first commit

victoria-alerts/victoria-alerts-VMAlert.yml

@@ -0,0 +1,15 @@
+---
+apiVersion: operator.victoriametrics.com/v1beta1
+kind: VMAlert
+metadata:
+  name: victoria-alerts-vmalert
+spec:
+  replicaCount: 1
+  datasource:
+    url: "http://vmselect-victoria-alerts-main.devops-core-victoria-alerts.svc.cluster.local:8481/select/0/prometheus"
+  notifier:
+      url: "http://vmalertmanager-victoria-alerts-vmalertmanager.devops-core-victoria-alerts.svc.cluster.local:9093"
+  evaluationInterval: "30s"
+  ruleSelector:
+    matchLabels:
+      role: alert-rules

victoria-alerts/victoria-alerts-VMAlertmanager.yml

@@ -0,0 +1,46 @@
+---
+apiVersion: operator.victoriametrics.com/v1beta1
+kind: VMAlertmanager
+metadata:
+  name: victoria-alerts-vmalertmanager
+spec:
+  replicaCount: 2
+  image:
+      repository: docker-remote-docker-io.art.lmru.tech/prom/alertmanager
+      tag: v0.25.0
+      pullPolicy: IfNotPresent
+  affinity:
+    podAntiAffinity:
+      requiredDuringSchedulingIgnoredDuringExecution:
+        - labelSelector:
+            matchExpressions:
+              - key: "app.kubernetes.io/name"
+                operator: In
+                values:
+                  - "alertmananger"
+          topologyKey: "kubernetes.io/hostname"
+  tolerations:
+    - effect: NoExecute
+      key: dedicated
+      value: victoria-alerts
+  nodeSelector:
+    node-role/victoria-alerts: ""
+  resources:
+    requests:
+      memory: "64Mi"
+      cpu: "250m"
+    limits:
+      memory: "128Mi"
+      cpu: "500m"
+  configRawYaml: |
+      global:
+        resolve_timeout: 5m
+      route:
+        group_wait: 30s
+        group_interval: 5m
+        repeat_interval: 12h
+        receiver: 'webhook'
+      receivers:
+      - name: 'webhook'
+        webhook_configs:
+        - url: 'http://localhost:30502/'

victoria-alerts/victoria-alerts-VMRule.yml

@@ -0,0 +1,33 @@
+apiVersion: operator.victoriametrics.com/v1beta1
+kind: VMRule
+metadata:
+  name: victoria-alerts-vmrule-correct-rule
+spec:
+  groups:
+    - name: vmalert
+      rules:
+        - alert: vmalert config reload error
+          expr: delta(vmalert_config_last_reload_errors_total[5m]) > 0
+          for: 10s
+          labels:
+            severity: major
+            job:  "{{ $labels.job }}"
+          annotations:
+            value: "{{ $value }}"
+            description: 'error reloading vmalert config, reload count for 5 min {{ $value }}'
+---
+apiVersion: operator.victoriametrics.com/v1beta1
+kind: VMRule
+metadata:
+  name: victoria-alerts-vmrule-incorrect-rule
+spec:
+  groups:
+    - name: incorrect rule
+      rules:
+        - alert: vmalert bad config
+          expr: bad expression
+          for: 10s
+          labels:
+            severity: major
+          annotations:
+            value: "{{ $badValue | bad function }}"

victoria-alerts/victoria-alerts-ic.yml

@@ -0,0 +1,13 @@
+---
+apiVersion: deckhouse.io/v1
+kind: YandexInstanceClass
+metadata:
+  name: victoria-alerts
+spec:
+  cores: 8
+  memory: 16384
+  diskSizeGB: 50
+  diskType: network-ssd
+  imageID: fd8emvfmfoaordspe1jr
+  networkType: Standard
+  platformID: standard-v2

victoria-alerts/victoria-alerts-main.yml

@@ -0,0 +1,150 @@
+---
+apiVersion: operator.victoriametrics.com/v1beta1
+kind: VMCluster
+metadata:
+  name: victoria-alerts-main
+spec:
+  retentionPeriod: "3d"
+  replicationFactor: 2
+  vmstorage:
+    replicaCount: 3
+    logFormat: json
+    logLevel: "INFO"
+    image:
+      repository: docker-remote-docker-io.art.lmru.tech/victoriametrics/vmstorage
+      tag: v1.97.0-cluster
+      pullPolicy: IfNotPresent
+    storageDataPath: "/vm-data"
+    topologySpreadConstraints:
+    - maxSkew: 1
+      topologyKey: "topology.kubernetes.io/zone"
+      whenUnsatisfiable: DoNotSchedule
+    affinity:
+      podAntiAffinity:
+        requiredDuringSchedulingIgnoredDuringExecution:
+          - labelSelector:
+              matchExpressions:
+                - key: "app.kubernetes.io/name"
+                  operator: In
+                  values:
+                    - "vmstorage"
+            topologyKey: "kubernetes.io/hostname"
+    tolerations:
+      - effect: NoExecute
+        key: dedicated
+        value: victoria-alerts
+    nodeSelector:
+      node-role/victoria-alerts: ""
+    podDisruptionBudget:
+      minAvailable: 2
+    storage:
+      volumeClaimTemplate:
+        spec:
+          storageClassName: network-ssd
+          resources:
+            requests:
+              storage: 30Gi
+    resources:
+      limits:
+        memory: 4Gi
+      requests:
+        memory: 512Mi
+        cpu: 1
+  vmselect:
+    replicaCount: 3
+    serviceSpec:
+      metadata:
+        name: victoria-alerts-cluster-main-access
+        annotations:
+          yandex.cpi.flant.com/listener-subnet-id: e9b62pbnf0oaj4btj7rc
+          yandex.cpi.flant.com/listener-address-ipv4: 10.203.199.3
+      spec:
+        type: LoadBalancer
+    logFormat: json
+    logLevel: "INFO"
+    image:
+      repository: docker-remote-docker-io.art.lmru.tech/victoriametrics/vmselect
+      tag: v1.97.0-cluster
+      pullPolicy: IfNotPresent
+    cacheMountPath: "/select-cache"
+    topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: "topology.kubernetes.io/zone"
+        whenUnsatisfiable: DoNotSchedule
+    affinity:
+      podAntiAffinity:
+        requiredDuringSchedulingIgnoredDuringExecution:
+          - labelSelector:
+              matchExpressions:
+                - key: "app.kubernetes.io/name"
+                  operator: In
+                  values:
+                    - "vmselect"
+            topologyKey: "kubernetes.io/hostname"
+    tolerations:
+      - effect: NoExecute
+        key: dedicated
+        value: victoria-alerts
+    nodeSelector:
+      node-role/victoria-alerts: ""
+    podDisruptionBudget:
+      minAvailable: 2
+    storage:
+      volumeClaimTemplate:
+        spec:
+          storageClassName: network-ssd
+          resources:
+            requests:
+              storage: 2Gi
+    resources:
+      limits:
+        memory: "1024Mi"
+      requests:
+        memory: 256Mi
+        cpu: 200m
+
+  #https://docs.victoriametrics.com/operator/api/#vminsert
+  vminsert:
+    replicaCount: 3
+    serviceSpec:
+      metadata:
+        name: victoria-alerts-cluster-main-insert
+        annotations:
+          yandex.cpi.flant.com/listener-subnet-id: e2l6nn0el6dm1e5p73ki
+          yandex.cpi.flant.com/listener-address-ipv4: 10.203.19.200
+      spec:
+        type: LoadBalancer
+    image:
+      repository: docker-remote-docker-io.art.lmru.tech/victoriametrics/vminsert
+      tag: v1.97.0-cluster
+      pullPolicy: IfNotPresent
+    logFormat: json
+    logLevel: "INFO"
+    topologySpreadConstraints:
+    - maxSkew: 1
+      topologyKey: "topology.kubernetes.io/zone"
+      whenUnsatisfiable: DoNotSchedule
+    affinity:
+      podAntiAffinity:
+        requiredDuringSchedulingIgnoredDuringExecution:
+          - labelSelector:
+              matchExpressions:
+                - key: "app.kubernetes.io/name"
+                  operator: In
+                  values:
+                    - "vminsert"
+            topologyKey: "kubernetes.io/hostname"
+    tolerations:
+      - effect: NoExecute
+        key: dedicated
+        value: victoria-alerts
+    nodeSelector:
+      node-role/victoria-alerts: ""
+    podDisruptionBudget:
+      minAvailable: 2
+    resources:
+      limits:
+        memory: "1Gi"
+      requests:
+          memory: "256Mi"
+          cpu: 1

victoria-alerts/victoria-alerts-ng.yml

@@ -0,0 +1,28 @@
+---
+apiVersion: deckhouse.io/v1
+kind: NodeGroup
+metadata:
+  name: victoria-alerts
+spec:
+  nodeType: CloudEphemeral
+  cloudInstances:
+    minPerZone: 1
+    maxPerZone: 3
+    zones:
+      - ru-central1-a
+      - ru-central1-b
+      - ru-central1-d
+    classReference:
+      kind: YandexInstanceClass
+      name: victoria-alerts
+  nodeTemplate:
+    labels:
+      node-role/victoria-alerts: ""
+    taints:
+      - effect: NoExecute
+        key: dedicated
+        value: victoria-alerts
+  disruptions:
+    approvalMode: Automatic
+  chaos:
+    mode: Disabled