receivers:
  httplogreceiver/json:
    endpoint: 0.0.0.0:8082
    source: json
  otlp:
    protocols:
      grpc:
        endpoint: 0.0.0.0:4317
      http:
        endpoint: 0.0.0.0:4318
  hostmetrics:
    collection_interval: 60s  # Frequency of metrics collection.
    scrapers:
      cpu: {}
      load: {}
      memory: {}
      disk: {}
      filesystem: {}
      network: {}
  docker_stats:
    endpoint: unix:///var/run/docker.sock
    collection_interval: 30s
    timeout: 10s
    api_version: "1.51"
    metrics:
      container.uptime:
        enabled: true
      container.restarts:
        enabled: true
      container.network.io.usage.rx_errors:
        enabled: true
      container.network.io.usage.tx_errors:
        enabled: true
      container.network.io.usage.rx_packets:
        enabled: true
      container.network.io.usage.tx_packets:
        enabled: true
  filelog/nginx-access-logs:
    include: ["${env:NGINX_ACCESS_LOG_FILE}"]
    operators:
      # Parse the default nginx access log format. Nginx defaults to the "combined" log format
      # $remote_addr - $remote_user [$time_local] "$request" $status $body_bytes_sent "$http_referer" "$http_user_agent"
      # For more details, see https://nginx.org/en/docs/http/ngx_http_log_module.html
      - type: regex_parser
        if: body matches '^(?P<remote_addr>[0-9\\.]+) - (?P<remote_user>[^\\s]+) \\[(?P<ts>.+)\\] "(?P<request_method>\\w+?) (?P<request_path>.+?)" (?P<status>[0-9]+) (?P<body_bytes_sent>[0-9]+) "(?P<http_referrer>.+?)" "(?P<http_user_agent>.+?)"$'
        parse_from: body
        parse_to: attributes
        regex: '^(?P<remote_addr>[0-9\.]+) - (?P<remote_user>[^\s]+) \[(?P<ts>.+)\] "(?P<request_method>\w+?) (?P<request_path>.+?)" (?P<status>[0-9]+) (?P<body_bytes_sent>[0-9]+) "(?P<http_referrer>.+?)" "(?P<http_user_agent>.+?)"$'
        timestamp:
          parse_from: attributes.ts
          layout: "02/Jan/2006:15:04:05 -0700"
          layout_type: gotime
        severity:
          parse_from: attributes.status
          overwrite_text: true
          mapping:
            debug: "1xx"
            info:
              - "2xx"
              - "3xx"
            warn: "4xx"
            error: "5xx"
      - type: remove
        if: attributes.ts != nil
        field: attributes.ts
      - type: add
        field: attributes.source
        value: nginx

  filelog/nginx-error-logs:
    include: ["${env:NGINX_ERROR_LOG_FILE}"]
    operators:
      # Parse the default nginx error log format.
      # YYYY/MM/DD HH:MM:SS [LEVEL] PID#TID: *CID MESSAGE
      # For more details, see https://github.com/phusion/nginx/blob/master/src/core/ngx_log.c
      - type: regex_parser
        if: body matches '^(?P<ts>.+?) \\[(?P<log_level>\\w+)\\] (?P<pid>\\d+)#(?P<tid>\\d+). \\*(?P<cid>\\d+) (?P<message>.+)$'
        parse_from: body
        parse_to: attributes
        regex: '^(?P<ts>.+?) \[(?P<log_level>\w+)\] (?P<pid>\d+)#(?P<tid>\d+). \*(?P<cid>\d+) (?P<message>.+)$'
        timestamp:
          parse_from: attributes.ts
          layout: "2006/01/02 15:04:05"
          layout_type: gotime
        severity:
          parse_from: attributes.log_level
          overwrite_text: true
          mapping:
            debug: "debug"
            info:
              - "info"
              - "notice"
            warn: "warn"
            error:
              - "error"
              - "crit"
              - "alert"
            fatal: "emerg"
      - type: remove
        if: attributes.ts != nil
        field: attributes.ts
      - type: move
        if: attributes.message != nil
        from: attributes.message
        to: body
      - type: add
        field: attributes.source
        value: nginx
  prometheus:
    config:
      global:
        scrape_interval: 60s
      scrape_configs:
        - job_name: otel-collector
          static_configs:
          - targets:
              - localhost:8888
            labels:
              job_name: otel-collector
processors:
  batch:
    send_batch_size: 10000
    send_batch_max_size: 11000
    timeout: 10s
  resourcedetection:
    detectors: [env, system]
    system:
      hostname_sources: [os]
  resourcedetection/env:
    detectors: [env]
    timeout: 2s
    override: false
  resourcedetection/system:
    detectors: ["system"]
    system:
      hostname_sources: ["dns", "os"]
  resourcedetection/docker:
    detectors: [env, docker]
    timeout: 2s
    override: false
  signozspanmetrics/delta:
    metrics_exporter: clickhousemetricswrite, 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
      - name: browser.platform
      - name: browser.mobile
      - name: k8s.cluster.name
      - name: k8s.node.name
      - name: k8s.namespace.name
      - name: host.name
      - name: host.type
      - name: container.name
extensions:
  health_check:
    endpoint: 0.0.0.0:13133
  pprof:
    endpoint: 0.0.0.0:1777
exporters:
  clickhousetraces:
    datasource: tcp://clickhouse:9000/signoz_traces
    low_cardinal_exception_grouping: ${env:LOW_CARDINAL_EXCEPTION_GROUPING}
    use_new_schema: true
  clickhousemetricswrite:
    endpoint: tcp://clickhouse:9000/signoz_metrics
    disable_v2: true
    resource_to_telemetry_conversion:
      enabled: true
  clickhousemetricswrite/prometheus:
    endpoint: tcp://clickhouse:9000/signoz_metrics
    disable_v2: true
  signozclickhousemetrics:
    dsn: tcp://clickhouse:9000/signoz_metrics
  clickhouselogsexporter:
    dsn: tcp://clickhouse:9000/signoz_logs
    timeout: 10s
    use_new_schema: true
  # debug: {}
  otlp/nginx-logs:
    endpoint: "localhost:4317"
    tls:
      insecure: true
service:
  telemetry:
    logs:
      encoding: json
  extensions:
    - health_check
    - pprof
  pipelines:
    traces:
      receivers: [otlp]
      processors: [signozspanmetrics/delta, batch]
      exporters: [clickhousetraces]
    metrics:
      receivers: [otlp]
      processors: [batch]
      exporters: [clickhousemetricswrite, signozclickhousemetrics, resourcedetection/docker, resourcedetection/system]
    metrics/hostmetrics:
      receivers: [hostmetrics]
      processors: [resourcedetection, resource/env]
      exporters: [otlp]
    metrics/prometheus:
      receivers: [prometheus]
      processors: [batch]
      exporters: [clickhousemetricswrite/prometheus, signozclickhousemetrics]
    logs:
      receivers: [otlp, tcplog/docker, httplogreceiver/json]
      processors: [batch]
      exporters: [clickhouselogsexporter]