# Specify the namespaces to monitor here
namespacesToMonitor:
- loki
# The name of the cluster where this will be installed
clusterLabelValue: "meta-monitoring"

# Set to true to write logs, metrics or traces to Grafana Cloud
# The secrets have to be created first
cloud:
  logs:
    enabled: true
    secret: "logs"
  metrics:
    enabled: true
    secret: "metrics"
  traces:
    enabled: true
    secret: "traces"

# Set to true for a local version of logs, metrics or traces
local:
  grafana:
    enabled: false
  logs:
    enabled: false
  metrics:
    enabled: false
  traces:
    enabled: false
  minio:
    enabled: false  # This should be set to true if any of the previous is enabled

grafana:
  # Gateway ingress configuration
  ingress:
    # -- Specifies whether an ingress for the gateway should be created
    enabled: true
    # -- Ingress Class Name. MAY be required for Kubernetes versions >= 1.18
    ingressClassName: ""
    # -- Annotations for the gateway ingress
    annotations: { }
    # -- Labels for the gateway ingress
    labels: { }
    # -- Hosts configuration for the gateway ingress, passed through the `tpl` function to allow templating
    hosts:
      - host: monitoring.example.com
        paths:
          - path: /
            # -- pathType (e.g. ImplementationSpecific, Prefix, .. etc.) might also be required by some Ingress Controllers
            # pathType: Prefix
    # -- TLS configuration for the gateway ingress. Hosts passed through the `tpl` function to allow templating
    #tls:
    #  - secretName: grafana-tls
    #    hosts:
    #      - monitoring.example.com


logs:
  # Adding regexes here will add a stage.replace block for logs. For more information see
  # https://grafana.com/docs/agent/latest/flow/reference/components/loki.process/#stagereplace-block
  piiRegexes:
  # This example replaces the word after password with *****
  # - expression: "password (\\\\S+)"
  #   source: ""         # Empty uses the log message
  #   replace: "*****""

  # The lines matching these will be kept in Loki
  retain:
  # This shows the queries
  - caller=metrics.go
  # This shows any errors
  - level=error
  # Log lines for delete requests
  - delete request for user added
  - Started processing delete request
  - delete request for user marked as processed
  # This shows the ingest requests and is very noisy. Uncomment to include.
  # - caller=push.go
  # Additional log lines to retain
  extraLogs: []

metrics:
  # The list of metrics to retain for logging dashboards
  retain:
  - agent_config_last_load_success_timestamp_seconds
  - agent_config_last_load_successful
  - agent_config_load_failures_total
  - container_cpu_usage_seconds_total
  - container_fs_writes_bytes_total
  - container_memory_working_set_bytes
  - container_network_receive_bytes_total
  - container_network_transmit_bytes_total
  - container_spec_cpu_period
  - container_spec_cpu_quota
  - container_spec_memory_limit_bytes
  - cortex_ingester_flush_queue_length
  - cortex_prometheus_rule_group_iterations_total
  - cortex_prometheus_rule_evaluation_failures_total
  - cortex_prometheus_rule_group_rules
  - cortex_prometheus_rule_group_last_duration_seconds
  - cortex_prometheus_rule_group_last_evaluation_timestamp_seconds
  - cortex_prometheus_rule_group_iterations_missed_total
  - go_gc_duration_seconds
  - go_goroutines
  - go_memstats_heap_inuse_bytes
  - kubelet_volume_stats_used_bytes
  - kubelet_volume_stats_capacity_bytes
  - kube_deployment_created
  - kube_persistentvolumeclaim_labels
  - kube_pod_container_info
  - kube_pod_container_resource_requests
  - kube_pod_container_status_last_terminated_reason
  - kube_pod_container_status_restarts_total
  - loki_boltdb_shipper_compact_tables_operation_duration_seconds
  - loki_boltdb_shipper_compact_tables_operation_last_successful_run_timestamp_seconds
  - loki_boltdb_shipper_retention_marker_count_total
  - loki_boltdb_shipper_retention_marker_table_processed_duration_seconds_bucket
  - loki_boltdb_shipper_retention_marker_table_processed_duration_seconds_count
  - loki_boltdb_shipper_retention_marker_table_processed_duration_seconds_sum
  - loki_boltdb_shipper_retention_marker_table_processed_total
  - loki_boltdb_shipper_request_duration_seconds_bucket
  - loki_boltdb_shipper_request_duration_seconds_count
  - loki_boltdb_shipper_request_duration_seconds_sum
  - loki_boltdb_shipper_retention_sweeper_chunk_deleted_duration_seconds_bucket
  - loki_boltdb_shipper_retention_sweeper_chunk_deleted_duration_seconds_count
  - loki_boltdb_shipper_retention_sweeper_chunk_deleted_duration_seconds_sum
  - loki_boltdb_shipper_retention_sweeper_marker_files_current
  - loki_boltdb_shipper_retention_sweeper_marker_file_processing_current_time
  - loki_build_info
  - loki_chunk_store_deduped_chunks_total
  - loki_chunk_store_index_entries_per_chunk_bucket
  - loki_chunk_store_index_entries_per_chunk_count
  - loki_chunk_store_index_entries_per_chunk_sum
  - loki_compactor_delete_requests_processed_total
  - loki_compactor_delete_requests_received_total
  - loki_compactor_deleted_lines
  - loki_compactor_oldest_pending_delete_request_age_seconds
  - loki_compactor_pending_delete_requests_count
  - loki_discarded_samples_total
  - loki_distributor_bytes_received_total
  - loki_distributor_lines_received_total
  - loki_distributor_structured_metadata_bytes_received_total
  - loki_index_request_duration_seconds_count
  - loki_ingester_chunk_age_seconds_bucket
  - loki_ingester_chunk_age_seconds_count
  - loki_ingester_chunk_age_seconds_sum
  - loki_ingester_chunk_bounds_hours_bucket
  - loki_ingester_chunk_bounds_hours_count
  - loki_ingester_chunk_bounds_hours_sum
  - loki_ingester_chunk_entries_bucket
  - loki_ingester_chunk_entries_count
  - loki_ingester_chunk_entries_sum
  - loki_ingester_chunk_size_bytes_bucket
  - loki_ingester_chunk_utilization_bucket
  - loki_ingester_chunk_utilization_sum
  - loki_ingester_chunks_flushed_total
  - loki_ingester_flush_queue_length
  - loki_ingester_memory_chunks
  - loki_ingester_memory_streams
  - loki_ingester_streams_created_total
  - loki_request_duration_seconds_bucket
  - loki_request_duration_seconds_count
  - loki_request_duration_seconds_sum
  - loki_ruler_wal_appender_ready
  - loki_ruler_wal_disk_size
  - loki_ruler_wal_prometheus_remote_storage_highest_timestamp_in_seconds
  - loki_ruler_wal_prometheus_remote_storage_queue_highest_sent_timestamp_seconds
  - loki_ruler_wal_prometheus_remote_storage_samples_pending
  - loki_ruler_wal_prometheus_remote_storage_samples_total
  - loki_ruler_wal_samples_appended_total
  - loki_ruler_wal_storage_created_series_total
  - loki_write_batch_retries_total
  - loki_write_dropped_bytes_total
  - loki_write_dropped_entries_total
  - loki_write_sent_bytes_total
  - loki_write_sent_entries_total
  - node_disk_read_bytes_total
  - node_disk_written_bytes_total
  - promtail_custom_bad_words_total
  # Additional metrics to retain
  extraMetrics: []

# Set enabled = true to add the default logs/metrics/traces dashboards to the local Grafana
dashboards:
  logs:
    enabled: true
  metrics:
    enabled: true
  traces:
    enabled: true

global:
  minio:
    rootUser: "rootuser"
    rootPassword: "rootpassword"

kubeStateMetrics:
  # Scrape https://github.com/kubernetes/kube-state-metrics by default
  enabled: true
  # This endpoint is created when the helm chart from
  # https://artifacthub.io/packages/helm/prometheus-community/kube-state-metrics/
  # is used. Change this if kube-state-metrics is installed somewhere else.
  endpoint: kube-state-metrics.kube-state-metrics.svc.cluster.local:8080

# The following are configuration for the dependencies.
# These should usually not be changed.

loki:
  loki:
    auth_enabled: false
    schemaConfig:
      configs:
        - from: 2024-03-29
          store: tsdb
          object_store: s3
          schema: v13
          index:
            prefix: index_
            period: 24h
    storage:
      type: "s3"
      s3:
        insecure: true
        s3ForcePathStyle: true
      bucketNames:
        chunks: loki-chunks
        ruler: loki-ruler
    structuredConfig:
      common:
        storage:
          s3:
            access_key_id: "${rootUser}"
            endpoint: "{{ .Release.Name }}-minio.{{ .Release.Namespace }}.svc:9000"
            secret_access_key: "${rootPassword}"
      compactor:
        retention_enabled: true
        delete_request_store: s3
      limits_config:
        retention_period: 30d
  lokiCanary:
    enabled: false
  test:
    enabled: false
  monitoring:
    dashboards:
      enabled: false
    rules:
      enabled: false
    serviceMonitor:
      enabled: false
    selfMonitoring:
      enabled: false
      grafanaAgent:
        installOperator: false
    lokiCanary:
      enabled: false
  write:
    extraArgs:
    - "-config.expand-env=true"
    extraEnvFrom:
    - secretRef:
        name: "mmc-minio"
  read:
    extraArgs:
    - "-config.expand-env=true"
    extraEnvFrom:
    - secretRef:
        name: "mmc-minio"
  backend:
    extraArgs:
    - "-config.expand-env=true"
    extraEnvFrom:
    - secretRef:
        name: "mmc-minio"

alloy:
  alloy:
    clustering:
      enabled: true
    configMap:
      create: false
      name: "agent-configmap"
      key: 'config.river'
    resources:
      requests:
        cpu: '1000m'
        memory: '600Mi'
      limits:
        memory: '4Gi'
    extraPorts:
    - name: "otel"
      port: 4317
      targetPort: 4317
      protocol: "TCP"
    - name: "thrifthttp"
      port: 14268
      targetPort: 14268
      protocol: "TCP"
  controller:
    type: "statefulset"
    autoscaling:
      enabled: true
      minReplicas: 3
      maxReplicas: 30
      targetMemoryUtilizationPercentage: 90
      targetCPUUtilizationPercentage: 90

mimir-distributed:
  minio:
    enabled: false
  global:
    extraEnvFrom:
    - secretRef:
        name: "mmc-minio"
  mimir:
    structuredConfig:
      alertmanager_storage:
        s3:
          bucket_name: mimir-ruler
      blocks_storage:
        backend: s3
        s3:
          bucket_name: mimir-tsdb
      ruler_storage:
        s3:
          bucket_name: mimir-ruler
      common:
        storage:
          backend: s3
          s3:
            bucket_name: mimir-ruler
            access_key_id: "${rootUser}"
            endpoint: "{{ .Release.Name }}-minio.{{ .Release.Namespace }}.svc:9000"
            secret_access_key: "${rootPassword}"
            insecure: true
      limits:
        compactor_blocks_retention_period: 30d

tempo-distributed:
  tempo:
    structuredConfig:
      storage:
        trace:
          backend: s3
          s3:
            bucket: tempo
            endpoint: "{{ .Release.Name }}-minio.{{ .Release.Namespace }}.svc:9000"
            access_key: "${rootUser}"
            secret_key: "${rootPassword}"
            insecure: true
  distributor:
    extraArgs:
    - "-config.expand-env=true"
    extraEnvFrom:
    - secretRef:
        name: "mmc-minio"
  ingester:
    extraArgs:
    - "-config.expand-env=true"
    extraEnvFrom:
    - secretRef:
        name: "mmc-minio"
  compactor:
    extraArgs:
    - "-config.expand-env=true"
    extraEnvFrom:
    - secretRef:
        name: "mmc-minio"
  querier:
    extraArgs:
    - "-config.expand-env=true"
    extraEnvFrom:
    - secretRef:
        name: "mmc-minio"
  queryFrontend:
    extraArgs:
    - "-config.expand-env=true"
    extraEnvFrom:
    - secretRef:
        name: "mmc-minio"
  traces:
    otlp:
      http:
        enabled: true
      grpc:
        enabled: true

minio:
  existingSecret: "minio"
  buckets:
    - name: loki-chunks
      policy: none
      purge: false
    - name: loki-ruler
      policy: none
      purge: false
    - name: tempo
      policy: none
      purge: false
    - name: mimir-ruler
      policy: none
      purge: false
    - name: mimir-tsdb
      policy: none
      purge: false
  mode: standalone
  persistence:
    size: 5Gi
  resources:
    requests:
      cpu: 100m
      memory: 128Mi
  # Changed the mc config path to '/tmp' from '/etc' as '/etc' is only writable by root and OpenShift will not permit this.
  configPathmc: "/tmp/minio/mc/"