about summary refs log tree commit diff
path: root/tools/monitoring/values.yaml
blob: d1dbe956428e1082290d08b2af1fc250d27ef65a (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
global:
  namespace: monitoring

grafana:
  ingress:
    enabled: true
    annotations:
      cert-manager.io/cluster-issuer: letsencrypt-prod
      traefik.ingress.kubernetes.io/router.entrypoints: websecure
      traefik.ingress.kubernetes.io/router.tls: "true"
      traefik.ingress.kubernetes.io/router.tls.certresolver: "default"
      traefik.ingress.kubernetes.io/redirect-entry-point: https
    hosts:
      - grafana.topkek.cloud
    path: /
    tls:
      - hosts:
          - grafana.topkek.cloud
        secretName: grafana-tls

  datasources:
    datasources.yaml:
      apiVersion: 1
      datasources:
        - name: Prometheus
          type: prometheus
          access: proxy
          url: http://prometheus-server
          isDefault: true
        - name: Elasticsearch
          type: elasticsearch
          access: proxy
          url: http://elasticsearch-master
          jsonData:
            esVersion: 7
            timeField: "@timestamp"
            
prometheus:
  alertmanager:
    enabled: true
  pushgateway:
    enabled: true
  server:
    enabled: true
    extraScrapeConfigs:
      - job_name: 'kubernetes-pods'
        kubernetes_sd_configs:
          - role: pod
        relabel_configs:
          - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
            action: keep
            regex: true
          - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
            action: replace
            target_label: __metrics_path__
            regex: (.+)
          - source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
            action: replace
            target_label: __address__
            regex: ([^:]+)(?::\d+)?;(\d+)
            replacement: $1:$2
          - action: labelmap
            regex: __meta_kubernetes_pod_label_(.+)
          - source_labels: [__meta_kubernetes_namespace]
            action: replace
            target_label: kubernetes_namespace
          - source_labels: [__meta_kubernetes_pod_name]
            action: replace
            target_label: kubernetes_pod_name

      - job_name: 'kubernetes-nodes'
        kubernetes_sd_configs:
          - role: node
        relabel_configs:
          - action: labelmap
            regex: __meta_kubernetes_node_label_(.+)

      - job_name: 'kubernetes-apiservers'
        kubernetes_sd_configs:
          - role: endpoints
            namespaces:
              names:
                - default
        relabel_configs:
          - source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
            action: keep
            regex: default;kubernetes;https

      - job_name: 'kubernetes-cadvisor'
        kubernetes_sd_configs:
          - role: node
        scheme: https
        tls_config:
          ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
          insecure_skip_verify: true
        bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
        relabel_configs:
          - action: labelmap
            regex: __meta_kubernetes_node_label_(.+)
          - target_label: __address__
            replacement: kubernetes.default.svc:443
          - source_labels: [__meta_kubernetes_node_name]
            regex: (.+)
            target_label: node
          - source_labels: [__meta_kubernetes_node_name]
            regex: (.+)
            target_label: instance
          - target_label: __metrics_path__
            replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor

      - job_name: 'kubernetes-service-endpoints'
        kubernetes_sd_configs:
          - role: endpoints
        relabel_configs:
          - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]
            action: keep
            regex: true
          - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]
            action: replace
            target_label: __scheme__
            regex: (https?)
          - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]
            action: replace
            target_label: __metrics_path__
            regex: (.+)
          - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]
            action: replace
            target_label: __address__
            regex: ([^:]+)(?::\d+)?;(\d+)
            replacement: $1:$2
          - action: labelmap
            regex: __meta_kubernetes_service_label_(.+)
          - source_labels: [__meta_kubernetes_namespace]
            action: replace
            target_label: kubernetes_namespace
          - source_labels: [__meta_kubernetes_service_name]
            action: replace
            target_label: kubernetes_name

elasticsearch:
  volumeClaimTemplate:
    accessModes: [ "ReadWriteOnce" ]
    resources:
      requests:
        storage: 30Gi

  master:
    resources:
      requests:
        cpu: "500m"
        memory: "2Gi"
      limits:
        cpu: "1"
        memory: "4Gi"

  data:
    resources:
      requests:
        cpu: "500m"
        memory: "2Gi"
      limits:
        cpu: "1"
        memory: "4Gi"

  ingest:
    resources:
      requests:
        cpu: "500m"
        memory: "2Gi"
      limits:
        cpu: "1"
        memory: "4Gi"

opentelemetry-collector:
  mode: deployment
  image:
    repository: otel/opentelemetry-collector
    tag: "latest"
  config:
    receivers:
      otlp:
        protocols:
          grpc: {}
          http: {}
    processors:
      batch: {}
      resource:
        attributes:
          - key: k8s.pod.name
            from_attribute: k8s.pod.uid
          - key: k8s.namespace.name
            from_attribute: k8s.namespace.uid
    exporters:
      prometheusremotewrite:
        endpoint: "http://prometheus-server.monitoring.svc.cluster.local/api/v1/write"
      logging:
        loglevel: debug
    service:
      pipelines:
        metrics:
          receivers: [otlp]
          processors: [batch]
          exporters: [prometheusremotewrite]

logstash:
  enabled: true
  image: "docker.elastic.co/logstash/logstash:7.17.3"
  resources:
    requests:
      cpu: "500m"
      memory: "2Gi"
    limits:
      cpu: "1"
      memory: "4Gi"
  config:
    logstash.yml: |
      http.host: "0.0.0.0"
      xpack.monitoring.enabled: true
      xpack.monitoring.elasticsearch.hosts: [ "http://elasticsearch-master:9200" ]
    logstash.conf: |
      input {
        beats {
          port => 5044
        }
      }
      output {
        elasticsearch {
          hosts => ["http://elasticsearch-master:9200"]
          index => "%{[@metadata][beat]}-%{+YYYY.MM.dd}"
        }
      }