mirror of
https://git.mirrors.martin98.com/https://github.com/SigNoz/signoz
synced 2025-08-11 01:39:03 +08:00
feat: signoz can now scale up in docker swarm (#309)
* feat: signoz can now scale up in docker swarm * chore: adding empty folders for volume mount * chore: using image 0.4.0 * chore: adding folder to persist signoz.db
This commit is contained in:
Ankit Nayan
GitHub
parent
6a01ce88cb
commit
004dda200c
517
deploy/docker-swarm/clickhouse-setup/clickhouse-config.xml
Normal file
517
deploy/docker-swarm/clickhouse-setup/clickhouse-config.xml
Normal file
@ -0,0 +1,517 @@
|
||||
<?xml version="1.0"?>
|
||||
<yandex>
|
||||
<logger>
|
||||
<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>
|
||||
</logger>
|
||||
|
||||
<http_port>8123</http_port>
|
||||
<tcp_port>9000</tcp_port>
|
||||
|
||||
<!-- For HTTPS and SSL over native protocol. -->
|
||||
<!--
|
||||
<https_port>8443</https_port>
|
||||
<tcp_ssl_port>9440</tcp_ssl_port>
|
||||
-->
|
||||
|
||||
<!-- Used with https_port and tcp_ssl_port. Full ssl options list: https://github.com/yandex/ClickHouse/blob/master/contrib/libpoco/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>0.0.0.0</listen_host> -->
|
||||
|
||||
<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>
|
||||
|
||||
<!-- 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>
|
||||
|
||||
<!-- 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/reference_en.html#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>
|
||||
</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/reference_en.html#Data%20replication
|
||||
-->
|
||||
<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/reference_en.html#Creating%20replicated%20tables
|
||||
-->
|
||||
<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>
|
||||
|
||||
<!-- 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/reference_en.html#Internal%20dictionaries
|
||||
-->
|
||||
|
||||
<!-- 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/reference_en.html#External%20Dictionaries
|
||||
-->
|
||||
<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>
|
||||
</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>
|
||||
<!-- carbon -->
|
||||
<pattern>
|
||||
<regexp>^carbon\.</regexp>
|
||||
<function>any</function>
|
||||
<retention>
|
||||
<age>0</age>
|
||||
<precision>60</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>7776000</age>
|
||||
<precision>3600</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>10368000</age>
|
||||
<precision>21600</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>34560000</age>
|
||||
<precision>43200</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>63072000</age>
|
||||
<precision>86400</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>94608000</age>
|
||||
<precision>604800</precision>
|
||||
</retention>
|
||||
</pattern>
|
||||
<!-- collectd -->
|
||||
<pattern>
|
||||
<regexp>^collectd\.</regexp>
|
||||
<function>any</function>
|
||||
<retention>
|
||||
<age>0</age>
|
||||
<precision>10</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>43200</age>
|
||||
<precision>60</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>864000</age>
|
||||
<precision>900</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>1728000</age>
|
||||
<precision>1800</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>3456000</age>
|
||||
<precision>3600</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>10368000</age>
|
||||
<precision>21600</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>34560000</age>
|
||||
<precision>43200</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>63072000</age>
|
||||
<precision>86400</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>94608000</age>
|
||||
<precision>604800</precision>
|
||||
</retention>
|
||||
</pattern>
|
||||
<!-- high -->
|
||||
<pattern>
|
||||
<regexp>^high\.</regexp>
|
||||
<function>any</function>
|
||||
<retention>
|
||||
<age>0</age>
|
||||
<precision>10</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>172800</age>
|
||||
<precision>60</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>864000</age>
|
||||
<precision>900</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>1728000</age>
|
||||
<precision>1800</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>3456000</age>
|
||||
<precision>3600</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>10368000</age>
|
||||
<precision>21600</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>34560000</age>
|
||||
<precision>43200</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>63072000</age>
|
||||
<precision>86400</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>94608000</age>
|
||||
<precision>604800</precision>
|
||||
</retention>
|
||||
</pattern>
|
||||
<!-- medium -->
|
||||
<pattern>
|
||||
<regexp>^medium\.</regexp>
|
||||
<function>any</function>
|
||||
<retention>
|
||||
<age>0</age>
|
||||
<precision>60</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>864000</age>
|
||||
<precision>900</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>1728000</age>
|
||||
<precision>1800</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>3456000</age>
|
||||
<precision>3600</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>10368000</age>
|
||||
<precision>21600</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>34560000</age>
|
||||
<precision>43200</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>63072000</age>
|
||||
<precision>86400</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>94608000</age>
|
||||
<precision>604800</precision>
|
||||
</retention>
|
||||
</pattern>
|
||||
<!-- low -->
|
||||
<pattern>
|
||||
<regexp>^low\.</regexp>
|
||||
<function>any</function>
|
||||
<retention>
|
||||
<age>0</age>
|
||||
<precision>600</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>15552000</age>
|
||||
<precision>1800</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>31536000</age>
|
||||
<precision>3600</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>63072000</age>
|
||||
<precision>21600</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>126144000</age>
|
||||
<precision>43200</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>252288000</age>
|
||||
<precision>86400</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>315360000</age>
|
||||
<precision>604800</precision>
|
||||
</retention>
|
||||
</pattern>
|
||||
<!-- default -->
|
||||
<default>
|
||||
<function>any</function>
|
||||
<retention>
|
||||
<age>0</age>
|
||||
<precision>60</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>864000</age>
|
||||
<precision>900</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>1728000</age>
|
||||
<precision>1800</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>3456000</age>
|
||||
<precision>3600</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>10368000</age>
|
||||
<precision>21600</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>34560000</age>
|
||||
<precision>43200</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>63072000</age>
|
||||
<precision>86400</precision>
|
||||
</retention>
|
||||
<retention>
|
||||
<age>94608000</age>
|
||||
<precision>604800</precision>
|
||||
</retention>
|
||||
</default>
|
||||
</graphite_rollup>
|
||||
|
||||
<!-- 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>
|
||||
</yandex>
|
||||
113
deploy/docker-swarm/clickhouse-setup/docker-compose.yaml
Normal file
113
deploy/docker-swarm/clickhouse-setup/docker-compose.yaml
Normal file
@ -0,0 +1,113 @@
|
||||
version: "3"
|
||||
|
||||
services:
|
||||
clickhouse:
|
||||
image: yandex/clickhouse-server
|
||||
expose:
|
||||
- 8123
|
||||
- 9000
|
||||
ports:
|
||||
- 9001:9000
|
||||
- 8123:8123
|
||||
volumes:
|
||||
- ./clickhouse-config.xml:/etc/clickhouse-server/config.xml
|
||||
- ./docker-entrypoint-initdb.d/init-db.sql:/docker-entrypoint-initdb.d/init-db.sql
|
||||
- ./data/clickhouse/:/var/lib/clickhouse/
|
||||
|
||||
healthcheck:
|
||||
# "clickhouse", "client", "-u ${CLICKHOUSE_USER}", "--password ${CLICKHOUSE_PASSWORD}", "-q 'SELECT 1'"
|
||||
test: ["CMD", "wget", "--spider", "-q", "localhost:8123/ping"]
|
||||
interval: 30s
|
||||
timeout: 5s
|
||||
retries: 3
|
||||
|
||||
query-service:
|
||||
image: signoz/query-service:0.4.0
|
||||
container_name: query-service
|
||||
restart: always
|
||||
command: ["-config=/root/config/prometheus.yml"]
|
||||
ports:
|
||||
- "8080:8080"
|
||||
volumes:
|
||||
- ./prometheus.yml:/root/config/prometheus.yml
|
||||
- ../dashboards:/root/config/dashboards
|
||||
|
||||
environment:
|
||||
- ClickHouseUrl=tcp://clickhouse:9000
|
||||
- STORAGE=clickhouse
|
||||
- POSTHOG_API_KEY=H-htDCae7CR3RV57gUzmol6IAKtm5IMCvbcm_fwnL-w
|
||||
- GODEBUG=netdns=go
|
||||
depends_on:
|
||||
- clickhouse
|
||||
|
||||
|
||||
frontend:
|
||||
image: signoz/frontend:0.4.0
|
||||
container_name: frontend
|
||||
|
||||
depends_on:
|
||||
- query-service
|
||||
links:
|
||||
- "query-service"
|
||||
ports:
|
||||
- "3000:3000"
|
||||
volumes:
|
||||
- ../common/nginx-config.conf:/etc/nginx/conf.d/default.conf
|
||||
|
||||
|
||||
otel-collector:
|
||||
image: signoz/otelcontribcol:0.4.0
|
||||
command: ["--config=/etc/otel-collector-config.yaml", "--mem-ballast-size-mib=2000"]
|
||||
volumes:
|
||||
- ./otel-collector-config.yaml:/etc/otel-collector-config.yaml
|
||||
ports:
|
||||
- "1777:1777" # pprof extension
|
||||
- "8887:8888" # Prometheus metrics exposed by the agent
|
||||
- "14268:14268" # Jaeger receiver
|
||||
- "55678" # OpenCensus receiver
|
||||
- "55680:55680" # OTLP HTTP/2.0 legacy port
|
||||
- "55681:55681" # OTLP HTTP/1.0 receiver
|
||||
- "4317:4317" # OTLP GRPC receiver
|
||||
- "55679:55679" # zpages extension
|
||||
- "13133" # health_check
|
||||
deploy:
|
||||
mode: replicated
|
||||
replicas: 3
|
||||
depends_on:
|
||||
- clickhouse
|
||||
|
||||
otel-collector-hostmetrics:
|
||||
image: signoz/otelcontribcol:0.4.0
|
||||
command: ["--config=/etc/otel-collector-config-hostmetrics.yaml", "--mem-ballast-size-mib=683"]
|
||||
volumes:
|
||||
- ./otel-collector-config-hostmetrics.yaml:/etc/otel-collector-config-hostmetrics.yaml
|
||||
depends_on:
|
||||
- clickhouse
|
||||
|
||||
|
||||
hotrod:
|
||||
image: jaegertracing/example-hotrod:latest
|
||||
container_name: hotrod
|
||||
ports:
|
||||
- "9000:8080"
|
||||
command: ["all"]
|
||||
environment:
|
||||
- JAEGER_ENDPOINT=http://otel-collector:14268/api/traces
|
||||
|
||||
|
||||
load-hotrod:
|
||||
image: "grubykarol/locust:1.2.3-python3.9-alpine3.12"
|
||||
container_name: load-hotrod
|
||||
hostname: load-hotrod
|
||||
ports:
|
||||
- "8089:8089"
|
||||
environment:
|
||||
ATTACKED_HOST: http://hotrod:8080
|
||||
LOCUST_MODE: standalone
|
||||
NO_PROXY: standalone
|
||||
TASK_DELAY_FROM: 5
|
||||
TASK_DELAY_TO: 30
|
||||
QUIET_MODE: "${QUIET_MODE:-false}"
|
||||
LOCUST_OPTS: "--headless -u 10 -r 1"
|
||||
volumes:
|
||||
- ../common/locust-scripts:/locust
|
||||
@ -0,0 +1,27 @@
|
||||
CREATE TABLE IF NOT EXISTS signoz_index (
|
||||
timestamp DateTime64(9) CODEC(Delta, ZSTD(1)),
|
||||
traceID String CODEC(ZSTD(1)),
|
||||
spanID String CODEC(ZSTD(1)),
|
||||
parentSpanID String CODEC(ZSTD(1)),
|
||||
serviceName LowCardinality(String) CODEC(ZSTD(1)),
|
||||
name LowCardinality(String) CODEC(ZSTD(1)),
|
||||
kind Int32 CODEC(ZSTD(1)),
|
||||
durationNano UInt64 CODEC(ZSTD(1)),
|
||||
tags Array(String) CODEC(ZSTD(1)),
|
||||
tagsKeys Array(String) CODEC(ZSTD(1)),
|
||||
tagsValues Array(String) CODEC(ZSTD(1)),
|
||||
statusCode Int64 CODEC(ZSTD(1)),
|
||||
references String CODEC(ZSTD(1)),
|
||||
externalHttpMethod Nullable(String) CODEC(ZSTD(1)),
|
||||
externalHttpUrl Nullable(String) CODEC(ZSTD(1)),
|
||||
component Nullable(String) CODEC(ZSTD(1)),
|
||||
dbSystem Nullable(String) CODEC(ZSTD(1)),
|
||||
dbName Nullable(String) CODEC(ZSTD(1)),
|
||||
dbOperation Nullable(String) CODEC(ZSTD(1)),
|
||||
peerService Nullable(String) CODEC(ZSTD(1)),
|
||||
INDEX idx_tagsKeys tagsKeys TYPE bloom_filter(0.01) GRANULARITY 64,
|
||||
INDEX idx_tagsValues tagsValues TYPE bloom_filter(0.01) GRANULARITY 64,
|
||||
INDEX idx_duration durationNano TYPE minmax GRANULARITY 1
|
||||
) ENGINE MergeTree()
|
||||
PARTITION BY toDate(timestamp)
|
||||
ORDER BY (serviceName, -toUnixTimestamp(timestamp))
|
||||
@ -0,0 +1,72 @@
|
||||
receivers:
|
||||
otlp:
|
||||
protocols:
|
||||
grpc:
|
||||
http:
|
||||
jaeger:
|
||||
protocols:
|
||||
grpc:
|
||||
thrift_http:
|
||||
|
||||
hostmetrics:
|
||||
collection_interval: 60s
|
||||
scrapers:
|
||||
cpu:
|
||||
load:
|
||||
memory:
|
||||
disk:
|
||||
filesystem:
|
||||
network:
|
||||
|
||||
# Data sources: metrics
|
||||
prometheus:
|
||||
config:
|
||||
scrape_configs:
|
||||
- job_name: "otel-collector"
|
||||
dns_sd_configs:
|
||||
- names:
|
||||
- 'tasks.signoz_otel-collector'
|
||||
type: 'A'
|
||||
port: 8888
|
||||
- job_name: "otel-collector-hostmetrics"
|
||||
scrape_interval: 10s
|
||||
static_configs:
|
||||
- targets: ["otel-collector-hostmetrics:8888"]
|
||||
processors:
|
||||
batch:
|
||||
send_batch_size: 1000
|
||||
timeout: 10s
|
||||
memory_limiter:
|
||||
# Same as --mem-ballast-size-mib CLI argument
|
||||
ballast_size_mib: 683
|
||||
# 80% of maximum memory up to 2G
|
||||
limit_mib: 1500
|
||||
# 25% of limit up to 2G
|
||||
spike_limit_mib: 512
|
||||
check_interval: 5s
|
||||
# queued_retry:
|
||||
# num_workers: 4
|
||||
# queue_size: 100
|
||||
# retry_on_failure: true
|
||||
extensions:
|
||||
health_check: {}
|
||||
zpages: {}
|
||||
exporters:
|
||||
clickhouse:
|
||||
datasource: tcp://clickhouse:9000
|
||||
clickhousemetricswrite:
|
||||
endpoint: tcp://clickhouse:9000/?database=signoz_metrics
|
||||
resource_to_telemetry_conversion:
|
||||
enabled: true
|
||||
|
||||
service:
|
||||
extensions: [health_check, zpages]
|
||||
pipelines:
|
||||
traces:
|
||||
receivers: [jaeger, otlp]
|
||||
processors: [batch]
|
||||
exporters: [clickhouse]
|
||||
metrics:
|
||||
receivers: [otlp, prometheus, hostmetrics]
|
||||
processors: [batch]
|
||||
exporters: [clickhousemetricswrite]
|
||||
@ -0,0 +1,47 @@
|
||||
receivers:
|
||||
otlp:
|
||||
protocols:
|
||||
grpc:
|
||||
http:
|
||||
jaeger:
|
||||
protocols:
|
||||
grpc:
|
||||
thrift_http:
|
||||
processors:
|
||||
batch:
|
||||
send_batch_size: 1000
|
||||
timeout: 10s
|
||||
memory_limiter:
|
||||
# Same as --mem-ballast-size-mib CLI argument
|
||||
ballast_size_mib: 683
|
||||
# 80% of maximum memory up to 2G
|
||||
limit_mib: 1500
|
||||
# 25% of limit up to 2G
|
||||
spike_limit_mib: 512
|
||||
check_interval: 5s
|
||||
# queued_retry:
|
||||
# num_workers: 4
|
||||
# queue_size: 100
|
||||
# retry_on_failure: true
|
||||
extensions:
|
||||
health_check: {}
|
||||
zpages: {}
|
||||
exporters:
|
||||
clickhouse:
|
||||
datasource: tcp://clickhouse:9000
|
||||
clickhousemetricswrite:
|
||||
endpoint: tcp://clickhouse:9000/?database=signoz_metrics
|
||||
resource_to_telemetry_conversion:
|
||||
enabled: true
|
||||
|
||||
service:
|
||||
extensions: [health_check, zpages]
|
||||
pipelines:
|
||||
traces:
|
||||
receivers: [jaeger, otlp]
|
||||
processors: [batch]
|
||||
exporters: [clickhouse]
|
||||
metrics:
|
||||
receivers: [otlp]
|
||||
processors: [batch]
|
||||
exporters: [clickhousemetricswrite]
|
||||
25
deploy/docker-swarm/clickhouse-setup/prometheus.yml
Normal file
25
deploy/docker-swarm/clickhouse-setup/prometheus.yml
Normal file
@ -0,0 +1,25 @@
|
||||
# my global config
|
||||
global:
|
||||
scrape_interval: 5s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
|
||||
evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
|
||||
# scrape_timeout is set to the global default (10s).
|
||||
|
||||
# Alertmanager configuration
|
||||
alerting:
|
||||
alertmanagers:
|
||||
- static_configs:
|
||||
- targets:
|
||||
# - alertmanager:9093
|
||||
|
||||
# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
|
||||
rule_files:
|
||||
# - "first_rules.yml"
|
||||
# - "second_rules.yml"
|
||||
|
||||
# A scrape configuration containing exactly one endpoint to scrape:
|
||||
# Here it's Prometheus itself.
|
||||
scrape_configs:
|
||||
|
||||
|
||||
remote_read:
|
||||
- url: tcp://clickhouse:9000/?database=signoz_metrics
|
||||
16
deploy/docker-swarm/common/locust-scripts/locustfile.py
Normal file
16
deploy/docker-swarm/common/locust-scripts/locustfile.py
Normal file
@ -0,0 +1,16 @@
|
||||
from locust import HttpUser, task, between
|
||||
class UserTasks(HttpUser):
|
||||
wait_time = between(5, 15)
|
||||
|
||||
@task
|
||||
def rachel(self):
|
||||
self.client.get("/dispatch?customer=123&nonse=0.6308392664170006")
|
||||
@task
|
||||
def trom(self):
|
||||
self.client.get("/dispatch?customer=392&nonse=0.015296363321630757")
|
||||
@task
|
||||
def japanese(self):
|
||||
self.client.get("/dispatch?customer=731&nonse=0.8022286220408668")
|
||||
@task
|
||||
def coffee(self):
|
||||
self.client.get("/dispatch?customer=567&nonse=0.0022220379420636593")
|
||||
30
deploy/docker-swarm/common/nginx-config.conf
Normal file
30
deploy/docker-swarm/common/nginx-config.conf
Normal file
@ -0,0 +1,30 @@
|
||||
server {
|
||||
listen 3000;
|
||||
server_name _;
|
||||
|
||||
gzip on;
|
||||
gzip_static on;
|
||||
gzip_types text/plain text/css application/json application/x-javascript text/xml application/xml application/xml+rss text/javascript;
|
||||
gzip_proxied any;
|
||||
gzip_vary on;
|
||||
gzip_comp_level 6;
|
||||
gzip_buffers 16 8k;
|
||||
gzip_http_version 1.1;
|
||||
|
||||
location / {
|
||||
root /usr/share/nginx/html;
|
||||
index index.html index.htm;
|
||||
try_files $uri $uri/ /index.html;
|
||||
}
|
||||
location /api {
|
||||
proxy_pass http://query-service:8080/api;
|
||||
|
||||
}
|
||||
|
||||
# redirect server error pages to the static page /50x.html
|
||||
#
|
||||
error_page 500 502 503 504 /50x.html;
|
||||
location = /50x.html {
|
||||
root /usr/share/nginx/html;
|
||||
}
|
||||
}
|
||||
0
deploy/docker-swarm/dashboards/.gitkeep
Normal file
0
deploy/docker-swarm/dashboards/.gitkeep
Normal file
Loading…
x
Reference in New Issue
Block a user