1
|
||||
;;
|
||||
-s | --strict)
|
||||
WAITFORIT_STRICT=1
|
||||
shift 1
|
||||
;;
|
||||
-h)
|
||||
WAITFORIT_HOST="$2"
|
||||
if [[ $WAITFORIT_HOST == "" ]]; then break; fi
|
||||
shift 2
|
||||
;;
|
||||
--host=*)
|
||||
WAITFORIT_HOST="${1#*=}"
|
||||
shift 1
|
||||
;;
|
||||
-p)
|
||||
WAITFORIT_PORT="$2"
|
||||
if [[ $WAITFORIT_PORT == "" ]]; then break; fi
|
||||
shift 2
|
||||
;;
|
||||
--port=*)
|
||||
WAITFORIT_PORT="${1#*=}"
|
||||
shift 1
|
||||
;;
|
||||
-t)
|
||||
WAITFORIT_TIMEOUT="$2"
|
||||
if [[ $WAITFORIT_TIMEOUT == "" ]]; then break; fi
|
||||
shift 2
|
||||
;;
|
||||
--timeout=*)
|
||||
WAITFORIT_TIMEOUT="${1#*=}"
|
||||
shift 1
|
||||
;;
|
||||
--)
|
||||
shift
|
||||
WAITFORIT_CLI=("$@")
|
||||
break
|
||||
;;
|
||||
--help)
|
||||
usage
|
||||
;;
|
||||
*)
|
||||
echoerr "Unknown argument: $1"
|
||||
usage
|
||||
;;
|
||||
esac
|
||||
done
|
||||
|
||||
if [[ "$WAITFORIT_HOST" == "" || "$WAITFORIT_PORT" == "" ]]; then
|
||||
echoerr "Error: you need to provide a host and port to test."
|
||||
usage
|
||||
fi
|
||||
|
||||
WAITFORIT_TIMEOUT=${WAITFORIT_TIMEOUT:-15}
|
||||
WAITFORIT_STRICT=${WAITFORIT_STRICT:-0}
|
||||
WAITFORIT_CHILD=${WAITFORIT_CHILD:-0}
|
||||
WAITFORIT_QUIET=${WAITFORIT_QUIET:-0}
|
||||
|
||||
# check to see if timeout is from busybox?
|
||||
WAITFORIT_TIMEOUT_PATH=$(type -p timeout)
|
||||
WAITFORIT_TIMEOUT_PATH=$(realpath $WAITFORIT_TIMEOUT_PATH 2>/dev/null || readlink -f $WAITFORIT_TIMEOUT_PATH)
|
||||
if [[ $WAITFORIT_TIMEOUT_PATH =~ "busybox" ]]; then
|
||||
WAITFORIT_ISBUSY=1
|
||||
WAITFORIT_BUSYTIMEFLAG="-t"
|
||||
|
||||
else
|
||||
WAITFORIT_ISBUSY=0
|
||||
WAITFORIT_BUSYTIMEFLAG=""
|
||||
fi
|
||||
|
||||
if [[ $WAITFORIT_CHILD -gt 0 ]]; then
|
||||
wait_for
|
||||
WAITFORIT_RESULT=$?
|
||||
exit $WAITFORIT_RESULT
|
||||
else
|
||||
if [[ $WAITFORIT_TIMEOUT -gt 0 ]]; then
|
||||
wait_for_wrapper
|
||||
WAITFORIT_RESULT=$?
|
||||
else
|
||||
wait_for
|
||||
WAITFORIT_RESULT=$?
|
||||
fi
|
||||
fi
|
||||
|
||||
if [[ $WAITFORIT_CLI != "" ]]; then
|
||||
if [[ $WAITFORIT_RESULT -ne 0 && $WAITFORIT_STRICT -eq 1 ]]; then
|
||||
echoerr "$WAITFORIT_cmdname: strict mode, refusing to execute subprocess"
|
||||
exit $WAITFORIT_RESULT
|
||||
fi
|
||||
exec "${WAITFORIT_CLI[@]}"
|
||||
else
|
||||
exit $WAITFORIT_RESULT
|
||||
fi
|
@ -11,6 +11,12 @@ COPY s3downloader /s3downloader
|
||||
|
||||
ENV DATASETS="hits visits"
|
||||
|
||||
# https://clang.llvm.org/docs/ThreadSanitizer.html
|
||||
# https://clang.llvm.org/docs/AddressSanitizer.html
|
||||
# https://clang.llvm.org/docs/UndefinedBehaviorSanitizer.html
|
||||
# https://clang.llvm.org/docs/MemorySanitizer.html
|
||||
|
||||
|
||||
CMD dpkg -i package_folder/clickhouse-common-static_*.deb; \
|
||||
dpkg -i package_folder/clickhouse-common-static-dbg_*.deb; \
|
||||
dpkg -i package_folder/clickhouse-server_*.deb; \
|
||||
|
Loading…
Reference in New Issue
Block a user