devops-infra-helm-charts-gcp/helm-templates/mimir-distributed/capped-large.yaml

# These values configure the Grafana Mimir or Grafana Enterprise Metrics cluster
# for a more production-ready setup. The setup targets 70% CPU and memory utilization
# so that the cluster has room to grow. The resource requests and limits reflect 100% utilization.
# This is useful when you want to strictly control costs when purchasing GEM through a marketplace subscription for example.
# limits==requests also ensure a "Guaranteed" QoS: https://kubernetes.io/docs/tasks/configure-pod-container/quality-service-pod/.
# Note that setting CPU limits has some known issues:
# https://engineering.indeedblog.com/blog/2019/12/unthrottled-fixing-cpu-limits-in-the-cloud/.
#
# These values are suitable for ingestion of ~10M series and scrape interval of 15s.
# This implies ingestion rate of around 660000 samples per second.
#
# Query requirements can vary dramatically depending on query rate and query
# ranges. The values here satisfy a "usual" query load of around 50 queries per second
# as seen from our production clusters at this scale.
#
# The values in this file also add podAntiAffinity rules for ingesters and store-gateways.
# The rules ensure that the replicas of the same component are not scheduled on the same
# Kubernetes Node. Zone-aware replication is enabled by default on new installation.
# Refer to [Migrate from single zone to zone-aware replication with Helm](https://grafana.com/docs/mimir/latest/migration-guide/migrating-from-single-zone-with-helm) and
# [Zone-Aware Replication](https://grafana.com/docs/mimir/latest/configure/configure-zone-aware-replication/)
# for more information.
#
# MinIO is no longer enabled, and you are encouraged to use your cloud providers
# object storage service such as S3 or GCS.

alertmanager:
  persistentVolume:
    enabled: true
  replicas: 3
  resources:
    limits:
      cpu: 1.4
      memory: 1.4Gi
    requests:
      cpu: 1.4
      memory: 1.4Gi
  statefulSet:
    enabled: true

compactor:
  persistentVolume:
    size: 50Gi
  resources:
    limits:
      cpu: 1.4
      memory: 2.8Gi
    requests:
      cpu: 1.4
      memory: 2.8Gi

distributor:
  replicas: 12
  resources:
    limits:
      cpu: 2.8
      memory: 5.7Gi
    requests:
      cpu: 2.8
      memory: 5.7Gi

ingester:
  persistentVolume:
    size: 50Gi
  replicas: 27
  resources:
    limits:
      cpu: 5
      memory: 12Gi
    requests:
      cpu: 5
      memory: 12Gi
  topologySpreadConstraints: {}
  affinity:
    podAntiAffinity:
      requiredDuringSchedulingIgnoredDuringExecution:
        - labelSelector:
            matchExpressions:
              - key: target # support for enterprise.legacyLabels
                operator: In
                values:
                  - ingester
          topologyKey: 'kubernetes.io/hostname'

        - labelSelector:
            matchExpressions:
              - key: app.kubernetes.io/component
                operator: In
                values:
                  - ingester
          topologyKey: 'kubernetes.io/hostname'
  zoneAwareReplication:
    topologyKey: 'kubernetes.io/hostname'

admin-cache:
  enabled: true
  replicas: 2

chunks-cache:
  enabled: true
  replicas: 32

index-cache:
  enabled: true
  replicas: 10

metadata-cache:
  enabled: true

results-cache:
  enabled: true
  replicas: 4

minio:
  enabled: false

overrides_exporter:
  replicas: 1
  resources:
    limits:
      cpu: 100m
      memory: 128Mi
    requests:
      cpu: 100m
      memory: 128Mi

querier:
  replicas: 4
  resources:
    limits:
      cpu: 2.8
      memory: 8.5Gi
    requests:
      cpu: 2.8
      memory: 8.5Gi

query_frontend:
  replicas: 3
  resources:
    limits:
      cpu: 2.8
      memory: 2.8Gi
    requests:
      cpu: 2.8
      memory: 2.8Gi

ruler:
  replicas: 3
  resources:
    limits:
      cpu: 1.4
      memory: 5.7Gi
    requests:
      cpu: 1.4
      memory: 5.7Gi

store_gateway:
  persistentVolume:
    size: 50Gi
  replicas: 6
  resources:
    limits:
      cpu: 1.4
      memory: 8.5Gi
    requests:
      cpu: 1.4
      memory: 8.5Gi
  topologySpreadConstraints: {}
  affinity:
    podAntiAffinity:
      requiredDuringSchedulingIgnoredDuringExecution:
        - labelSelector:
            matchExpressions:
              - key: target # support for enterprise.legacyLabels
                operator: In
                values:
                  - store-gateway
          topologyKey: 'kubernetes.io/hostname'

        - labelSelector:
            matchExpressions:
              - key: app.kubernetes.io/component
                operator: In
                values:
                  - store-gateway
          topologyKey: 'kubernetes.io/hostname'
  zoneAwareReplication:
    topologyKey: 'kubernetes.io/hostname'

nginx:
  replicas: 3
  resources:
    limits:
      cpu: 1.4
      memory: 731Mi
    requests:
      cpu: 1.4
      memory: 731Mi

# Grafana Enterprise Metrics feature related
admin_api:
  replicas: 2
  resources:
    limits:
      cpu: 200m
      memory: 128Mi
    requests:
      cpu: 200m
      memory: 128Mi

gateway:
  replicas: 3
  resources:
    limits:
      cpu: 1.4
      memory: 731Mi
    requests:
      cpu: 1.4
      memory: 731Mi