coolify/templates/compose/signoz.yaml

# documentation: https://signoz.io/docs/introduction/
# slogan: An observability platform native to OpenTelemetry with logs, traces and metrics.
# category: monitoring
# tags: telemetry, server, applications, interface, logs, monitoring, traces, metrics
# logo: svgs/signoz.svg
# port: 8080

services:
  init-clickhouse:
    image: clickhouse/clickhouse-server:25.12.5-alpine
    command:
      - bash
      - -c
      - |
        version="v0.0.1"
        node_os=$$(uname -s | tr '[:upper:]' '[:lower:]')
        node_arch=$$(uname -m | sed s/aarch64/arm64/ | sed s/x86_64/amd64/)
        echo "Fetching histogram-binary for $${node_os}/$${node_arch}"
        cd /tmp
        wget -O histogram-quantile.tar.gz "https://github.com/SigNoz/signoz/releases/download/histogram-quantile%2F$${version}/histogram-quantile_$${node_os}_$${node_arch}.tar.gz"
        tar -xvzf histogram-quantile.tar.gz
        mv histogram-quantile /var/lib/clickhouse/user_scripts/histogramQuantile
    restart: on-failure
    exclude_from_hc: true
    logging:
      options:
        max-size: 50m
        max-file: "3"
    volumes:
      - type: volume
        source: user-scripts
        target: /var/lib/clickhouse/user_scripts

  zookeeper:
    image: signoz/zookeeper:3.9.3
    user: root
    healthcheck:
      test:
        - CMD-SHELL
        - curl -s -m 2 http://localhost:8080/commands/ruok | grep error | grep null
      interval: 30s
      timeout: 5s
      retries: 3
    logging:
      options:
        max-size: 50m
        max-file: "3"
    volumes:
      - zookeeper:/bitnami/zookeeper
    environment:
      - ALLOW_ANONYMOUS_LOGIN=${ZOO_ALLOW_ANONYMOUS_LOGIN:-yes}
      - ZOO_AUTOPURGE_INTERVAL=${ZOO_AUTOPURGE_INTERVAL:-1}
      - ZOO_ENABLE_PROMETHEUS_METRICS=${ZOO_ENABLE_PROMETHEUS_METRICS:-yes}
      - ZOO_PROMETHEUS_METRICS_PORT_NUMBER=${ZOO_PROMETHEUS_METRICS_PORT_NUMBER:-9141}

  clickhouse:
    image: clickhouse/clickhouse-server:25.12.5-alpine
    tty: true
    depends_on:
      init-clickhouse:
        condition: service_completed_successfully
      zookeeper:
        condition: service_healthy
    healthcheck:
      test:
        - CMD
        - wget
        - -q
        - -O-
        - 0.0.0.0:8123/ping
      interval: 30s
      timeout: 5s
      retries: 3
    ulimits:
      nproc: 65535
      nofile:
        soft: 262144
        hard: 262144
    logging:
      options:
        max-size: 50m
        max-file: "3"
    environment:
      - CLICKHOUSE_SKIP_USER_SETUP=1
    volumes:
      - type: volume
        source: clickhouse
        target: /var/lib/clickhouse/
      - type: volume
        source: user-scripts
        target: /var/lib/clickhouse/user_scripts
        read_only: true
      - type: bind
        source: ./clickhouse/custom-function.xml
        target: /etc/clickhouse-server/custom-function.xml
        content: |
          <functions>
              <function>
                  <type>executable</type>
                  <name>histogramQuantile</name>
                  <return_type>Float64</return_type>
                  <argument>
                      <type>Array(Float64)</type>
                      <name>buckets</name>
                  </argument>
                  <argument>
                      <type>Array(Float64)</type>
                      <name>counts</name>
                  </argument>
                  <argument>
                      <type>Float64</type>
                      <name>quantile</name>
                  </argument>
                  <format>CSV</format>
                  <command>./histogramQuantile</command>
              </function>
          </functions>
      - type: bind
        source: ./clickhouse/cluster.xml
        target: /etc/clickhouse-server/config.d/cluster.xml
        content: |
          <?xml version="1.0"?>
          <clickhouse>
              <zookeeper>
                  <node index="1">
                      <host>zookeeper</host>
                      <port>2181</port>
                  </node>
              </zookeeper>
              <remote_servers>
                  <cluster>
                      <shard>
                          <replica>
                              <host>clickhouse</host>
                              <port>9000</port>
                          </replica>
                      </shard>
                  </cluster>
              </remote_servers>
              <macros>
                  <shard>01</shard>
                  <replica>replica01</replica>
              </macros>
              <user_scripts_path>/var/lib/clickhouse/user_scripts/</user_scripts_path>
              <user_defined_executable_functions_config>*function.xml</user_defined_executable_functions_config>
          </clickhouse>
      - type: bind
        source: ./clickhouse/system-logs.xml
        target: /etc/clickhouse-server/config.d/system-logs.xml
        content: |
          <?xml version="1.0"?>
          <clickhouse>
              <query_log>
                  <ttl>event_date + INTERVAL 1 DAY DELETE</ttl>
                  <flush_interval_milliseconds>30000</flush_interval_milliseconds>
              </query_log>
              <query_thread_log>
                  <ttl>event_date + INTERVAL 1 DAY DELETE</ttl>
              </query_thread_log>
              <query_metric_log>
                  <ttl>event_date + INTERVAL 1 DAY DELETE</ttl>
              </query_metric_log>
              <query_views_log>
                  <ttl>event_date + INTERVAL 1 DAY DELETE</ttl>
              </query_views_log>
              <part_log>
                  <ttl>event_date + INTERVAL 1 DAY DELETE</ttl>
              </part_log>
              <metric_log>
                  <ttl>event_date + INTERVAL 1 DAY DELETE</ttl>
                  <flush_interval_milliseconds>30000</flush_interval_milliseconds>
              </metric_log>
              <asynchronous_metric_log>
                  <ttl>event_date + INTERVAL 1 DAY DELETE</ttl>
              </asynchronous_metric_log>
              <trace_log>
                  <ttl>event_date + INTERVAL 1 DAY DELETE</ttl>
                  <flush_interval_milliseconds>30000</flush_interval_milliseconds>
              </trace_log>
              <error_log>
                  <ttl>event_date + INTERVAL 1 DAY DELETE</ttl>
              </error_log>
              <processors_profile_log>
                  <ttl>event_date + INTERVAL 1 DAY DELETE</ttl>
                  <flush_interval_milliseconds>30000</flush_interval_milliseconds>
              </processors_profile_log>
              <text_log>
                  <ttl>event_date + INTERVAL 1 DAY DELETE</ttl>
                  <flush_interval_milliseconds>30000</flush_interval_milliseconds>
              </text_log>
          </clickhouse>

  signoz:
    image: signoz/signoz:v0.137.1
    depends_on:
      clickhouse:
        condition: service_healthy
      telemetrystore-migrator:
        condition: service_completed_successfully
    logging:
      options:
        max-size: 50m
        max-file: "3"
    volumes:
      - type: volume
        source: sqlite
        target: /var/lib/signoz/
    environment:
      - SERVICE_URL_SIGNOZ_8080
      - SIGNOZ_TOKENIZER_JWT_SECRET=${SERVICE_REALBASE64_JWTSECRET}
      - SIGNOZ_SQLSTORE_PROVIDER=sqlite
      - SIGNOZ_SQLSTORE_SQLITE_PATH=/var/lib/signoz/signoz.db
      - SIGNOZ_TELEMETRYSTORE_PROVIDER=clickhouse
      - SIGNOZ_TELEMETRYSTORE_CLICKHOUSE_DSN=tcp://clickhouse:9000
      - GODEBUG=netdns=go
      - DEPLOYMENT_TYPE=docker-standalone-amd
      - SIGNOZ_STATSREPORTER_ENABLED=${SIGNOZ_STATSREPORTER_ENABLED:-true}
      - SIGNOZ_EMAILING_ENABLED=${SIGNOZ_EMAILING_ENABLED:-false}
      - SIGNOZ_EMAILING_SMTP_ADDRESS=${SIGNOZ_EMAILING_SMTP_ADDRESS}
      - SIGNOZ_EMAILING_SMTP_FROM=${SIGNOZ_EMAILING_SMTP_FROM}
      - SIGNOZ_EMAILING_SMTP_AUTH_USERNAME=${SIGNOZ_EMAILING_SMTP_AUTH_USERNAME}
      - SIGNOZ_EMAILING_SMTP_AUTH_PASSWORD=${SIGNOZ_EMAILING_SMTP_AUTH_PASSWORD}
      - SIGNOZ_ALERTMANAGER_PROVIDER=signoz
      - SIGNOZ_ALERTMANAGER_SIGNOZ_GLOBAL_SMTP__AUTH__PASSWORD=${SIGNOZ_ALERTMANAGER_SIGNOZ_GLOBAL_SMTP__AUTH__PASSWORD}
      - SIGNOZ_ALERTMANAGER_SIGNOZ_GLOBAL_SMTP__AUTH__USERNAME=${SIGNOZ_ALERTMANAGER_SIGNOZ_GLOBAL_SMTP__AUTH__USERNAME}
      - SIGNOZ_ALERTMANAGER_SIGNOZ_GLOBAL_SMTP__FROM=${SIGNOZ_ALERTMANAGER_SIGNOZ_GLOBAL_SMTP__FROM}
      - SIGNOZ_ALERTMANAGER_SIGNOZ_GLOBAL_SMTP__SMARTHOST=${SIGNOZ_ALERTMANAGER_SIGNOZ_GLOBAL_SMTP__SMARTHOST}
      - DOT_METRICS_ENABLED=true
    healthcheck:
      test:
        - CMD
        - wget
        - --spider
        - -q
        - localhost:8080/api/v1/health
      interval: 30s
      timeout: 5s
      retries: 3

  telemetrystore-migrator:
    image: signoz/signoz-otel-collector:v0.144.8
    depends_on:
      clickhouse:
        condition: service_healthy
    entrypoint:
      - /bin/sh
      - -c
    command:
      - |
        /signoz-otel-collector migrate bootstrap --clickhouse-dsn tcp://clickhouse:9000 &&
        /signoz-otel-collector migrate sync up --clickhouse-dsn tcp://clickhouse:9000 &&
        /signoz-otel-collector migrate async up --clickhouse-dsn tcp://clickhouse:9000
    environment:
      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_DSN=tcp://clickhouse:9000
      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_CLUSTER=cluster
      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_REPLICATION=true
      - SIGNOZ_OTEL_COLLECTOR_TIMEOUT=10m
    restart: on-failure
    exclude_from_hc: true
    logging:
      options:
        max-size: 50m
        max-file: "3"

  otel-collector:
    image: signoz/signoz-otel-collector:v0.144.8
    depends_on:
      clickhouse:
        condition: service_healthy
      telemetrystore-migrator:
        condition: service_completed_successfully
      signoz:
        condition: service_healthy
    logging:
      options:
        max-size: 50m
        max-file: "3"
    entrypoint:
      - /bin/sh
    command:
      - -c
      - |
        set -e
        cat > /tmp/otel-config.yaml <<'SIGNOZ_CFG'
        connectors:
          signozmeter:
            metrics_flush_interval: 1h
            dimensions:
              - name: service.name
              - name: deployment.environment
              - name: host.name
        receivers:
          otlp:
            protocols:
              grpc:
                endpoint: 0.0.0.0:4317
              http:
                endpoint: 0.0.0.0:4318
                auth:
                  authenticator: basicauth/server
        processors:
          batch:
            send_batch_size: 50000
            send_batch_max_size: 55000
            timeout: 5s
          batch/meter:
            send_batch_size: 20000
            send_batch_max_size: 25000
            timeout: 5s
          signozspanmetrics/delta:
            metrics_exporter: signozclickhousemetrics
            metrics_flush_interval: 60s
            latency_histogram_buckets: [100us, 1ms, 2ms, 6ms, 10ms, 50ms, 100ms, 250ms, 500ms, 1000ms, 1400ms, 2000ms, 5s, 10s, 20s, 40s, 60s]
            dimensions_cache_size: 100000
            aggregation_temporality: AGGREGATION_TEMPORALITY_DELTA
            enable_exp_histogram: true
            dimensions:
              - name: service.namespace
                default: default
              - name: deployment.environment
                default: default
              # This is added to ensure the uniqueness of the timeseries
              # Otherwise, identical timeseries produced by multiple replicas of
              # collectors result in incorrect APM metrics
              - name: signoz.collector.id
              - name: service.version
        exporters:
          clickhousetraces:
            datasource: tcp://clickhouse:9000/signoz_traces
            low_cardinal_exception_grouping: false
            use_new_schema: true
            timeout: 45s
            sending_queue:
              enabled: false
          signozclickhousemetrics:
            dsn: tcp://clickhouse:9000/signoz_metrics
            timeout: 45s
            sending_queue:
              enabled: false
          clickhouselogsexporter:
            dsn: tcp://clickhouse:9000/signoz_logs
            use_new_schema: true
            timeout: 45s
            sending_queue:
              enabled: false
          signozclickhousemeter:
            dsn: tcp://clickhouse:9000/signoz_meter
            timeout: 45s
            sending_queue:
              enabled: false
          metadataexporter:
            enabled: true
            dsn: tcp://clickhouse:9000/signoz_metadata
            timeout: 45s
            cache:
              provider: in_memory
        extensions:
          signoz_health_check:
            endpoint: 0.0.0.0:13133
          pprof:
            endpoint: 0.0.0.0:1777
          basicauth/server:
            htpasswd:
              inline: "$${env:OTEL_BASIC_AUTH}\n"
        service:
          telemetry:
            logs:
              encoding: json
          extensions:
            - signoz_health_check
            - pprof
            - basicauth/server
          pipelines:
            traces:
              receivers: [otlp]
              processors: [signozspanmetrics/delta, batch]
              exporters: [clickhousetraces, signozmeter, metadataexporter]
            metrics:
              receivers: [otlp]
              processors: [batch]
              exporters: [signozclickhousemetrics, signozmeter, metadataexporter]
            logs:
              receivers: [otlp]
              processors: [batch]
              exporters: [clickhouselogsexporter, signozmeter, metadataexporter]
            metrics/meter:
              receivers: [signozmeter]
              processors: [batch/meter]
              exporters: [signozclickhousemeter]
        SIGNOZ_CFG
        cat > /tmp/opamp-config.yaml <<'SIGNOZ_OPAMP'
        server_endpoint: ws://signoz:4320/v1/opamp
        SIGNOZ_OPAMP
        /signoz-otel-collector migrate sync check
        exec /signoz-otel-collector --config=/tmp/otel-config.yaml --manager-config=/tmp/opamp-config.yaml --copy-path=/var/tmp/collector-config.yaml
    environment:
      - SERVICE_URL_OTELCOLLECTORHTTP_4318
      - OTEL_RESOURCE_ATTRIBUTES=host.name=signoz-host,os.type=linux
      - LOW_CARDINAL_EXCEPTION_GROUPING=false
      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_DSN=tcp://clickhouse:9000
      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_CLUSTER=cluster
      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_REPLICATION=true
      - SIGNOZ_OTEL_COLLECTOR_TIMEOUT=10m
      - OTEL_BASIC_AUTH=signoz:${SERVICE_PASSWORD_64_OTELAUTH}
    healthcheck:
      test: bash -c "exec 6<> /dev/tcp/localhost/13133"
      interval: 30s
      timeout: 5s
      retries: 3