This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision | ||
сервис_victoriametrics [2025/03/28 12:50] val [Уведомления] |
сервис_victoriametrics [2025/03/29 09:32] (current) val [Уведомления] |
||
---|---|---|---|
Line 56: | Line 56: | ||
kube1:~/vm# helm show values vm/victoria-metrics-alert > vm-alert-values.yaml | 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 | kube1:~/vm# cat vm-alert-values.yaml | ||
Line 75: | Line 79: | ||
# groups: [] | # groups: [] | ||
groups: | groups: | ||
- | - name: node_exporter_alerts | + | - name: NodeExporter |
... | ... | ||
- | - name: vm_k8s_alerts | + | - name: KubestateExporter |
rules: | rules: | ||
- alert: KubernetesContainerOomKiller | - alert: KubernetesContainerOomKiller | ||
Line 166: | Line 170: | ||
Builder-> Filter: kubernetes.pod_name = my-debian | 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> | </code> |