apiVersion: source.toolkit.fluxcd.io/v1
kind: HelmRepository
metadata:
  name: grafana
  namespace: monitoring
spec:
  interval: 24h
  url: https://grafana.github.io/helm-charts
---
apiVersion: helm.toolkit.fluxcd.io/v2
kind: HelmRelease
metadata:
  name: loki
  namespace: monitoring
spec:
  interval: 30m
  chart:
    spec:
      chart: loki
      version: ">=6.0.0"
      sourceRef:
        kind: HelmRepository
        name: grafana
        namespace: monitoring
  install:
    remediation:
      retries: 3
  upgrade:
    remediation:
      retries: 3
  values:
    deploymentMode: SingleBinary
    loki:
      auth_enabled: false
      commonConfig:
        replication_factor: 1
      storage:
        type: filesystem
      limits_config:
        retention_period: 2160h
        ingestion_rate_mb: 10
        ingestion_burst_size_mb: 20
        max_streams_per_user: 10000
        max_query_length: 720h
        max_entries_limit_per_query: 5000
      schemaConfig:
        configs:
          - from: "2024-01-01"
            store: tsdb
            object_store: filesystem
            schema: v13
            index:
              prefix: loki_index_
              period: 24h
    singleBinary:
      replicas: 1
      persistence:
        enabled: true
        storageClass: ceph-block
        size: 80Gi
      # Chart ships no defaults. Without a memory limit the pod is OOM-
      # killed by the kernel when WAL replay / large queries spike RSS
      # (lost loki-0 once on 2026-05-14 to exit 137 during initial
      # install). Steady-state RSS is ~540Mi at current ingest (~37
      # lines/sec); 2Gi limit gives 4x headroom for replay/query bursts.
      # CPU is left unlimited so queries can burst.
      resources:
        requests:
          cpu: 100m
          memory: 512Mi
        limits:
          memory: 2Gi
    gateway:
      enabled: false
    chunksCache:
      enabled: false
    resultsCache:
      enabled: false
    # Disable components not needed in SingleBinary mode
    backend:
      replicas: 0
    read:
      replicas: 0
    write:
      replicas: 0
---
apiVersion: helm.toolkit.fluxcd.io/v2
kind: HelmRelease
metadata:
  name: alloy
  namespace: monitoring
spec:
  interval: 30m
  chart:
    spec:
      chart: alloy
      version: ">=0.12.0"
      sourceRef:
        kind: HelmRepository
        name: grafana
        namespace: monitoring
  install:
    remediation:
      retries: 3
  upgrade:
    remediation:
      retries: 3
  values:
    alloy:
      configMap:
        content: |
          // Discover and collect K8s pod logs
          discovery.kubernetes "pods" {
            role = "pod"
          }

          discovery.relabel "pods" {
            targets = discovery.kubernetes.pods.targets

            rule {
              source_labels = ["__meta_kubernetes_namespace"]
              target_label  = "namespace"
            }
            rule {
              source_labels = ["__meta_kubernetes_pod_name"]
              target_label  = "pod"
            }
            rule {
              source_labels = ["__meta_kubernetes_pod_container_name"]
              target_label  = "container"
            }
          }

          loki.source.kubernetes "pods" {
            targets    = discovery.relabel.pods.output
            forward_to = [loki.write.default.receiver]
          }

          loki.write "default" {
            endpoint {
              url = "http://loki.monitoring.svc.cluster.local:3100/loki/api/v1/push"
            }
          }