# Minimum configuration file for the OpenTelemetry Collector Contrib distribution
# https://github.com/open-telemetry/opentelemetry-collector-contrib
#
# For official documentation, see the following page:
# https://docs.splunk.com/Observability/gdi/other-ingestion-methods/upstream-collector.html

# The following environment variables are required to be manually defined or
# configured below:
# - SPLUNK_ACCESS_TOKEN: The Splunk access token to authenticate requests
# - SPLUNK_API_URL: The Splunk API URL, e.g. https://api.us0.signalfx.com
# - SPLUNK_MEMORY_LIMIT_MIB: 90% of memory allocated
# - SPLUNK_HEC_TOKEN: The Splunk HEC authentication token
# - SPLUNK_HEC_URL: The Splunk HEC endpoint URL, e.g. https://http-inputs-acme.splunkcloud.com/services/collector
# - SPLUNK_INGEST_URL: The Splunk ingest URL, e.g. https://ingest.us0.signalfx.com

extensions:
  headers_setter:
    headers:
      - action: upsert
        key: X-SF-TOKEN
        from_context: X-SF-TOKEN
        default_value: "${SPLUNK_ACCESS_TOKEN}"
  health_check:
    endpoint: 0.0.0.0:13133
  http_forwarder:
    ingress:
      endpoint: 0.0.0.0:6060
    egress:
      endpoint: "${SPLUNK_API_URL}"
      # Use instead when sending to gateway
      #endpoint: "${SPLUNK_GATEWAY_URL}"
  zpages:
    #endpoint: 0.0.0.0:55679
    expvar:
      enabled: true

receivers:
  fluentforward:
    endpoint: 127.0.0.1:8006
  hostmetrics:
    collection_interval: 10s
    scrapers:
      cpu:
      disk:
      filesystem:
      memory:
      network:
      # System load average metrics https://en.wikipedia.org/wiki/Load_(computing)
      load:
      # Paging/Swap space utilization and I/O metrics
      paging:
      # Aggregated system process count metrics
      processes:
      # System processes metrics, disabled by default
      # process:
  jaeger:
    protocols:
      grpc:
        endpoint: 0.0.0.0:14250
      thrift_binary:
        endpoint: 0.0.0.0:6832
      thrift_compact:
        endpoint: 0.0.0.0:6831
      thrift_http:
        endpoint: 0.0.0.0:14268
  otlp:
    protocols:
      grpc:
        endpoint: 0.0.0.0:4317
        # Uncomment below config to preserve incoming access token and use it instead of the token value set in exporter config
        # include_metadata: true
      http:
        endpoint: 0.0.0.0:4318
        # Uncomment below config to preserve incoming access token and use it instead of the token value set in exporter config
        # include_metadata: true
  # This section is used to collect the OpenTelemetry Collector metrics
  # Even if just a Splunk APM customer, these metrics are included
  prometheus/internal:
    config:
      scrape_configs:
      - job_name: 'otel-collector'
        scrape_interval: 10s
        static_configs:
        - targets: ['0.0.0.0:8888']
        metric_relabel_configs:
          - source_labels: [ __name__ ]
            regex: 'promhttp_metric_handler_errors.*'
            action: drop
          - source_labels: [ __name__ ]
            regex: 'otelcol_processor_batch_.*'
            action: drop
  zipkin:
    endpoint: 0.0.0.0:9411
  nop:

processors:
  batch:
    metadata_keys:
      - X-SF-Token
  # Enabling the memory_limiter is strongly recommended for every pipeline.
  # Configuration is based on the amount of memory allocated to the collector.
  # In general, the limit should be 90% of the collector's memory. The simplest way to specify the
  # memory allocation is set the value of GOMEMLIMIT env variable.
  # For more information about memory limiter, see
  # https://github.com/open-telemetry/opentelemetry-collector/blob/main/processor/memorylimiter/README.md
  memory_limiter:
    check_interval: 2s
    limit_mib: ${SPLUNK_MEMORY_LIMIT_MIB}

  # Detect if the collector is running on a cloud system, which is important for creating unique cloud provider dimensions.
  # Detector order is important: the `system` detector goes last so it can't preclude cloud detectors from setting host/os info.
  # Resource detection processor is configured to override all host and cloud attributes because instrumentation
  # libraries can send wrong values from container environments.
  # https://github.com/open-telemetry/opentelemetry-collector-contrib/tree/main/processor/resourcedetectionprocessor#ordering
  resourcedetection:
    detectors: [gcp, ecs, ec2, azure, system]
    override: true

  # Optional: The following processor can be used to add a default "deployment.environment" attribute to the logs and
  # traces when it's not populated by instrumentation libraries.
  # If enabled, make sure to enable this processor in the pipeline below.
  #resource/add_environment:
    #attributes:
      #- action: insert
        #value: staging/production/...
        #key: deployment.environment

exporters:
  # Traces
  otlphttp:
    traces_endpoint: "${SPLUNK_INGEST_URL}/v2/trace/otlp"
    headers:
      "X-SF-Token": "${SPLUNK_ACCESS_TOKEN}"
    auth:
      authenticator: headers_setter
  # Metrics + Events
  signalfx:
    access_token: "${SPLUNK_ACCESS_TOKEN}"
    api_url: "${SPLUNK_API_URL}"
    ingest_url: "${SPLUNK_INGEST_URL}"
    # Use instead when sending to gateway
    #api_url: http://${SPLUNK_GATEWAY_URL}:6060
    #ingest_url: http://${SPLUNK_GATEWAY_URL}:9943
    sync_host_metadata: true
    correlation:
  # Entities (applicable only if discovery mode is enabled)
  otlphttp/entities:
    logs_endpoint: "${SPLUNK_INGEST_URL}/v3/event"
    # Use instead when sending to gateway
    # endpoint: http://${SPLUNK_GATEWAY_URL}:4318
    headers:
      "X-SF-Token": "${SPLUNK_ACCESS_TOKEN}"
    auth:
      authenticator: headers_setter
  splunk_hec/profiling:
    token: "${SPLUNK_ACCESS_TOKEN}"
    endpoint: "https://ingest.${SPLUNK_REALM}.signalfx.com/v1/log"
    log_data_enabled: false
  # Send to gateway
  otlp/gateway:
    endpoint: "${SPLUNK_GATEWAY_URL}:4317"
    tls:
      insecure: true
    auth:
      authenticator: headers_setter
  # Debug
  debug:
    verbosity: detailed

service:
  extensions: [headers_setter, health_check, http_forwarder, zpages]
  pipelines:
    # Required for Splunk APM
    traces:
      receivers: [jaeger, otlp, zipkin]
      processors:
      - memory_limiter
      - batch
      - resourcedetection
      #- resource/add_environment
      exporters: [otlphttp, signalfx]
      # Use instead when sending to gateway
      #exporters: [otlp/gateway, signalfx]
    # Required for Splunk Infrastructure Monitoring
    metrics:
      receivers: [hostmetrics, otlp]
      processors: [memory_limiter, batch, resourcedetection]
      exporters: [signalfx]
      # Use instead when sending to gateway
      #exporters: [otlp/gateway]
    # Required for Splunk APM and/or Infrastructure Monitoring
    metrics/internal:
      receivers: [prometheus/internal]
      processors: [memory_limiter, batch, resourcedetection]
      exporters: [signalfx]
      # Use instead when sending to gateway
      #exporters: [otlp/gateway]
    logs/entities:
      # Receivers are dynamically added if discovery mode is enabled
      receivers: [nop]
      processors: [memory_limiter, batch, resourcedetection]
      exporters: [otlphttp/entities]
    # Required for profiling
    logs:
      receivers: [otlp]
      processors:
      - memory_limiter
      - batch
      - resourcedetection
      #- resource/add_environment
      exporters: [splunk_hec/profiling]
      # Use instead when sending to gateway
      #exporters: [otlp/gateway]