software/components/observability/subnet_monitoring.yaml

apiVersion: v1
kind: ConfigMap
metadata:
  name: container-azm-ms-agentconfig
  namespace: kube-system
data:
  schema-version:
    #string.used by agent to parse config. supported versions are {v1}. Configs with other schema versions will be rejected by the agent.
    v1
  config-version:
    #string.used by customer to keep track of this config file's version in their source control/repository (max allowed 10 chars, other chars will be truncated)
    ver1
  log-data-collection-settings: |-
    # Log data collection settings
    # Any errors related to config map settings can be found in the KubeMonAgentEvents table in the Log Analytics workspace that the cluster is sending data to.

    [log_collection_settings]
       [log_collection_settings.stdout]
          # In the absense of this configmap, default value for enabled is true
          enabled = true
          # exclude_namespaces setting holds good only if enabled is set to true
          # kube-system,gatekeeper-system log collection are disabled by default in the absence of 'log_collection_settings.stdout' setting. If you want to enable kube-system,gatekeeper-system, remove them from the following setting.
          # If you want to continue to disable kube-system,gatekeeper-system log collection keep the namespaces in the following setting and add any other namespace you want to disable log collection to the array.
          # In the absense of this configmap, default value for exclude_namespaces = ["kube-system","gatekeeper-system"]
          exclude_namespaces = ["kube-system","gatekeeper-system"]
          # If you want to collect logs from only selective pods inside system namespaces add them to the following setting. Provide namepace:controllerName of the system pod. NOTE: this setting is only for pods in system namespaces
          # Valid values for system namespaces are: kube-system, azure-arc, gatekeeper-system, kube-public, kube-node-lease, calico-system. The system namespace used should not be present in exclude_namespaces
          # collect_system_pod_logs = ["kube-system:coredns"]

       [log_collection_settings.stderr]
          # Default value for enabled is true
          enabled = true
          # exclude_namespaces setting holds good only if enabled is set to true
          # kube-system,gatekeeper-system log collection are disabled by default in the absence of 'log_collection_settings.stderr' setting. If you want to enable kube-system,gatekeeper-system, remove them from the following setting.
          # If you want to continue to disable kube-system,gatekeeper-system log collection keep the namespaces in the following setting and add any other namespace you want to disable log collection to the array.
          # In the absense of this configmap, default value for exclude_namespaces = ["kube-system","gatekeeper-system"]
          exclude_namespaces = ["kube-system","gatekeeper-system"]
          # If you want to collect logs from only selective pods inside system namespaces add them to the following setting. Provide namepace:controllerName of the system pod. NOTE: this setting is only for pods in system namespaces
          # Valid values for system namespaces are: kube-system, azure-arc, gatekeeper-system, kube-public, kube-node-lease, calico-system. The system namespace used should not be present in exclude_namespaces
          # collect_system_pod_logs = ["kube-system:coredns"]

       [log_collection_settings.env_var]
          # In the absense of this configmap, default value for enabled is true
          enabled = true
       [log_collection_settings.enrich_container_logs]
          # In the absense of this configmap, default value for enrich_container_logs is false
          enabled = false
          # When this is enabled (enabled = true), every container log entry (both stdout & stderr) will be enriched with container Name & container Image
       [log_collection_settings.collect_all_kube_events]
          # In the absense of this configmap, default value for collect_all_kube_events is false
          # When the setting is set to false, only the kube events with !normal event type will be collected
          enabled = false
          # When this is enabled (enabled = true), all kube events including normal events will be collected
       [log_collection_settings.schema]
          # In the absence of this configmap, default value for containerlog_schema_version is "v1" if "v2" is not enabled while onboarding
          # Supported values for this setting are "v1","v2"
          # See documentation at https://aka.ms/ContainerLogv2 for benefits of v2 schema over v1 schema
          containerlog_schema_version = "v2"
       #[log_collection_settings.enable_multiline_logs]
          # fluent-bit based multiline log collection for .NET, Go, Java, and Python stacktraces. Update stacktrace_languages to specificy which languages to collect stacktraces for(valid inputs: "go", "java", "python", "dotnet").
          # NOTE: for better performance consider enabling only for languages that are needed. Dotnet is experimental and may not work in all cases.
          # If enabled will also stitch together container logs split by docker/cri due to size limits(16KB per log line) up to 64 KB.
          # Requires ContainerLogV2 schema to be enabled. See https://aka.ms/ContainerLogv2 for more details.
          # enabled = "false"
          # stacktrace_languages = []
       #[log_collection_settings.metadata_collection]
          # kube_meta_cache_ttl_secs is a configurable option for K8s cached metadata. Default is 60s. You may adjust it in below section [agent_settings.k8s_metadata_config]. Reference link: https://docs.fluentbit.io/manual/pipeline/filters/kubernetes#configuration-parameters
          # if enabled will collect kubernetes metadata for ContainerLogv2 schema. Default is false. 
          # enabled = false
          # if include_fields commented out or empty, all fields will be included. If include_fields is set, only the fields listed will be included.
          # include_fields = ["podLabels","podAnnotations","podUid","image","imageID","imageRepo","imageTag"]
       #[log_collection_settings.filter_using_annotations]
          # if enabled will exclude logs from pods with annotations fluenbit.io/exclude: "true".
          # Read more: https://docs.fluentbit.io/manual/pipeline/filters/kubernetes#kubernetes-annotations
          # enabled = false

  prometheus-data-collection-settings: |-
    # Custom Prometheus metrics data collection settings
    [prometheus_data_collection_settings.cluster]
        # Cluster level scrape endpoint(s). These metrics will be scraped from agent's Replicaset (singleton)
        # Any errors related to prometheus scraping can be found in the KubeMonAgentEvents table in the Log Analytics workspace that the cluster is sending data to.

        #Interval specifying how often to scrape for metrics. This is duration of time and can be specified for supporting settings by combining an integer value and time unit as a string value. Valid time units are ns, us (or µs), ms, s, m, h.
        interval = "1m"

        ## Uncomment the following settings with valid string arrays for prometheus scraping
        #fieldpass = ["metric_to_pass1", "metric_to_pass12"]

        #fielddrop = ["metric_to_drop"]

        # An array of urls to scrape metrics from.
        # urls = ["http://myurl:9101/metrics"]

        # An array of Kubernetes services to scrape metrics from.
        # kubernetes_services = ["http://my-service-dns.my-namespace:9102/metrics"]

        # When monitor_kubernetes_pods = true, prometheus sidecar container will scrape Kubernetes pods for the following prometheus annotations:
        # - prometheus.io/scrape: Enable scraping for this pod
        # - prometheus.io/scheme: Default is http
        # - prometheus.io/path: If the metrics path is not /metrics, define it with this annotation.
        # - prometheus.io/port: If port is not 9102 use this annotation
        monitor_kubernetes_pods = false

        ## Restricts Kubernetes monitoring to namespaces for pods that have annotations set and are scraped using the monitor_kubernetes_pods setting.
        ## This will take effect when monitor_kubernetes_pods is set to true
        ##   ex: monitor_kubernetes_pods_namespaces = ["default1", "default2", "default3"]
        # monitor_kubernetes_pods_namespaces = ["default1"]

        ## Label selector to target pods which have the specified label
        ## This will take effect when monitor_kubernetes_pods is set to true
        ## Reference the docs at https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/#label-selectors
        # kubernetes_label_selector = "env=dev,app=nginx"

        ## Field selector to target pods which have the specified field
        ## This will take effect when monitor_kubernetes_pods is set to true
        ## Reference the docs at https://kubernetes.io/docs/concepts/overview/working-with-objects/field-selectors/
        ## eg. To scrape pods on a specific node
        # kubernetes_field_selector = "spec.nodeName=$HOSTNAME"

    [prometheus_data_collection_settings.node]
        # Node level scrape endpoint(s). These metrics will be scraped from agent's DaemonSet running in every node in the cluster
        # Any errors related to prometheus scraping can be found in the KubeMonAgentEvents table in the Log Analytics workspace that the cluster is sending data to.

        #Interval specifying how often to scrape for metrics. This is duration of time and can be specified for supporting settings by combining an integer value and time unit as a string value. Valid time units are ns, us (or µs), ms, s, m, h.
        interval = "1m"

        ## Uncomment the following settings with valid string arrays for prometheus scraping

        # An array of urls to scrape metrics from. $NODE_IP (all upper case) will substitute of running Node's IP address
        # urls = ["http://$NODE_IP:9103/metrics"]

        #fieldpass = ["metric_to_pass1", "metric_to_pass12"]

        #fielddrop = ["metric_to_drop"]

  metric_collection_settings: |-
    # Metrics collection settings for metrics sent to Log Analytics and MDM
    [metric_collection_settings.collect_kube_system_pv_metrics]
      # In the absense of this configmap, default value for collect_kube_system_pv_metrics is false
      # When the setting is set to false, only the persistent volume metrics outside the kube-system namespace will be collected
      enabled = false
      # When this is enabled (enabled = true), persistent volume metrics including those in the kube-system namespace will be collected

  alertable-metrics-configuration-settings: |-
    # Alertable metrics configuration settings for container resource utilization
    [alertable_metrics_configuration_settings.container_resource_utilization_thresholds]
        # The threshold(Type Float) will be rounded off to 2 decimal points
        # Threshold for container cpu, metric will be sent only when cpu utilization exceeds or becomes equal to the following percentage
        container_cpu_threshold_percentage = 95.0
        # Threshold for container memoryRss, metric will be sent only when memory rss exceeds or becomes equal to the following percentage
        container_memory_rss_threshold_percentage = 95.0
        # Threshold for container memoryWorkingSet, metric will be sent only when memory working set exceeds or becomes equal to the following percentage
        container_memory_working_set_threshold_percentage = 95.0

    # Alertable metrics configuration settings for persistent volume utilization
    [alertable_metrics_configuration_settings.pv_utilization_thresholds]
        # Threshold for persistent volume usage bytes, metric will be sent only when persistent volume utilization exceeds or becomes equal to the following percentage
        pv_usage_threshold_percentage = 60.0

    # Alertable metrics configuration settings for completed jobs count
    [alertable_metrics_configuration_settings.job_completion_threshold]
        # Threshold for completed job count , metric will be sent only for those jobs which were completed earlier than the following threshold
        job_completion_threshold_time_minutes = 360
  integrations: |-
    [integrations.azure_network_policy_manager]
        collect_basic_metrics = false
        collect_advanced_metrics = false
    [integrations.azure_subnet_ip_usage]
        enabled = false

# Doc - https://github.com/microsoft/Docker-Provider/blob/ci_prod/Documentation/AgentSettings/ReadMe.md
  agent-settings: |-
    # prometheus scrape fluent bit settings for high scale
    # buffer size should be greater than or equal to chunk size else we set it to chunk size.
    # settings scoped to prometheus sidecar container. all values in mb
    [agent_settings.prometheus_fbit_settings]
      tcp_listener_chunk_size = 10
      tcp_listener_buffer_size = 10
      tcp_listener_mem_buf_limit = 200

    # prometheus scrape fluent bit settings for high scale
    # buffer size should be greater than or equal to chunk size else we set it to chunk size.
    # settings scoped to daemonset container. all values in mb
    # [agent_settings.node_prometheus_fbit_settings]
      # tcp_listener_chunk_size = 1
      # tcp_listener_buffer_size = 1
      # tcp_listener_mem_buf_limit = 10

    # prometheus scrape fluent bit settings for high scale
    # buffer size should be greater than or equal to chunk size else we set it to chunk size.
    # settings scoped to replicaset container. all values in mb
    # [agent_settings.cluster_prometheus_fbit_settings]
      # tcp_listener_chunk_size = 1
      # tcp_listener_buffer_size = 1
      # tcp_listener_mem_buf_limit = 10

    # The following settings are "undocumented", we don't recommend uncommenting them unless directed by Microsoft.
    # They increase the maximum stdout/stderr log collection rate but will also cause higher cpu/memory usage.
    ## Ref for more details about Ignore_Older -  https://docs.fluentbit.io/manual/v/1.7/pipeline/inputs/tail
    # [agent_settings.fbit_config]
    #   log_flush_interval_secs = "1"                 # default value is 15
    #   tail_mem_buf_limit_megabytes = "10"           # default value is 10
    #   tail_buf_chunksize_megabytes = "1"            # default value is 32kb (comment out this line for default)
    #   tail_buf_maxsize_megabytes = "1"              # default value is 32kb (comment out this line for default)
    #   tail_ignore_older = "5m"                      # default value same as fluent-bit default i.e.0m

    # On both AKS & Arc K8s enviornments, if Cluster has configured with Forward Proxy then Proxy settings automatically applied and used for the agent
    # Certain configurations, proxy config should be ignored for example Cluster with AMPLS + Proxy
    # in such scenarios, use the following config to ignore proxy settings
    # [agent_settings.proxy_config]
    #    ignore_proxy_settings = "true"  # if this is not applied, default value is false

    # Disables fluent-bit for perf and container inventory for Windows
    #[agent_settings.windows_fluent_bit]
    #    disabled = "true"

    # The following settings are "undocumented", we don't recommend uncommenting them unless directed by Microsoft.
    # Configuration settings for the waittime for the network listeners to be available
    # [agent_settings.network_listener_waittime]
    #   tcp_port_25226 = 45                           # Port 25226 is used for telegraf to fluent-bit data in ReplicaSet
    #   tcp_port_25228 = 60                           # Port 25228 is used for telegraf to fluentd data
    #   tcp_port_25229 = 45                           # Port 25229 is used for telegraf to fluent-bit data in DaemonSet

    # The following settings are "undocumented", we don't recommend uncommenting them unless directed by Microsoft.
    # [agent_settings.mdsd_config]
    #   monitoring_max_event_rate = "50000" # default 20K eps
    #   backpressure_memory_threshold_in_mb = "1500" # default 3500MB
    #   upload_max_size_in_mb = "20"  # default 2MB
    #   upload_frequency_seconds = "1" # default 60 upload_frequency_seconds
    #   compression_level = "0"  # supported levels 0 to 9 and 0 means no compression

    # The following settings are "undocumented", we don't recommend uncommenting them unless directed by Microsoft.
    # [agent_settings.telemetry_config]
    #   disable_telemetry = false  # if this is not applied, default value is false
    
    # The following setting is for KubernetesMetadata CacheTTL Settings.
    # [agent_settings.k8s_metadata_config]
    #   kube_meta_cache_ttl_secs = 60  # if this is not applied, default value is 60s