folderstructure

infra/values/argocd-values.yaml

@@ -0,0 +1,23 @@
+global:
+  domain: argocd.127.0.0.1.nip.io
+configs:
+  secret:
+    createSecret: true
+  cm:
+    application.resourceTrackingMethod: annotation
+    timeout.reconciliation: 60s
+    admin.enabled: "false"
+    # Add Git configuration for Azure authentication
+    repositories: |
+      - type: git
+        url: https://github.com/snothub
+        name: github-repo
+  params:
+    "server.insecure": true
+server:
+  ingress:
+    enabled: true
+    ingressClassName: nginx
+  extraArgs:
+  - --insecure
+  - --disable-auth

infra/values/fluent-bit-values.yaml

@@ -0,0 +1,68 @@
+# Fluent Bit Helm Chart Values
+# Static configuration for Loki output
+
+config:
+  service: |
+    [SERVICE]
+        Daemon Off
+        Flush 1
+        Log_Level info
+        Parsers_File parsers.conf
+        Parsers_File custom_parsers.conf
+        HTTP_Server On
+        HTTP_Listen 0.0.0.0
+        HTTP_Port 2020
+        Health_Check On
+
+  inputs: |
+    [INPUT]
+        Name tail
+        Path /var/log/containers/*.log
+        multiline.parser docker, cri
+        Tag kube.*
+        Mem_Buf_Limit 5MB
+        Skip_Long_Lines On
+
+    [INPUT]
+        Name systemd
+        Tag host.*
+        Systemd_Filter _SYSTEMD_UNIT=kubelet.service
+        Read_From_Tail On
+
+  filters: |
+    [FILTER]
+        Name kubernetes
+        Match kube.*
+        Kube_URL https://kubernetes.default.svc:443
+        Kube_CA_File /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+        Kube_Token_File /var/run/secrets/kubernetes.io/serviceaccount/token
+        Kube_Tag_Prefix kube.var.log.containers.
+        Merge_Log On
+        Keep_Log Off
+        K8S-Logging.Parser On
+        K8S-Logging.Exclude On
+
+  outputs: |
+    [OUTPUT]
+        Name loki
+        Match *
+        Host loki-gateway.loki.svc.cluster.local
+        Port 80
+        Labels job=fluent-bit
+        Auto_Kubernetes_Labels On
+
+tolerations:
+- key: node-role.kubernetes.io/control-plane
+  operator: Exists
+  effect: NoSchedule
+- key: node-role.kubernetes.io/master
+  operator: Exists
+  effect: NoSchedule
+
+resources:
+  requests:
+    cpu: 50m
+    memory: 128Mi
+  limits:
+    cpu: 100m
+    memory: 256Mi

infra/values/grafana-values.yaml

@@ -0,0 +1,45 @@
+ingress:
+  enabled: true
+
+resources:
+  requests:
+    cpu: 100m
+    memory: 128Mi
+  limits:
+    cpu: 200m
+    memory: 256Mi
+
+adminUser: admin
+adminPassword: "forte"
+
+datasources:
+  datasources.yaml:
+    apiVersion: 1
+    datasources:
+    - name: Prometheus
+      type: prometheus
+      url: http://prometheus-server.monitoring.svc.cluster.local
+      access: proxy
+      isDefault: true
+    - name: Loki
+      type: loki
+      url: http://loki-gateway.monitoring.svc.cluster.local
+      access: proxy
+dashboardProviders:
+  dashboardproviders.yaml:
+    apiVersion: 1
+    providers:
+    - name: 'default'
+      orgId: 1
+      folder: ''
+      type: file
+      disableDeletion: false
+      editable: true
+      options:
+        path: /var/lib/grafana/dashboards/default
+dashboards:
+  default:
+    kubernetes:
+      gnetId: 15758
+      revision: 1
+      datasource: Prometheus

infra/values/loki-values.yaml

@@ -0,0 +1,38 @@
+deploymentMode: SingleBinary
+loki:
+  auth_enabled: false
+  commonConfig:
+    replication_factor: 1
+  storage:
+    type: 'filesystem'
+  schemaConfig:
+    configs:
+    - from: "2024-01-01"
+      store: tsdb
+      index:
+        prefix: loki_index_
+        period: 24h
+      object_store: filesystem # we're storing on filesystem so there's no real persistence here.
+      schema: v13
+  limits_config:
+    reject_old_samples: true
+    reject_old_samples_max_age: 168h
+    ingestion_rate_mb: 10
+    ingestion_burst_size_mb: 20
+chunksCache:
+  enabled: false
+singleBinary:
+  replicas: 1
+  resources:
+    requests:
+      cpu: 100m
+      memory: 256Mi
+    limits:
+      cpu: 200m
+      memory: 512Mi
+read:
+  replicas: 0
+backend:
+  replicas: 0
+write:
+  replicas: 0

infra/values/prometheus-values.yaml

@@ -0,0 +1,49 @@
+server:
+  ingress:
+    enabled: false
+  service:
+    servicePort: 80
+
+  resources:
+    requests:
+      cpu: 250m
+      memory: 512Mi
+    limits:
+      cpu: 500m
+      memory: 1Gi
+
+  # Add your custom scrape configurations here
+  extraScrapeConfigs: |
+    - job_name: kubernetes-nodes-cadvisor
+      scrape_interval: 10s
+      scrape_timeout: 10s
+      scheme: https  # remove if you want to scrape metrics on insecure port
+      tls_config:
+        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+      kubernetes_sd_configs:
+        - role: node
+      relabel_configs:
+        - action: labelmap
+          regex: __meta_kubernetes_node_label_(.+)
+        # Only for Kubernetes ^1.7.3.
+        # See: https://github.com/prometheus/prometheus/issues/2916
+        - target_label: __address__
+          replacement: kubernetes.default.svc:443
+        - source_labels: [__meta_kubernetes_node_name]
+          regex: (.+)
+          target_label: __metrics_path__
+          replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor
+      metric_relabel_configs:
+        - action: replace
+          source_labels: [id]
+          regex: '^/machine\.slice/machine-rkt\\x2d([^\\]+)\\.+/([^/]+)\.service$'
+          target_label: rkt_container_name
+          replacement: '${2}-${1}'
+        - action: replace
+          source_labels: [id]
+          regex: '^/system\.slice/(.+)\.service$'
+          target_label: systemd_service_name
+          replacement: '${1}'
+alertmanager:
+  enabled: false