Differences

This shows you the differences between two versions of the page.

--- сервис_victoriametrics [2025/03/25 13:07]
val
+++ сервис_victoriametrics [2025/03/29 09:32] (current)
val [Уведомления]
@@ Line 1: / Line 1: @@
 ====== Сервис VictoriaMetrics ======
-==== Метрики ====
+===== Метрики =====
   * [[https://docs.victoriametrics.com/sd_configs/|vmagent and single-node VictoriaMetrics supports the following Prometheus-compatible service discovery]]
+  * [[https://docs.victoriametrics.com/guides/k8s-monitoring-via-vm-cluster/|Kubernetes monitoring with VictoriaMetrics Cluster]]
   * [[https://docs.victoriametrics.com/guides/k8s-monitoring-via-vm-single/|Kubernetes monitoring via VictoriaMetrics Single]]
+  * [[https://docs.victoriametrics.com/scrape_config_examples/]]
+  * [[Система Kubernetes#kube-state-metrics]]
 <code>
 (venv1) server# ansible all -f 4 -m apt -a 'pkg=prometheus-node-exporter state=present update_cache=true' -i /root/kubespray/inventory/mycluster/hosts.yaml
@@ Line 17: / Line 21: @@
 </code><code>
 ...
+        - job_name: kube-state-metrics
+          kubernetes_sd_configs:
+          - role: pod
+          relabel_configs:
+          - source_labels: [__meta_kubernetes_pod_container_name]
+            regex: kube-state-metrics
+            action: keep
+          - source_labels: [__meta_kubernetes_pod_container_port_number]
+            regex: "8080"
+            action: keep
         - job_name: node-exporter
           static_configs:
@@ Line 26: / Line 41: @@
 kube1:~/vm# helm upgrade -i vmsingle vm/victoria-metrics-single -f guide-vmsingle-values.yaml -n vm --create-namespace
-kube1:~/vm# kubectl scale --replicas 1 statefulset vmsingle-victoria-metrics-single-server
+kube1:~/vm# kubectl scale --replicas 1 statefulset vmsingle-victoria-metrics-single-server -n vm
-cmder> kubectl -n vm port-forward svc/vmsingle-victoria-metrics-single-server 8428
+cmder> kubectl port-forward svc/vmsingle-victoria-metrics-single-server 8428 -n vm
+</code>
-kube1# helm repo add grafana https://grafana.github.io/helm-charts
+  * Сервис Grafana в [[Сервис Grafana#Kubernetes]]
-kube1# helm repo update
-kube1:~/vm# cat my-grafana-values.yaml
+===== Уведомления =====
-</code><code>
-  datasources:
-    datasources.yaml:
-      apiVersion: 1
-      datasources:
-        - name: victoriametrics
-          type: prometheus
-          orgId: 1
-          url: http://vmsingle-victoria-metrics-single-server:8428
-          access: proxy
-          isDefault: true
-          updateIntervalSeconds: 10
-          editable: true
-  dashboardProviders:
-   dashboardproviders.yaml:
-     apiVersion: 1
-     providers:
-     - name: 'default'
-       orgId: 1
-       folder: ''
-       type: file
-       disableDeletion: true
-       editable: true
-       options:
-         path: /var/lib/grafana/dashboards/default
-  dashboards:
-    default:
-      victoriametrics:
-        gnetId: 10229
-        revision: 22
-        datasource: victoriametrics
-      kubernetes:
-        gnetId: 14205
-        revision: 1
-        datasource: victoriametrics
-      node-exporter:
-        gnetId: 1860
-        revision: 37
-        datasource: victoriametrics
-</code><code>
-kube1:~/vm# helm upgrade -i my-grafana grafana/grafana -f my-grafana-values.yaml -n vm --create-namespace
-kube1# kubectl get secret --namespace vm my-grafana -o jsonpath="{.data.admin-password}" | base64 --decode ; echo
-cmder> kubectl -n vm port-forward svc/vmsingle-victoria-metrics-single-server 3000:80
-</code>
-  * [[https://docs.victoriametrics.com/guides/k8s-monitoring-via-vm-cluster/|Kubernetes monitoring with VictoriaMetrics Cluster]]
-==== Уведомления ====
-  * [[Сервис Prometheus#prometheus-alertmanager]]
+  * [[Сервис Prometheus#prometheus-alertmanager]] (ссылки на правила)
 <code>
@@ Line 92: / Line 56: @@
 kube1:~/vm# helm show values vm/victoria-metrics-alert > vm-alert-values.yaml
+$ wget -qO - https://raw.githubusercontent.com/samber/awesome-prometheus-alerts/master/dist/rules/host-and-hardware/node-exporter.yml | sed 's/^/    /'
+$ wget -qO - https://raw.githubusercontent.com/samber/awesome-prometheus-alerts/master/dist/rules/kubernetes/kubestate-exporter.yml | sed 's/^/    /'
 kube1:~/vm# cat vm-alert-values.yaml
@@ Line 111: / Line 79: @@
 #      groups: []
       groups:
-      - name: node_exporter_alerts
+      - name: NodeExporter
 ...
-      - name: vm_k8s_alerts
+      - name: KubestateExporter
         rules:
-        - alert: CriticalCPU
+        - alert: KubernetesContainerOomKiller
-          expr: sum by (kubernetes_io_hostname) (rate (container_cpu_usage_seconds_total[1m])) / sum (machine_cpu_cores) * 100 > 40
+          expr: (kube_pod_container_status_restarts_total - kube_pod_container_status_restarts_total offset 10m >= 1) and ignoring (reason) min_over_time(kube_pod_container_status_last_terminated_reason{reason="OOMKilled"}[10m]) == 1
-          for: 1m
+          for: 0m
           labels:
-            severity: "critical"
+            severity: warning
           annotations:
-            summary: "CriticalCPU {{ $labels.instance }}"
+            summary: Kubernetes Container oom killer (instance {{ $labels.instance }})
+            description: "Container {{ $labels.container }} in pod {{ $labels.namespace }}/{{ $labels.pod }} has been OOMKill"
-        - alert: CriticalFS
-          expr: container_fs_usage_bytes{device=~"^/dev/[sv]d[a-z][1-9]$"} / container_fs_limit_bytes * 100 > 80
-          for: 1m
-          labels:
-            severity: "critical"
-          annotations:
-            summary: "CriticalFS {{ $labels.instance }}"
-        - alert: CriticalMEM
-          expr: sum by (kubernetes_io_hostname) (container_memory_working_set_bytes) / sum (machine_memory_bytes) * 100 > 80
-          for: 1m
-          labels:
-            severity: "critical"
-          annotations:
-            summary: "CriticalMEM {{ $labels.instance }}"
 ...
 alertmanager:
@@ Line 183: / Line 135: @@
   * [[Команда dd]] для нехватки места на диске
-==== Журналы ====
+===== Журналы =====
   * [[https://docs.victoriametrics.com/helm/victorialogs-single/]]
@@ Line 204: / Line 156: @@
 VMUI-> Log Query: kubernetes.pod_name: my-debian
-</code><code>
+</code>
+==== Подключение Grafana ====
+<code>
 Grafana -> Connections ->
 Add new connection: VictoriaLogs ->
@@ Line 214: / Line 170: @@
 Builder-> Filter: kubernetes.pod_name = my-debian
+</code>
+====== Черновик ======
+<code>
+        - alert: CriticalCPU
+          expr: sum by (kubernetes_io_hostname) (rate (container_cpu_usage_seconds_total[1m])) / sum (machine_cpu_cores) * 100 > 40
+          for: 1m
+          labels:
+            severity: "critical"
+          annotations:
+            summary: "CriticalCPU {{ $labels.instance }}"
+        - alert: CriticalFS
+          expr: container_fs_usage_bytes{device=~"^/dev/[sv]d[a-z][1-9]$"} / container_fs_limit_bytes * 100 > 80
+          for: 1m
+          labels:
+            severity: "critical"
+          annotations:
+            summary: "CriticalFS {{ $labels.instance }}"
+        - alert: CriticalMEM
+          expr: sum by (kubernetes_io_hostname) (container_memory_working_set_bytes) / sum (machine_memory_bytes) * 100 > 80
+          for: 1m
+          labels:
+            severity: "critical"
+          annotations:
+            summary: "CriticalMEM {{ $labels.instance }}"
 </code>

Методические материалы Лохтурова Вячеслава

User Tools

Site Tools

Differences

Page Tools