Agent Controlでシステムを計装します

chart_values:
  newrelic-infrastructure:
    kubelet:
      tolerations:
        - operator: "Exists"
          effect: "NoSchedule"
        - operator: "Exists"
          effect: "NoExecute"
    common:
      config:
        interval: 30s

chart_values:
  newrelic-logging:
    resources:
      limits:
        cpu: 200m
      requests:
        cpu: 200m

chart_values:
  newrelic-prometheus-agent:
    lowDataMode: true
    config:
      kubernetes:
        integrations_filter:
          enabled: false

chart_values:
  nr-k8s-otel-collector:
    receivers:
      filelog:
        enabled: false

config_agent:
  license_key: '${nr-env:NEW_RELIC_LICENSE_KEY}'
  custom_attributes:
    env: production
config_logging:
  logging.yml:
    logs:
      - name: syslog
        file: /var/log/syslog
        attributes:
          logtype: linux_syslog

config:
  integrations:
    - name: nri-mysql
      env:
        HOSTNAME: localhost
        PORT: 3306
        USERNAME: newrelic
        PASSWORD: ${nr-env:MYSQL_PASSWORD}
        REMOTE_MONITORING: true
      interval: 30s

config:
  integrations:
    - name: nri-flex
      config:
        name: diskUsage
        apis:
          - event_type: DiskUsageSample
            commands:
              - run: df -kP /
                split: horizontal
                split_by: \s+
                set_header: [filesystem, blocks, used, available, usePercent, mountpoint]
                row_start: 1

config:
  # Variables set automatically by Agent Control:
  # - NEW_RELIC_LICENSE_KEY: New Relic ingest license key.
  # - OTEL_EXPORTER_OTLP_ENDPOINT: OTLP endpoint (see: https://docs.newrelic.com/docs/opentelemetry/best-practices/opentelemetry-otlp/).

  extensions:
    health_check:

  receivers:
    otlp:
      protocols:
        grpc:
        http:

    hostmetrics:
      collection_interval: 60s
      scrapers:
        cpu:
          metrics:
            system.cpu.time:
              enabled: false
            system.cpu.utilization:
              enabled: true
        load:
        memory:
          metrics:
            system.memory.utilization:
              enabled: true
        paging:
          metrics:
            system.paging.utilization:
              enabled: false
            system.paging.faults:
              enabled: false
        filesystem:
          metrics:
            system.filesystem.utilization:
              enabled: true
        disk:
          metrics:
            system.disk.merged:
              enabled: false
            system.disk.pending_operations:
              enabled: false
            system.disk.weighted_io_time:
              enabled: false
        network:
          metrics:
            system.network.connections:
              enabled: false
        # Uncomment to enable process metrics, which can be noisy but valuable.
        # processes:
        # process:
        #  metrics:
        #    process.cpu.utilization:
        #      enabled: true
        #    process.cpu.time:
        #      enabled: false

    filelog:
      include:
        - /var/log/alternatives.log
        - /var/log/cloud-init.log
        - /var/log/auth.log
        - /var/log/dpkg.log
        - /var/log/syslog
        - /var/log/messages
        - /var/log/secure
        - /var/log/yum.log

  processors:
    metricstransform:
      transforms:
        - include: system.cpu.utilization
          action: update
          operations:
            - action: aggregate_labels
              label_set: [state]
              aggregation_type: mean
        - include: system.paging.operations
          action: update
          operations:
            - action: aggregate_labels
              label_set: [direction]
              aggregation_type: sum
    filter/exclude_cpu_utilization:
      metrics:
        datapoint:
          - 'metric.name == "system.cpu.utilization" and attributes["state"] == "interrupt"'
          - 'metric.name == "system.cpu.utilization" and attributes["state"] == "nice"'
          - 'metric.name == "system.cpu.utilization" and attributes["state"] == "softirq"'
    filter/exclude_memory_utilization:
      metrics:
        datapoint:
          - 'metric.name == "system.memory.utilization" and attributes["state"] == "slab_unreclaimable"'
          - 'metric.name == "system.memory.utilization" and attributes["state"] == "inactive"'
          - 'metric.name == "system.memory.utilization" and attributes["state"] == "cached"'
          - 'metric.name == "system.memory.utilization" and attributes["state"] == "buffered"'
          - 'metric.name == "system.memory.utilization" and attributes["state"] == "slab_reclaimable"'
    filter/exclude_memory_usage:
      metrics:
        datapoint:
          - 'metric.name == "system.memory.usage" and attributes["state"] == "slab_unreclaimable"'
          - 'metric.name == "system.memory.usage" and attributes["state"] == "inactive"'
    filter/exclude_filesystem_utilization:
      metrics:
        datapoint:
          - 'metric.name == "system.filesystem.utilization" and attributes["type"] == "squashfs"'
    filter/exclude_filesystem_usage:
      metrics:
        datapoint:
          - 'metric.name == "system.filesystem.usage" and attributes["type"] == "squashfs"'
          - 'metric.name == "system.filesystem.usage" and attributes["state"] == "reserved"'
    filter/exclude_filesystem_inodes_usage:
      metrics:
        datapoint:
          - 'metric.name == "system.filesystem.inodes.usage" and attributes["type"] == "squashfs"'
          - 'metric.name == "system.filesystem.inodes.usage" and attributes["state"] == "reserved"'
    filter/exclude_system_disk:
      metrics:
        datapoint:
          - 'metric.name == "system.disk.operations" and IsMatch(attributes["device"], "^loop.*") == true'
          - 'metric.name == "system.disk.merged" and IsMatch(attributes["device"], "^loop.*") == true'
          - 'metric.name == "system.disk.io" and IsMatch(attributes["device"], "^loop.*") == true'
          - 'metric.name == "system.disk.io_time" and IsMatch(attributes["device"], "^loop.*") == true'
          - 'metric.name == "system.disk.operation_time" and IsMatch(attributes["device"], "^loop.*") == true'
    filter/exclude_system_paging:
      metrics:
        datapoint:
          - 'metric.name == "system.paging.usage" and attributes["state"] == "cached"'
          - 'metric.name == "system.paging.operations" and attributes["type"] == "cached"'
    filter/exclude_network:
      metrics:
        datapoint:
          - 'IsMatch(metric.name, "^system.network.*") == true and attributes["device"] == "lo"'
    attributes/exclude_system_paging:
      include:
        match_type: strict
        metric_names:
          - system.paging.operations
      actions:
        - key: type
          action: delete
    cumulativetodelta:
    transform/host:
      metric_statements:
        - context: metric
          statements:
            - set(description, "")
            - set(unit, "")
    transform:
      trace_statements:
        - context: span
          statements:
            - truncate_all(attributes, 4095)
            - truncate_all(resource.attributes, 4095)
      log_statements:
        - context: log
          statements:
            - truncate_all(attributes, 4095)
            - truncate_all(resource.attributes, 4095)
    memory_limiter:
      check_interval: 1s
      limit_mib: 100
    batch:
    resourcedetection:
      detectors: ["system"]
      system:
        hostname_sources: ["os"]
        resource_attributes:
          host.id:
            enabled: true
    resourcedetection/cloud:
      detectors: ["gcp", "ec2", "azure"]
      timeout: 2s
      ec2:
        resource_attributes:
          host.name:
            enabled: false
    resourcedetection/env:
      detectors: ["env"]
      timeout: 2s
      override: true

  exporters:
    otlphttp:
      endpoint: ${nr-env:OTEL_EXPORTER_OTLP_ENDPOINT}
      headers:
        api-key: ${nr-env:NEW_RELIC_LICENSE_KEY}

  service:
    pipelines:
      metrics/host:
        receivers: [hostmetrics]
        processors:
          - memory_limiter
          - metricstransform
          - filter/exclude_cpu_utilization
          - filter/exclude_memory_utilization
          - filter/exclude_memory_usage
          - filter/exclude_filesystem_utilization
          - filter/exclude_filesystem_usage
          - filter/exclude_filesystem_inodes_usage
          - filter/exclude_system_disk
          - filter/exclude_network
          - attributes/exclude_system_paging
          - transform/host
          - resourcedetection
          - resourcedetection/cloud
          - resourcedetection/env
          - cumulativetodelta
          - batch
        exporters: [otlphttp]
      logs/host:
        receivers: [filelog]
        processors: [memory_limiter, transform, resourcedetection, resourcedetection/cloud, resourcedetection/env, batch]
        exporters: [otlphttp]
      traces:
        receivers: [otlp]
        processors: [memory_limiter, transform, resourcedetection, resourcedetection/cloud, resourcedetection/env, batch]
        exporters: [otlphttp]
      metrics:
        receivers: [otlp]
        processors: [memory_limiter, transform, resourcedetection, resourcedetection/cloud, resourcedetection/env, batch]
        exporters: [otlphttp]
      logs:
        receivers: [otlp]
        processors: [memory_limiter, transform, resourcedetection, resourcedetection/cloud, resourcedetection/env, batch]
        exporters: [otlphttp]
    extensions: [health_check]

config_agent:
  license_key: '${nr-env:NEW_RELIC_LICENSE_KEY}'
  custom_attributes:
    env: production
config_logging:
  windows-event-log.yml:
    logs:
      - name: windows-event-log
        winevtlog:
          channel: System
        attributes:
          logtype: windows_event_log

config:
  integrations:
    - name: nri-mysql
      env:
        HOSTNAME: localhost
        PORT: 3306
        USERNAME: newrelic
        PASSWORD: ${nr-env:MYSQL_PASSWORD}
        REMOTE_MONITORING: true
      interval: 30s

config:
  integrations:
    - name: nri-flex
      config:
        name: winDiskPerf
        apis:
          - event_type: WinDiskPerfSample
            shell: powershell
            commands:
              - run: >
                  Get-CimInstance -ClassName Win32_PerfFormattedData_PerfDisk_LogicalDisk |
                  Select-Object -Property Name, PercentFreeSpace, FreeMegabytes |
                  ConvertTo-Json

config:
  # Variables set automatically by Agent Control:
  # - NEW_RELIC_LICENSE_KEY: New Relic ingest license key.
  # - OTEL_EXPORTER_OTLP_ENDPOINT: OTLP endpoint (see: https://docs.newrelic.com/docs/opentelemetry/best-practices/opentelemetry-otlp/).

  extensions:
    health_check:

  receivers:
    otlp:
      protocols:
        grpc:
        http:

    hostmetrics:
      collection_interval: 60s
      scrapers:
        cpu:
          metrics:
            system.cpu.time:
              enabled: false
            system.cpu.utilization:
              enabled: true
        load:
        memory:
          metrics:
            system.memory.utilization:
              enabled: true
        paging:
          metrics:
            system.paging.utilization:
              enabled: false
            system.paging.faults:
              enabled: false
        filesystem:
          metrics:
            system.filesystem.utilization:
              enabled: true
        disk:
          metrics:
            system.disk.merged:
              enabled: false
            system.disk.pending_operations:
              enabled: false
            system.disk.weighted_io_time:
              enabled: false
        network:
          metrics:
            system.network.connections:
              enabled: false

  processors:
    metricstransform:
      transforms:
        - include: system.cpu.utilization
          action: update
          operations:
            - action: aggregate_labels
              label_set: [state]
              aggregation_type: mean
        - include: system.paging.operations
          action: update
          operations:
            - action: aggregate_labels
              label_set: [direction]
              aggregation_type: sum
    filter/exclude_cpu_utilization:
      metrics:
        datapoint:
          - 'metric.name == "system.cpu.utilization" and attributes["state"] == "interrupt"'
          - 'metric.name == "system.cpu.utilization" and attributes["state"] == "nice"'
          - 'metric.name == "system.cpu.utilization" and attributes["state"] == "softirq"'
    filter/exclude_memory_utilization:
      metrics:
        datapoint:
          - 'metric.name == "system.memory.utilization" and attributes["state"] == "slab_unreclaimable"'
          - 'metric.name == "system.memory.utilization" and attributes["state"] == "inactive"'
          - 'metric.name == "system.memory.utilization" and attributes["state"] == "cached"'
          - 'metric.name == "system.memory.utilization" and attributes["state"] == "buffered"'
          - 'metric.name == "system.memory.utilization" and attributes["state"] == "slab_reclaimable"'
    filter/exclude_memory_usage:
      metrics:
        datapoint:
          - 'metric.name == "system.memory.usage" and attributes["state"] == "slab_unreclaimable"'
          - 'metric.name == "system.memory.usage" and attributes["state"] == "inactive"'
    filter/exclude_filesystem_utilization:
      metrics:
        datapoint:
          - 'metric.name == "system.filesystem.utilization" and attributes["type"] == "squashfs"'
    filter/exclude_filesystem_usage:
      metrics:
        datapoint:
          - 'metric.name == "system.filesystem.usage" and attributes["type"] == "squashfs"'
          - 'metric.name == "system.filesystem.usage" and attributes["state"] == "reserved"'
    filter/exclude_filesystem_inodes_usage:
      metrics:
        datapoint:
          - 'metric.name == "system.filesystem.inodes.usage" and attributes["type"] == "squashfs"'
          - 'metric.name == "system.filesystem.inodes.usage" and attributes["state"] == "reserved"'
    filter/exclude_system_disk:
      metrics:
        datapoint:
          - 'metric.name == "system.disk.operations" and IsMatch(attributes["device"], "^loop.*") == true'
          - 'metric.name == "system.disk.merged" and IsMatch(attributes["device"], "^loop.*") == true'
          - 'metric.name == "system.disk.io" and IsMatch(attributes["device"], "^loop.*") == true'
          - 'metric.name == "system.disk.io_time" and IsMatch(attributes["device"], "^loop.*") == true'
          - 'metric.name == "system.disk.operation_time" and IsMatch(attributes["device"], "^loop.*") == true'
    filter/exclude_system_paging:
      metrics:
        datapoint:
          - 'metric.name == "system.paging.usage" and attributes["state"] == "cached"'
          - 'metric.name == "system.paging.operations" and attributes["type"] == "cached"'
    filter/exclude_network:
      metrics:
        datapoint:
          - 'IsMatch(metric.name, "^system.network.*") == true and attributes["device"] == "lo"'
    attributes/exclude_system_paging:
      include:
        match_type: strict
        metric_names:
          - system.paging.operations
      actions:
        - key: type
          action: delete
    cumulativetodelta:
    transform/host:
      metric_statements:
        - context: metric
          statements:
            - set(description, "")
            - set(unit, "")
    transform:
      trace_statements:
        - context: span
          statements:
            - truncate_all(attributes, 4095)
            - truncate_all(resource.attributes, 4095)
      log_statements:
        - context: log
          statements:
            - truncate_all(attributes, 4095)
            - truncate_all(resource.attributes, 4095)
    memory_limiter:
      check_interval: 1s
      limit_mib: 100
    batch:
    resourcedetection:
      detectors: ["system"]
      system:
        hostname_sources: ["os"]
        resource_attributes:
          host.id:
            enabled: true
    resourcedetection/cloud:
      detectors: ["gcp", "ec2", "azure"]
      timeout: 2s
      ec2:
        resource_attributes:
          host.name:
            enabled: false
    resourcedetection/env:
      detectors: ["env"]
      timeout: 2s
      override: true

  exporters:
    otlphttp:
      endpoint: ${nr-env:OTEL_EXPORTER_OTLP_ENDPOINT}
      headers:
        api-key: ${nr-env:NEW_RELIC_LICENSE_KEY}

  service:
    pipelines:
      metrics/host:
        receivers: [hostmetrics]
        processors:
          - memory_limiter
          - metricstransform
          - filter/exclude_cpu_utilization
          - filter/exclude_memory_utilization
          - filter/exclude_memory_usage
          - filter/exclude_filesystem_utilization
          - filter/exclude_filesystem_usage
          - filter/exclude_filesystem_inodes_usage
          - filter/exclude_system_disk
          - filter/exclude_network
          - attributes/exclude_system_paging
          - transform/host
          - resourcedetection
          - resourcedetection/cloud
          - resourcedetection/env
          - cumulativetodelta
          - batch
        exporters: [otlphttp]
      traces:
        receivers: [otlp]
        processors: [memory_limiter, transform, resourcedetection, resourcedetection/cloud, resourcedetection/env, batch]
        exporters: [otlphttp]
      metrics:
        receivers: [otlp]
        processors: [memory_limiter, transform, resourcedetection, resourcedetection/cloud, resourcedetection/env, batch]
        exporters: [otlphttp]
      logs:
        receivers: [otlp]
        processors: [memory_limiter, transform, resourcedetection, resourcedetection/cloud, resourcedetection/env, batch]
        exporters: [otlphttp]
    extensions: [health_check]