Add ClickHouse

This commit is contained in:
Andrey Bunyaev 2020-11-11 09:47:25 +04:00
parent 89c9cfe099
commit 4d803e617b
8 changed files with 863 additions and 2 deletions

53
clickhouse/Dockerfile Normal file
View File

@ -0,0 +1,53 @@
FROM ubuntu:20.04
ARG CLICKHOUSE_VERSION=20.9.4.76
ARG CLICKHOUSE_GOSU_VERSION=1.10
RUN apt-get update \
&& apt-get install --yes --no-install-recommends \
apt-transport-https \
dirmngr \
gnupg \
&& mkdir -p /etc/apt/sources.list.d \
&& apt-key adv --keyserver keyserver.ubuntu.com --recv E0C56BD4 \
&& echo "deb http://repo.yandex.ru/clickhouse/deb/stable/ main/" > /etc/apt/sources.list.d/clickhouse.list \
&& apt-get update \
&& env DEBIAN_FRONTEND=noninteractive \
apt-get install --allow-unauthenticated --yes --no-install-recommends \
clickhouse-common-static=$CLICKHOUSE_VERSION \
clickhouse-client=$CLICKHOUSE_VERSION \
clickhouse-server=$CLICKHOUSE_VERSION \
locales \
tzdata \
wget \
&& rm -rf \
/var/lib/apt/lists/* \
/var/cache/debconf \
/tmp/* \
&& apt-get clean
ADD https://github.com/tianon/gosu/releases/download/$CLICKHOUSE_GOSU_VERSION/gosu-amd64 /bin/gosu
RUN locale-gen en_US.UTF-8
ENV LANG en_US.UTF-8
ENV LANGUAGE en_US:en
ENV LC_ALL en_US.UTF-8
RUN mkdir /docker-entrypoint-initdb.d
COPY docker_related_config.xml /etc/clickhouse-server/config.d/
COPY config.xml /etc/clickhouse-server/config.xml
COPY entrypoint.sh /entrypoint.sh
RUN chmod +x \
/entrypoint.sh \
/bin/gosu
EXPOSE 9000 8123 9009
VOLUME /var/lib/clickhouse
ENV CLICKHOUSE_CONFIG /etc/clickhouse-server/config.xml
ENV CLICKHOUSE_USER ${CLICKHOUSE_USER}
ENV CLICKHOUSE_PASSWORD ${CLICKHOUSE_PASSWORD}
ENTRYPOINT ["/entrypoint.sh"]

510
clickhouse/config.xml Normal file
View File

@ -0,0 +1,510 @@
<?xml version="1.0"?>
<!--
NOTE: User and query level settings are set up in "users.xml" file.
-->
<yandex>
<!-- The list of hosts allowed to use in URL-related storage engines and table functions.
If this section is not present in configuration, all hosts are allowed.
-->
<remote_url_allow_hosts>
<!-- Host should be specified exactly as in URL. The name is checked before DNS resolution.
Example: "yandex.ru", "yandex.ru." and "www.yandex.ru" are different hosts.
If port is explicitly specified in URL, the host:port is checked as a whole.
If host specified here without port, any port with this host allowed.
"yandex.ru" -> "yandex.ru:443", "yandex.ru:80" etc. is allowed, but "yandex.ru:80" -> only "yandex.ru:80" is allowed.
If the host is specified as IP address, it is checked as specified in URL. Example: "[2a02:6b8:a::a]".
If there are redirects and support for redirects is enabled, every redirect (the Location field) is checked.
-->
<!-- Regular expression can be specified. RE2 engine is used for regexps.
Regexps are not aligned: don't forget to add ^ and $. Also don't forget to escape dot (.) metacharacter
(forgetting to do so is a common source of error).
-->
</remote_url_allow_hosts>
<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> -->
<!-- Perform mlockall after startup to lower first queries latency
and to prevent clickhouse executable from being paged out under high IO load.
Enabling this option is recommended but will lead to increased startup time for up to a few seconds.
-->
<mlock_executable>false</mlock_executable>
<!-- 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_cluster_two_shards_localhost>
<shard>
<replica>
<host>localhost</host>
<port>9000</port>
</replica>
</shard>
<shard>
<replica>
<host>localhost</host>
<port>9000</port>
</replica>
</shard>
</test_cluster_two_shards_localhost>
<test_cluster_two_shards>
<shard>
<replica>
<host>127.0.0.1</host>
<port>9000</port>
</replica>
</shard>
<shard>
<replica>
<host>127.0.0.2</host>
<port>9000</port>
</replica>
</shard>
</test_cluster_two_shards>
<test_shard_localhost_secure>
<shard>
<replica>
<host>localhost</host>
<port>9440</port>
<secure>1</secure>
</replica>
</shard>
</test_shard_localhost_secure>
<test_unavailable_shard>
<shard>
<replica>
<host>localhost</host>
<port>9000</port>
</replica>
</shard>
<shard>
<replica>
<host>localhost</host>
<port>1</port>
</replica>
</shard>
</test_unavailable_shard>
</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 incl="zookeeper-servers" optional="true" />
<!-- 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>
<events_cumulative>false</events_cumulative>
<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>
<events_cumulative>false</events_cumulative>
<asynchronous_metrics>false</asynchronous_metrics>
</graphite>
-->
<!-- Serve endpoint fot Prometheus monitoring. -->
<!--
endpoint - mertics path (relative to root, statring with "/")
port - port to setup server. If not defined or 0 than http_port used
metrics - send data from table system.metrics
events - send data from table system.events
asynchronous_metrics - send data from table system.asynchronous_metrics
-->
<!--
<prometheus>
<endpoint>/metrics</endpoint>
<port>9363</port>
<metrics>true</metrics>
<events>true</events>
<asynchronous_metrics>true</asynchronous_metrics>
</prometheus>
-->
<!-- 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>
<!-- Trace log. Stores stack traces collected by query profilers.
See query_profiler_real_time_period_ns and query_profiler_cpu_time_period_ns settings. -->
<trace_log>
<database>system</database>
<table>trace_log</table>
<partition_by>toYYYYMM(event_date)</partition_by>
<flush_interval_milliseconds>7500</flush_interval_milliseconds>
</trace_log>
<!-- Query thread log. Has information about all threads participated in query execution.
Used only for queries with setting log_query_threads = 1. -->
<query_thread_log>
<database>system</database>
<table>query_thread_log</table>
<partition_by>toYYYYMM(event_date)</partition_by>
<flush_interval_milliseconds>7500</flush_interval_milliseconds>
</query_thread_log>
<!-- Uncomment if use part log.
Part log contains information about all actions with parts in MergeTree tables (creation, deletion, merges, downloads).
<part_log>
<database>system</database>
<table>part_log</table>
<flush_interval_milliseconds>7500</flush_interval_milliseconds>
</part_log>
-->
<!-- Uncomment to write text log into table.
Text log contains all information from usual server log but stores it in structured and efficient way.
<text_log>
<database>system</database>
<table>text_log</table>
<flush_interval_milliseconds>7500</flush_interval_milliseconds>
</text_log>
-->
<!-- Uncomment to write metric log into table.
Metric log contains rows with current values of ProfileEvents, CurrentMetrics collected with "collect_interval_milliseconds" interval.
<metric_log>
<database>system</database>
<table>metric_log</table>
<flush_interval_milliseconds>7500</flush_interval_milliseconds>
<collect_interval_milliseconds>1000</collect_interval_milliseconds>
</metric_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 change clickhouse-server config, 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.
The same for max_partition_size_to_drop.
Uncomment to disable protection.
-->
<!-- <max_table_size_to_drop>0</max_table_size_to_drop> -->
<!-- <max_partition_size_to_drop>0</max_partition_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 use query masking rules.
name - name for the rule (optional)
regexp - RE2 compatible regular expression (mandatory)
replace - substitution string for sensitive data (optional, by default - six asterisks)
<query_masking_rules>
<rule>
<name>hide SSN</name>
<regexp>\b\d{3}-\d{2}-\d{4}\b</regexp>
<replace>000-00-0000</replace>
</rule>
</query_masking_rules>
-->
<!-- Uncomment to disable ClickHouse internal DNS caching. -->
<!-- <disable_internal_dns_cache>1</disable_internal_dns_cache> -->
</yandex>

View File

@ -0,0 +1,12 @@
<yandex>
<!-- Listen wildcard address to allow accepting connections from other containers and host network. -->
<listen_host>::</listen_host>
<listen_host>0.0.0.0</listen_host>
<listen_try>1</listen_try>
<!--
<logger>
<console>1</console>
</logger>
-->
</yandex>

103
clickhouse/entrypoint.sh Normal file
View File

@ -0,0 +1,103 @@
#!/bin/bash
# set some vars
CLICKHOUSE_CONFIG="${CLICKHOUSE_CONFIG:-/etc/clickhouse-server/config.xml}"
if [ x"$UID" == x0 ]; then
USER="$(id -u clickhouse)"
GROUP="$(id -g clickhouse)"
gosu="gosu $USER:$GROUP"
else
USER="$(id -u)"
GROUP="$(id -g)"
gosu=""
fi
# port is needed to check if clickhouse-server is ready for connections
HTTP_PORT="$(clickhouse extract-from-config --config-file $CLICKHOUSE_CONFIG --key=http_port)"
# get CH directories locations
DATA_DIR="$(clickhouse extract-from-config --config-file $CLICKHOUSE_CONFIG --key=path || true)"
TMP_DIR="$(clickhouse extract-from-config --config-file $CLICKHOUSE_CONFIG --key=tmp_path || true)"
USER_PATH="$(clickhouse extract-from-config --config-file $CLICKHOUSE_CONFIG --key=user_files_path || true)"
LOG_PATH="$(clickhouse extract-from-config --config-file $CLICKHOUSE_CONFIG --key=logger.log || true)"
LOG_DIR="$(dirname $LOG_PATH || true)"
ERROR_LOG_PATH="$(clickhouse extract-from-config --config-file $CLICKHOUSE_CONFIG --key=logger.errorlog || true)"
ERROR_LOG_DIR="$(dirname $ERROR_LOG_PATH || true)"
FORMAT_SCHEMA_PATH="$(clickhouse extract-from-config --config-file $CLICKHOUSE_CONFIG --key=format_schema_path || true)"
CLICKHOUSE_USER="${CLICKHOUSE_USER:-default}"
for dir in "$DATA_DIR" \
"$ERROR_LOG_DIR" \
"$LOG_DIR" \
"$TMP_DIR" \
"$USER_PATH" \
"$FORMAT_SCHEMA_PATH"
do
# check if variable not empty
[ -z "$dir" ] && continue
# ensure directories exist
if ! mkdir -p "$dir"; then
echo "Couldn't create necessary directory: $dir"
exit 1
fi
if [ x"$UID" == x0 ] && [ "$CLICKHOUSE_DO_NOT_CHOWN" != "1" ]; then
# ensure proper directories permissions
chown -R "$USER:$GROUP" "$dir"
elif [ "$(stat -c %u "$dir")" != "$USER" ]; then
echo "Necessary directory '$dir' isn't owned by user with id '$USER'"
exit 1
fi
done
if [ -n "$(ls /docker-entrypoint-initdb.d/)" ]; then
$gosu /usr/bin/clickhouse-server --config-file=$CLICKHOUSE_CONFIG &
pid="$!"
# check if clickhouse is ready to accept connections
# will try to send ping clickhouse via http_port (max 12 retries, with 1 sec delay)
if ! wget --spider --quiet --tries=12 --waitretry=1 --retry-connrefused "http://localhost:$HTTP_PORT/ping" ; then
echo >&2 'ClickHouse init process failed.'
exit 1
fi
if [ ! -z "$CLICKHOUSE_PASSWORD" ]; then
printf -v WITH_PASSWORD '%s %q' "--password" "$CLICKHOUSE_PASSWORD"
fi
clickhouseclient=( clickhouse-client --multiquery -u $CLICKHOUSE_USER $WITH_PASSWORD )
echo
for f in /docker-entrypoint-initdb.d/*; do
case "$f" in
*.sh)
if [ -x "$f" ]; then
echo "$0: running $f"
"$f"
else
echo "$0: sourcing $f"
. "$f"
fi
;;
*.sql) echo "$0: running $f"; cat "$f" | "${clickhouseclient[@]}" ; echo ;;
*.sql.gz) echo "$0: running $f"; gunzip -c "$f" | "${clickhouseclient[@]}"; echo ;;
*) echo "$0: ignoring $f" ;;
esac
echo
done
if ! kill -s TERM "$pid" || ! wait "$pid"; then
echo >&2 'Finishing of ClickHouse init process failed.'
exit 1
fi
fi
# if no args passed to `docker run` or first argument start with `--`, then the user is passing clickhouse-server arguments
if [[ $# -lt 1 ]] || [[ "$1" == "--"* ]]; then
exec $gosu /usr/bin/clickhouse-server --config-file=$CLICKHOUSE_CONFIG "$@"
fi
# Otherwise, we assume the user want to run his own process, for example a `bash` shell to explore this image
exec "$@"

138
clickhouse/users.xml Normal file
View File

@ -0,0 +1,138 @@
<?xml version="1.0"?>
<yandex>
<!-- Profiles of settings. -->
<profiles>
<!-- Default settings. -->
<default>
<!-- Maximum memory usage for processing single query, in bytes. -->
<max_memory_usage>10000000000</max_memory_usage>
<!-- Use cache of uncompressed blocks of data. Meaningful only for processing many of very short queries. -->
<use_uncompressed_cache>0</use_uncompressed_cache>
<!-- How to choose between replicas during distributed query processing.
random - choose random replica from set of replicas with minimum number of errors
nearest_hostname - from set of replicas with minimum number of errors, choose replica
with minimum number of different symbols between replica's hostname and local hostname
(Hamming distance).
in_order - first live replica is chosen in specified order.
first_or_random - if first replica one has higher number of errors, pick a random one from replicas with minimum number of errors.
-->
<load_balancing>random</load_balancing>
</default>
<!-- Profile that allows only read queries. -->
<readonly>
<readonly>1</readonly>
</readonly>
</profiles>
<!-- Users and ACL. -->
<users>
<!-- If user name was not specified, 'default' user is used. -->
<default>
<!-- Password could be specified in plaintext or in SHA256 (in hex format).
If you want to specify password in plaintext (not recommended), place it in 'password' element.
Example: <password>qwerty</password>.
Password could be empty.
If you want to specify SHA256, place it in 'password_sha256_hex' element.
Example: <password_sha256_hex>65e84be33532fb784c48129675f9eff3a682b27168c0ea744b2cf58ee02337c5</password_sha256_hex>
Restrictions of SHA256: impossibility to connect to ClickHouse using MySQL JS client (as of July 2019).
If you want to specify double SHA1, place it in 'password_double_sha1_hex' element.
Example: <password_double_sha1_hex>e395796d6546b1b65db9d665cd43f0e858dd4303</password_double_sha1_hex>
How to generate decent password:
Execute: PASSWORD=$(base64 < /dev/urandom | head -c8); echo "$PASSWORD"; echo -n "$PASSWORD" | sha256sum | tr -d '-'
In first line will be password and in second - corresponding SHA256.
How to generate double SHA1:
Execute: PASSWORD=$(base64 < /dev/urandom | head -c8); echo "$PASSWORD"; echo -n "$PASSWORD" | openssl dgst -sha1 -binary | openssl dgst -sha1
In first line will be password and in second - corresponding double SHA1.
-->
<password>HAHA</password>
<!-- List of networks with open access.
To open access from everywhere, specify:
<ip>::/0</ip>
To open access only from localhost, specify:
<ip>::1</ip>
<ip>127.0.0.1</ip>
Each element of list has one of the following forms:
<ip> IP-address or network mask. Examples: 213.180.204.3 or 10.0.0.1/8 or 10.0.0.1/255.255.255.0
2a02:6b8::3 or 2a02:6b8::3/64 or 2a02:6b8::3/ffff:ffff:ffff:ffff::.
<host> Hostname. Example: server01.yandex.ru.
To check access, DNS query is performed, and all received addresses compared to peer address.
<host_regexp> Regular expression for host names. Example, ^server\d\d-\d\d-\d\.yandex\.ru$
To check access, DNS PTR query is performed for peer address and then regexp is applied.
Then, for result of PTR query, another DNS query is performed and all received addresses compared to peer address.
Strongly recommended that regexp is ends with $
All results of DNS requests are cached till server restart.
-->
<networks incl="networks" replace="replace">
<ip>::/0</ip>
</networks>
<!-- Settings profile for user. -->
<profile>default</profile>
<!-- Quota for user. -->
<quota>default</quota>
<!-- For testing the table filters -->
<databases>
<test>
<!-- Simple expression filter -->
<filtered_table1>
<filter>a = 1</filter>
</filtered_table1>
<!-- Complex expression filter -->
<filtered_table2>
<filter>a + b &lt; 1 or c - d &gt; 5</filter>
</filtered_table2>
<!-- Filter with ALIAS column -->
<filtered_table3>
<filter>c = 1</filter>
</filtered_table3>
</test>
</databases>
</default>
<!-- Example of user with readonly access. -->
<!-- <readonly>
<password></password>
<networks incl="networks" replace="replace">
<ip>::1</ip>
<ip>127.0.0.1</ip>
</networks>
<profile>readonly</profile>
<quota>default</quota>
</readonly> -->
</users>
<!-- Quotas. -->
<quotas>
<!-- Name of quota. -->
<default>
<!-- Limits for time interval. You could specify many intervals with different limits. -->
<interval>
<!-- Length of interval. -->
<duration>3600</duration>
<!-- No limits. Just calculate resource usage for time interval. -->
<queries>0</queries>
<errors>0</errors>
<result_rows>0</result_rows>
<read_rows>0</read_rows>
<execution_time>0</execution_time>
</interval>
</default>
</quotas>
</yandex>

View File

@ -596,6 +596,37 @@ services:
networks:
- backend
### ClickHouse #############################################
clickhouse:
build:
context: ./clickhouse
args:
- CLICKHOUSE_VERSION=${CLICKHOUSE_VERSION}
- CLICKHOUSE_GOSU_VERSION=${CLICKHOUSE_GOSU_VERSION}
environment:
- CLICKHOUSE_USER=${CLICKHOUSE_USER}
- CLICKHOUSE_PASSWORD=${CLICKHOUSE_PASSWORD}
volumes:
- ${DATA_PATH_HOST}/clickhouse:/var/lib/clickhouse
- ${CLICKHOUSE_CUSTOM_CONFIG}:/etc/clickhouse-server/config.xml
- ${CLICKHOUSE_USERS_CUSTOM_CONFIG}:/etc/clickhouse-server/users.xml
- ${CLICKHOUSE_HOST_LOG_PATH}:/var/log/clickhouse
- ${CLICKHOUSE_ENTRYPOINT_INITDB}:/docker-entrypoint-initdb.d
links:
- workspace
ports:
- "${CLICKHOUSE_HTTP_PORT}:8123"
- "${CLICKHOUSE_CLIENT_PORT}:9000"
- "${CLICKHOUSE_NATIVE_PORT}:9009"
ulimits:
nproc: 65535
nofile:
soft: 262144
hard: 262144
networks:
# - frontend
- backend
### Redis ################################################
redis:
build: ./redis

View File

@ -39,7 +39,7 @@ COMPOSE_PROJECT_NAME=laradock
# Select a PHP version of the Workspace and PHP-FPM containers (Does not apply to HHVM).
# Accepted values: 7.4 - 7.3 - 7.2 - 7.1 - 7.0 - 5.6
PHP_VERSION=7.3
PHP_VERSION=7.4
### Phalcon Version ###########################################
@ -325,6 +325,20 @@ MYSQL_PORT=3306
MYSQL_ROOT_PASSWORD=root
MYSQL_ENTRYPOINT_INITDB=./mysql/docker-entrypoint-initdb.d
### CLICKHOUSE #################################################
CLICKHOUSE_VERSION=20.6
CLICKHOUSE_GOSU_VERSION=1.10
CLICKHOUSE_CUSTOM_CONFIG=./clickhouse/config.xml
CLICKHOUSE_USERS_CUSTOM_CONFIG=./clickhouse/users.xml
CLICKHOUSE_USER=default
CLICKHOUSE_PASSWORD=HAHA
CLICKHOUSE_HTTP_PORT=8123
CLICKHOUSE_CLIENT_PORT=9000
CLICKHOUSE_NATIVE_PORT=9009
CLICKHOUSE_ENTRYPOINT_INITDB=./clickhouse/docker-entrypoint-initdb.d
CLICKHOUSE_HOST_LOG_PATH=./logs/clickhouse
### REDIS #################################################
REDIS_PORT=6379