Configuration Files

These are the config files that you get when running a basi setup of SigNoz.

These config files have been taken from a local instance of SigNoz running on a Apple M1 macOS system.

Tip

we can write few lines about each of these config files as well, so that users find it easy to change these files as per their need, hence, less support will be needed.

alertmanager.yml

global:
  resolve_timeout: 1m
  slack_api_url: 'https://hooks.slack.com/services/xxx'

route:
  receiver: 'slack-notifications'

receivers:
- name: 'slack-notifications'
  slack_configs:
  - channel: '#alerts'
    send_resolved: true
    icon_url: https://avatars3.githubusercontent.com/u/3380462
    title: |-
     [{{ .Status | toUpper }}{{ if eq .Status "firing" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .CommonLabels.alertname }} for {{ .CommonLabels.job }}
     {{- if gt (len .CommonLabels) (len .GroupLabels) -}}
       {{" "}}(
       {{- with .CommonLabels.Remove .GroupLabels.Names }}
         {{- range $index, $label := .SortedPairs -}}
           {{ if $index }}, {{ end }}
           {{- $label.Name }}="{{ $label.Value -}}"
         {{- end }}
       {{- end -}}
       )
     {{- end }}
    text: >-
     {{ range .Alerts -}}
     *Alert:* {{ .Annotations.title }}{{ if .Labels.severity }} - `{{ .Labels.severity }}`{{ end }}

     *Description:* {{ .Annotations.description }}

     *Details:*
       {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}`
       {{ end }}
     {{ end }}

alerts.yml

groups:
- name: ExampleCPULoadGroup
  rules:
  - alert: HighCpuLoad
    expr: system_cpu_load_average_1m > 0.1
    for: 0m
    labels:
      severity: warning
    annotations:
      summary: High CPU load
      description: "CPU load is > 0.1\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

docker-compose.arm.yml

version: "2.4"

services:
  clickhouse:
    image: altinity/clickhouse-server:21.12.3.32.altinitydev.arm
    # ports:
    #   - "9000:9000"
    #   - "8123:8123"
    volumes:
      - ./clickhouse-config.xml:/etc/clickhouse-server/config.xml
      - ./data/clickhouse/:/var/lib/clickhouse/
    restart: on-failure
    logging:
      options:
        max-size: 50m
        max-file: "3"
    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

  alertmanager:
    image: signoz/alertmanager:0.6.1
    volumes:
      - ./data/alertmanager:/data
    depends_on:
      query-service:
        condition: service_healthy
    restart: on-failure
    command:
      - --queryService.url=http://query-service:8080
      - --storage.path=/data

  query-service:
    image: signoz/query-service:0.7.5
    container_name: query-service
    command: ["-config=/root/config/prometheus.yml"]
    volumes:
      - ./prometheus.yml:/root/config/prometheus.yml
      - ../dashboards:/root/config/dashboards
      - ./data/signoz/:/var/lib/signoz/
    environment:
      - ClickHouseUrl=tcp://clickhouse:9000
      - STORAGE=clickhouse
      - GODEBUG=netdns=go
      - TELEMETRY_ENABLED=true
      - DEPLOYMENT_TYPE=docker-standalone-arm
      
    restart: on-failure
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "localhost:8080/api/v1/version"]
      interval: 30s
      timeout: 5s
      retries: 3
    depends_on:
      clickhouse:
        condition: service_healthy

  frontend:
    image: signoz/frontend:0.7.5
    container_name: frontend
    restart: on-failure
    depends_on:
      - alertmanager
      - query-service
    ports:
      - "3301:3301"
    volumes:
      - ../common/nginx-config.conf:/etc/nginx/conf.d/default.conf

  otel-collector:
    image: signoz/otelcontribcol:0.43.0
    command: ["--config=/etc/otel-collector-config.yaml"]
    volumes:
      - ./otel-collector-config.yaml:/etc/otel-collector-config.yaml
    ports:
      - "4317:4317"     # OTLP gRPC receiver
      - "4318:4318"     # OTLP HTTP receiver
      # - "8889:8889"     # Prometheus metrics exposed by the agent
      # - "13133"         # health_check
      # - "14268:14268"   # Jaeger receiver
      # - "55678:55678"   # OpenCensus receiver
      # - "55679:55679"   # zpages extension
      # - "55680:55680"   # OTLP gRPC legacy receiver
      # - "55681:55681"   # OTLP HTTP legacy receiver
    mem_limit: 2000m
    restart: on-failure
    depends_on:
      clickhouse:
        condition: service_healthy

  otel-collector-metrics:
    image: signoz/otelcontribcol:0.43.0
    command: ["--config=/etc/otel-collector-metrics-config.yaml"]
    volumes:
      - ./otel-collector-metrics-config.yaml:/etc/otel-collector-metrics-config.yaml
    restart: on-failure
    depends_on:
      clickhouse:
        condition: service_healthy

  hotrod:
    image: jaegertracing/example-hotrod:1.30
    container_name: hotrod
    logging:
      options:
        max-size: 50m
        max-file: "3"
    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
    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

docker-compose.yml

version: "2.4"

services:
  clickhouse:
    image: yandex/clickhouse-server:21.12.3.32
    # ports:
    #   - "9000:9000"
    #   - "8123:8123"
    volumes:
      - ./clickhouse-config.xml:/etc/clickhouse-server/config.xml
      - ./data/clickhouse/:/var/lib/clickhouse/
    restart: on-failure
    logging:
      options:
        max-size: 50m
        max-file: "3"
    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

  alertmanager:
    image: signoz/alertmanager:0.6.1
    volumes:
      - ./data/alertmanager:/data
    depends_on:
      query-service:
        condition: service_healthy
    restart: on-failure
    command:
      - --queryService.url=http://query-service:8080
      - --storage.path=/data

# Notes for Maintainers/Contributors who will change Line Numbers of Frontend & Query-Section. Please Update Line Numbers in `./scripts/commentLinesForSetup.sh` & `./CONTRIBUTING.md`

  query-service:
    image: signoz/query-service:0.7.5
    container_name: query-service
    command: ["-config=/root/config/prometheus.yml"]
    volumes:
      - ./prometheus.yml:/root/config/prometheus.yml
      - ../dashboards:/root/config/dashboards
      - ./data/signoz/:/var/lib/signoz/
    environment:
      - ClickHouseUrl=tcp://clickhouse:9000
      - STORAGE=clickhouse
      - GODEBUG=netdns=go
      - TELEMETRY_ENABLED=true
      - DEPLOYMENT_TYPE=docker-standalone-amd
    restart: on-failure
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "localhost:8080/api/v1/version"]
      interval: 30s
      timeout: 5s
      retries: 3
    depends_on:
      clickhouse:
        condition: service_healthy

  frontend:
    image: signoz/frontend:0.7.5
    container_name: frontend
    restart: on-failure
    depends_on:
      - alertmanager
      - query-service
    ports:
      - "3301:3301"
    volumes:
      - ../common/nginx-config.conf:/etc/nginx/conf.d/default.conf

  otel-collector:
    image: signoz/otelcontribcol:0.43.0
    command: ["--config=/etc/otel-collector-config.yaml"]
    volumes:
      - ./otel-collector-config.yaml:/etc/otel-collector-config.yaml
    ports:
      - "4317:4317"     # OTLP gRPC receiver
      - "4318:4318"     # OTLP HTTP receiver
      # - "8889:8889"     # Prometheus metrics exposed by the agent
      # - "13133"         # health_check
      # - "14268:14268"   # Jaeger receiver
      # - "55678:55678"   # OpenCensus receiver
      # - "55679:55679"   # zpages extension
      # - "55680:55680"   # OTLP gRPC legacy receiver
      # - "55681:55681"   # OTLP HTTP legacy receiver
    mem_limit: 2000m
    restart: on-failure
    depends_on:
      clickhouse:
        condition: service_healthy

  otel-collector-metrics:
    image: signoz/otelcontribcol:0.43.0
    command: ["--config=/etc/otel-collector-metrics-config.yaml"]
    volumes:
      - ./otel-collector-metrics-config.yaml:/etc/otel-collector-metrics-config.yaml
    restart: on-failure
    depends_on:
      clickhouse:
        condition: service_healthy

  hotrod:
    image: jaegertracing/example-hotrod:1.30
    container_name: hotrod
    logging:
      options:
        max-size: 50m
        max-file: "3"
    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
    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
"

otel-collector-config.yml

receivers:
  otlp/spanmetrics:
    protocols:
      grpc:
        endpoint: "localhost:12345"
  otlp:
    protocols:
      grpc:
      http:
  jaeger:
    protocols:
      grpc:
      thrift_http:
  hostmetrics:
    collection_interval: 30s
    scrapers:
      cpu:
      load:
      memory:
      disk:
      filesystem:
      network:
processors:
  batch:
    send_batch_size: 1000
    timeout: 10s
  signozspanmetrics/prometheus:
    metrics_exporter: prometheus
    latency_histogram_buckets: [100us, 1ms, 2ms, 6ms, 10ms, 50ms, 100ms, 250ms, 500ms, 1000ms, 1400ms, 2000ms, 5s, 10s, 20s, 40s, 60s ]
    dimensions_cache_size: 10000
  # memory_limiter:
  #   # 80% of maximum memory up to 2G
  #   limit_mib: 1500
  #   # 25% of limit up to 2G
  #   spike_limit_mib: 512
  #   check_interval: 5s
  #
  #   # 50% of the maximum memory
  #   limit_percentage: 50
  #   # 20% of max memory usage spike expected
  #   spike_limit_percentage: 20
  # 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
  prometheus:
    endpoint: "0.0.0.0:8889"
service:
  extensions: [health_check, zpages]
  pipelines:
    traces:
      receivers: [jaeger, otlp]
      processors: [signozspanmetrics/prometheus, batch]
      exporters: [clickhouse]
    metrics:
      receivers: [otlp, hostmetrics]
      processors: [batch]
      exporters: [clickhousemetricswrite]
    metrics/spanmetrics:
      receivers: [otlp/spanmetrics]
      exporters: [prometheus]

otel-collector-metrics-config.yml

receivers:
  otlp:
    protocols:
      grpc:
      http:

  # Data sources: metrics
  prometheus:
    config:
      scrape_configs:
        - job_name: "otel-collector"
          scrape_interval: 30s
          static_configs:
            - targets: ["otel-collector:8889"]
processors:
  batch:
    send_batch_size: 1000
    timeout: 10s
  # memory_limiter:
  #   # 80% of maximum memory up to 2G
  #   limit_mib: 1500
  #   # 25% of limit up to 2G
  #   spike_limit_mib: 512
  #   check_interval: 5s
  #
  #   # 50% of the maximum memory
  #   limit_percentage: 50
  #   # 20% of max memory usage spike expected
  #   spike_limit_percentage: 20
  # queued_retry:
  #   num_workers: 4
  #   queue_size: 100
  #   retry_on_failure: true
extensions:
  health_check: {}
  zpages: {}
exporters:
  clickhousemetricswrite:
    endpoint: tcp://clickhouse:9000/?database=signoz_metrics

service:
  extensions: [health_check, zpages]
  pipelines:
    metrics:
      receivers: [otlp, prometheus]
      processors: [batch]
      exporters: [clickhousemetricswrite]

prometheus.yml

# 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"
  - 'alerts.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