Skip to content

Instantly share code, notes, and snippets.

@aitor

aitor/README.md

Forked from igorwwwwwwwwwwwwwwwwwwww/README.md
Created October 13, 2019 17:13
Show Gist options
  • Save aitor/f6cba9782fa47d4ab5bccc413f30fd9f to your computer and use it in GitHub Desktop.
Save aitor/f6cba9782fa47d4ab5bccc413f30fd9f to your computer and use it in GitHub Desktop.
Download ZIP
clickhouse-playground
Raw
README.md

clickhouse-playground

capture logs:

heroku logs --tail -a travis-api-production | grep at=info | gsed -e 's/^\([0-9]*-[0-9]*-[0-9]*\)T\([0-9]*:[0-9]*:[0-9]*\)/date=\1 time="\1 \2" /' | lcut date time method path host request_id fwd dyno connect service status bytes > access.log

boot:

docker-compose up

connect:

docker-compose run click_client clickhouse-client --host click_00_00

create base table:

for shard in 00 01; do
  for replica in 00 01; do
    docker-compose run click_client clickhouse-client --host click_${shard}_${replica} --query 'create table requests (EventDate Date, EventTime DateTime, Method String, Path String, Host String, RequestId String, Fwd String, Dyno String, Connect String, Service String, Status UInt16, Bytes UInt16) ENGINE=MergeTree(EventDate, (RequestId), 8192)'
  done
done

create distributed table:

for shard in 00 01; do
  for replica in 00 01; do
    docker-compose run click_client clickhouse-client --host click_${shard}_${replica} --query 'create table requests_dist (EventDate Date, EventTime DateTime, Method String, Path String, Host String, RequestId String, Fwd String, Dyno String, Connect String, Service String, Status UInt16, Bytes UInt16) ENGINE=Distributed(logs, default, requests, sipHash64(RequestId))'
  done
done

create replicated table:

for shard in 00 01; do
  for replica in 00 01; do
    docker-compose run click_client clickhouse-client --host click_${shard}_${replica} --query "create table requests_replicated (EventDate Date, EventTime DateTime, Method String, Path String, Host String, RequestId String, Fwd String, Dyno String, Connect String, Service String, Status UInt16, Bytes UInt16) ENGINE=ReplicatedMergeTree('/clickhouse/tables/$shard/hits', '$replica', EventDate, (RequestId), 8192)"
  done
done

create distributed and replicated table:

for shard in 00 01; do
  for replica in 00 01; do
    docker-compose run click_client clickhouse-client --host click_${shard}_${replica} --query 'create table requests_dist_replicated (EventDate Date, EventTime DateTime, Method String, Path String, Host String, RequestId String, Fwd String, Dyno String, Connect String, Service String, Status UInt16, Bytes UInt16) ENGINE=Distributed(logs, default, requests_replicated, sipHash64(RequestId))'
  done
done

import distributed:

cat access.log | docker-compose run click_client clickhouse-client --host click_00_00 --query 'INSERT INTO requests_dist FORMAT TabSeparated'

docker-compose run click_client clickhouse-client --host click_00_00 --query 'select count(*) from requests'
docker-compose run click_client clickhouse-client --host click_01_00 --query 'select count(*) from requests'

docker-compose run click_client clickhouse-client --host click_00_00 --query 'select count(*) from requests_dist'

import distributed and replicated:

docker-compose run click_client clickhouse-client --host click_00_00 --query 'INSERT INTO requests_dist_replicated SELECT * FROM requests_dist'

docker-compose run click_client clickhouse-client --host click_00_00 --query 'select count(*) from requests_dist_replicated'
docker-compose run click_client clickhouse-client --host click_00_01 --query 'select count(*) from requests_dist_replicated'
docker-compose run click_client clickhouse-client --host click_01_00 --query 'select count(*) from requests_dist_replicated'
docker-compose run click_client clickhouse-client --host click_01_01 --query 'select count(*) from requests_dist_replicated'
Raw
config.xml
<?xml version="1.0"?>
<yandex>
<logger>
<!-- Possible levels: https://github.com/pocoproject/poco/blob/develop/Foundation/include/Poco/Logger.h#L105 -->
<level>trace</level>
<log>/var/log/clickhouse-server/clickhouse-server.log</log>
<errorlog>/var/log/clickhouse-server/clickhouse-server.err.log</errorlog>
<size>1000M</size>
<count>10</count>
<console>1</console> <!-- Default behavior is autodetection (log to console if not daemon mode and is tty) -->
</logger>
<!--display_name>production</display_name--> <!-- It is the name that will be shown in the client -->
<http_port>8123</http_port>
<tcp_port>9000</tcp_port>
<!-- For HTTPS and SSL over native protocol. -->
<!--
<https_port>8443</https_port>
<tcp_port_secure>9440</tcp_port_secure>
-->
<!-- Used with https_port and tcp_port_secure. Full ssl options list: https://github.com/ClickHouse-Extras/poco/blob/master/NetSSL_OpenSSL/include/Poco/Net/SSLManager.h#L71 -->
<openSSL>
<server> <!-- Used for https server AND secure tcp port -->
<!-- openssl req -subj "/CN=localhost" -new -newkey rsa:2048 -days 365 -nodes -x509 -keyout /etc/clickhouse-server/server.key -out /etc/clickhouse-server/server.crt -->
<certificateFile>/etc/clickhouse-server/server.crt</certificateFile>
<privateKeyFile>/etc/clickhouse-server/server.key</privateKeyFile>
<!-- openssl dhparam -out /etc/clickhouse-server/dhparam.pem 4096 -->
<dhParamsFile>/etc/clickhouse-server/dhparam.pem</dhParamsFile>
<verificationMode>none</verificationMode>
<loadDefaultCAFile>true</loadDefaultCAFile>
<cacheSessions>true</cacheSessions>
<disableProtocols>sslv2,sslv3</disableProtocols>
<preferServerCiphers>true</preferServerCiphers>
</server>
<client> <!-- Used for connecting to https dictionary source -->
<loadDefaultCAFile>true</loadDefaultCAFile>
<cacheSessions>true</cacheSessions>
<disableProtocols>sslv2,sslv3</disableProtocols>
<preferServerCiphers>true</preferServerCiphers>
<!-- Use for self-signed: <verificationMode>none</verificationMode> -->
<invalidCertificateHandler>
<!-- Use for self-signed: <name>AcceptCertificateHandler</name> -->
<name>RejectCertificateHandler</name>
</invalidCertificateHandler>
</client>
</openSSL>
<!-- Default root page on http[s] server. For example load UI from https://tabix.io/ when opening http://localhost:8123 -->
<!--
<http_server_default_response><![CDATA[<html ng-app="SMI2"><head><base href="http://ui.tabix.io/"></head><body><div ui-view="" class="content-ui"></div><script src="http://loader.tabix.io/master.js"></script></body></html>]]></http_server_default_response>
-->
<!-- Port for communication between replicas. Used for data exchange. -->
<interserver_http_port>9009</interserver_http_port>
<!-- Hostname that is used by other replicas to request this server.
If not specified, than it is determined analoguous to 'hostname -f' command.
This setting could be used to switch replication to another network interface.
-->
<!--
<interserver_http_host>example.yandex.ru</interserver_http_host>
-->
<!-- Listen specified host. use :: (wildcard IPv6 address), if you want to accept connections both with IPv4 and IPv6 from everywhere. -->
<!-- <listen_host>::</listen_host> -->
<!-- Same for hosts with disabled ipv6: -->
<!-- <listen_host>0.0.0.0</listen_host> -->
<!-- Default values - try listen localhost on ipv4 and ipv6: -->
<!--
<listen_host>::1</listen_host>
<listen_host>127.0.0.1</listen_host>
-->
<!-- Don't exit if ipv6 or ipv4 unavailable, but listen_host with this protocol specified -->
<!-- <listen_try>0</listen_try> -->
<!-- Allow listen on same address:port -->
<!-- <listen_reuse_port>0</listen_reuse_port> -->
<!-- <listen_backlog>64</listen_backlog> -->
<max_connections>4096</max_connections>
<keep_alive_timeout>3</keep_alive_timeout>
<!-- Maximum number of concurrent queries. -->
<max_concurrent_queries>100</max_concurrent_queries>
<!-- Set limit on number of open files (default: maximum). This setting makes sense on Mac OS X because getrlimit() fails to retrieve
correct maximum value. -->
<!-- <max_open_files>262144</max_open_files> -->
<!-- Size of cache of uncompressed blocks of data, used in tables of MergeTree family.
In bytes. Cache is single for server. Memory is allocated only on demand.
Cache is used when 'use_uncompressed_cache' user setting turned on (off by default).
Uncompressed cache is advantageous only for very short queries and in rare cases.
-->
<uncompressed_cache_size>8589934592</uncompressed_cache_size>
<!-- Approximate size of mark cache, used in tables of MergeTree family.
In bytes. Cache is single for server. Memory is allocated only on demand.
You should not lower this value.
-->
<mark_cache_size>5368709120</mark_cache_size>
<!-- Path to data directory, with trailing slash. -->
<path>/var/lib/clickhouse/</path>
<!-- Path to temporary data for processing hard queries. -->
<tmp_path>/var/lib/clickhouse/tmp/</tmp_path>
<!-- Directory with user provided files that are accessible by 'file' table function. -->
<user_files_path>/var/lib/clickhouse/user_files/</user_files_path>
<!-- Path to configuration file with users, access rights, profiles of settings, quotas. -->
<users_config>users.xml</users_config>
<!-- Default profile of settings. -->
<default_profile>default</default_profile>
<!-- System profile of settings. This settings are used by internal processes (Buffer storage, Distibuted DDL worker and so on). -->
<!-- <system_profile>default</system_profile> -->
<!-- Default database. -->
<default_database>default</default_database>
<!-- Server time zone could be set here.
Time zone is used when converting between String and DateTime types,
when printing DateTime in text formats and parsing DateTime from text,
it is used in date and time related functions, if specific time zone was not passed as an argument.
Time zone is specified as identifier from IANA time zone database, like UTC or Africa/Abidjan.
If not specified, system time zone at server startup is used.
Please note, that server could display time zone alias instead of specified name.
Example: W-SU is an alias for Europe/Moscow and Zulu is an alias for UTC.
-->
<!-- <timezone>Europe/Moscow</timezone> -->
<!-- You can specify umask here (see "man umask"). Server will apply it on startup.
Number is always parsed as octal. Default umask is 027 (other users cannot read logs, data files, etc; group can only read).
-->
<!-- <umask>022</umask> -->
<!-- Configuration of clusters that could be used in Distributed tables.
https://clickhouse.yandex/docs/en/table_engines/distributed/
-->
<remote_servers incl="clickhouse_remote_servers" >
<!-- Test only shard config for testing distributed storage -->
<test_shard_localhost>
<shard>
<replica>
<host>localhost</host>
<port>9000</port>
</replica>
</shard>
</test_shard_localhost>
<test_shard_localhost_secure>
<shard>
<replica>
<host>localhost</host>
<port>9440</port>
<secure>1</secure>
</replica>
</shard>
</test_shard_localhost_secure>
<logs>
<shard>
<replica>
<host>click_00_00</host>
<port>9000</port>
</replica>
<replica>
<host>click_00_01</host>
<port>9000</port>
</replica>
</shard>
<shard>
<replica>
<host>click_01_00</host>
<port>9000</port>
</replica>
<replica>
<host>click_01_01</host>
<port>9000</port>
</replica>
</shard>
</logs>
</remote_servers>
<!-- If element has 'incl' attribute, then for it's value will be used corresponding substitution from another file.
By default, path to file with substitutions is /etc/metrika.xml. It could be changed in config in 'include_from' element.
Values for substitutions are specified in /yandex/name_of_substitution elements in that file.
-->
<!-- ZooKeeper is used to store metadata about replicas, when using Replicated tables.
Optional. If you don't use replicated tables, you could omit that.
See https://clickhouse.yandex/docs/en/table_engines/replication/
-->
<zookeeper>
<node index="1">
<host>zk1</host>
<port>2181</port>
</node>
<node index="2">
<host>zk2</host>
<port>2181</port>
</node>
<node index="3">
<host>zk3</host>
<port>2181</port>
</node>
</zookeeper>
<!-- Substitutions for parameters of replicated tables.
Optional. If you don't use replicated tables, you could omit that.
See https://clickhouse.yandex/docs/en/table_engines/replication/#creating-replicated-tables
-->
<macros incl="macros" optional="true" />
<!-- Reloading interval for embedded dictionaries, in seconds. Default: 3600. -->
<builtin_dictionaries_reload_interval>3600</builtin_dictionaries_reload_interval>
<!-- Maximum session timeout, in seconds. Default: 3600. -->
<max_session_timeout>3600</max_session_timeout>
<!-- Default session timeout, in seconds. Default: 60. -->
<default_session_timeout>60</default_session_timeout>
<!-- Sending data to Graphite for monitoring. Several sections can be defined. -->
<!--
interval - send every X second
root_path - prefix for keys
hostname_in_path - append hostname to root_path (default = true)
metrics - send data from table system.metrics
events - send data from table system.events
asynchronous_metrics - send data from table system.asynchronous_metrics
-->
<!--
<graphite>
<host>localhost</host>
<port>42000</port>
<timeout>0.1</timeout>
<interval>60</interval>
<root_path>one_min</root_path>
<hostname_in_path>true</hostname_in_path>
<metrics>true</metrics>
<events>true</events>
<asynchronous_metrics>true</asynchronous_metrics>
</graphite>
<graphite>
<host>localhost</host>
<port>42000</port>
<timeout>0.1</timeout>
<interval>1</interval>
<root_path>one_sec</root_path>
<metrics>true</metrics>
<events>true</events>
<asynchronous_metrics>false</asynchronous_metrics>
</graphite>
-->
<!-- Query log. Used only for queries with setting log_queries = 1. -->
<query_log>
<!-- What table to insert data. If table is not exist, it will be created.
When query log structure is changed after system update,
then old table will be renamed and new table will be created automatically.
-->
<database>system</database>
<table>query_log</table>
<!--
PARTITION BY expr https://clickhouse.yandex/docs/en/table_engines/custom_partitioning_key/
Example:
event_date
toMonday(event_date)
toYYYYMM(event_date)
toStartOfHour(event_time)
-->
<partition_by>toYYYYMM(event_date)</partition_by>
<!-- Interval of flushing data. -->
<flush_interval_milliseconds>7500</flush_interval_milliseconds>
</query_log>
<!-- Uncomment if use part_log
<part_log>
<database>system</database>
<table>part_log</table>
<flush_interval_milliseconds>7500</flush_interval_milliseconds>
</part_log>
-->
<!-- Parameters for embedded dictionaries, used in Yandex.Metrica.
See https://clickhouse.yandex/docs/en/dicts/internal_dicts/
-->
<!-- Path to file with region hierarchy. -->
<!-- <path_to_regions_hierarchy_file>/opt/geo/regions_hierarchy.txt</path_to_regions_hierarchy_file> -->
<!-- Path to directory with files containing names of regions -->
<!-- <path_to_regions_names_files>/opt/geo/</path_to_regions_names_files> -->
<!-- Configuration of external dictionaries. See:
https://clickhouse.yandex/docs/en/dicts/external_dicts/
-->
<dictionaries_config>*_dictionary.xml</dictionaries_config>
<!-- Uncomment if you want data to be compressed 30-100% better.
Don't do that if you just started using ClickHouse.
-->
<compression incl="clickhouse_compression">
<!--
<!- - Set of variants. Checked in order. Last matching case wins. If nothing matches, lz4 will be used. - ->
<case>
<!- - Conditions. All must be satisfied. Some conditions may be omitted. - ->
<min_part_size>10000000000</min_part_size> <!- - Min part size in bytes. - ->
<min_part_size_ratio>0.01</min_part_size_ratio> <!- - Min size of part relative to whole table size. - ->
<!- - What compression method to use. - ->
<method>zstd</method>
</case>
-->
</compression>
<!-- Allow to execute distributed DDL queries (CREATE, DROP, ALTER, RENAME) on cluster.
Works only if ZooKeeper is enabled. Comment it if such functionality isn't required. -->
<distributed_ddl>
<!-- Path in ZooKeeper to queue with DDL queries -->
<path>/clickhouse/task_queue/ddl</path>
<!-- Settings from this profile will be used to execute DDL queries -->
<!-- <profile>default</profile> -->
</distributed_ddl>
<!-- Settings to fine tune MergeTree tables. See documentation in source code, in MergeTreeSettings.h -->
<!--
<merge_tree>
<max_suspicious_broken_parts>5</max_suspicious_broken_parts>
</merge_tree>
-->
<!-- Protection from accidental DROP.
If size of a MergeTree table is greater than max_table_size_to_drop (in bytes) than table could not be dropped with any DROP query.
If you want do delete one table and don't want to restart clickhouse-server, you could create special file <clickhouse-path>/flags/force_drop_table and make DROP once.
By default max_table_size_to_drop is 50GB, max_table_size_to_drop=0 allows to DROP any tables.
Uncomment to disable protection.
-->
<!-- <max_table_size_to_drop>0</max_table_size_to_drop> -->
<!-- Example of parameters for GraphiteMergeTree table engine -->
<graphite_rollup_example>
<pattern>
<regexp>click_cost</regexp>
<function>any</function>
<retention>
<age>0</age>
<precision>3600</precision>
</retention>
<retention>
<age>86400</age>
<precision>60</precision>
</retention>
</pattern>
<default>
<function>max</function>
<retention>
<age>0</age>
<precision>60</precision>
</retention>
<retention>
<age>3600</age>
<precision>300</precision>
</retention>
<retention>
<age>86400</age>
<precision>3600</precision>
</retention>
</default>
</graphite_rollup_example>
<!-- Directory in <clickhouse-path> containing schema files for various input formats.
The directory will be created if it doesn't exist.
-->
<format_schema_path>/var/lib/clickhouse/format_schemas/</format_schema_path>
<!-- Uncomment to disable ClickHouse internal DNS caching. -->
<!-- <disable_internal_dns_cache>1</disable_internal_dns_cache> -->
</yandex>
Raw
docker-compose.yml
version: '3'
services:
click_00_00:
image: yandex/clickhouse-server
ulimits:
nofile: 262144
volumes:
- ./config.xml:/etc/clickhouse-server/config.xml
click_00_01:
image: yandex/clickhouse-server
ulimits:
nofile: 262144
volumes:
- ./config.xml:/etc/clickhouse-server/config.xml
click_01_00:
image: yandex/clickhouse-server
ulimits:
nofile: 262144
volumes:
- ./config.xml:/etc/clickhouse-server/config.xml
click_01_01:
image: yandex/clickhouse-server
ulimits:
nofile: 262144
volumes:
- ./config.xml:/etc/clickhouse-server/config.xml
click_client:
image: yandex/clickhouse-client
zk1:
image: zookeeper
restart: always
hostname: zk1
ports:
- 2181:2181
environment:
ZOO_MY_ID: 1
ZOO_SERVERS: server.1=0.0.0.0:2888:3888 server.2=zk2:2888:3888 server.3=zk3:2888:3888
zk2:
image: zookeeper
restart: always
hostname: zk2
ports:
- 2182:2181
environment:
ZOO_MY_ID: 2
ZOO_SERVERS: server.1=zk1:2888:3888 server.2=0.0.0.0:2888:3888 server.3=zk3:2888:3888
zk3:
image: zookeeper
restart: always
hostname: zk3
ports:
- 2183:2181
environment:
ZOO_MY_ID: 3
ZOO_SERVERS: server.1=zk1:2888:3888 server.2=zk2:2888:3888 server.3=0.0.0.0:2888:3888
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment