easylinux/kube-prometheus
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

run make

Browse Source
This commit is contained in:
omerlh
2020-01-06 13:49:57 +02:00
parent 92d4cbae08
commit 81e2d19398
2 changed files with 60 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
manifests/prometheus-rules.yaml
View File

@@ -90,31 +90,31 @@ spec:
- name: k8s.rules
rules:
- expr: |
sum(rate(container_cpu_usage_seconds_total{job="kubelet", image!="", container!="POD"}[5m])) by (namespace)
sum(rate(container_cpu_usage_seconds_total{job="kubelet", metrics_path="/metrics/cadvisor", image!="", container!="POD"}[5m])) by (namespace)
record: namespace:container_cpu_usage_seconds_total:sum_rate
- expr: |
sum by (namespace, pod, container) (
rate(container_cpu_usage_seconds_total{job="kubelet", image!="", container!="POD"}[5m])
rate(container_cpu_usage_seconds_total{job="kubelet", metrics_path="/metrics/cadvisor", image!="", container!="POD"}[5m])
) * on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)
record: node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate
- expr: |
container_memory_working_set_bytes{job="kubelet", image!=""}
container_memory_working_set_bytes{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
* on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)
record: node_namespace_pod_container:container_memory_working_set_bytes
- expr: |
container_memory_rss{job="kubelet", image!=""}
container_memory_rss{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
* on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)
record: node_namespace_pod_container:container_memory_rss
- expr: |
container_memory_cache{job="kubelet", image!=""}
container_memory_cache{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
* on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)
record: node_namespace_pod_container:container_memory_cache
- expr: |
container_memory_swap{job="kubelet", image!=""}
container_memory_swap{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
* on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)
record: node_namespace_pod_container:container_memory_swap
- expr: |
sum(container_memory_usage_bytes{job="kubelet", image!="", container!="POD"}) by (namespace)
sum(container_memory_usage_bytes{job="kubelet", metrics_path="/metrics/cadvisor", image!="", container!="POD"}) by (namespace)
record: namespace:container_memory_usage_bytes:sum
- expr: |
sum by (namespace) (
@@ -703,9 +703,9 @@ spec:
}} free.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumeusagecritical
expr: |
kubelet_volume_stats_available_bytes{job="kubelet"}
kubelet_volume_stats_available_bytes{job="kubelet", metrics_path="/metrics"}
/
kubelet_volume_stats_capacity_bytes{job="kubelet"}
kubelet_volume_stats_capacity_bytes{job="kubelet", metrics_path="/metrics"}
< 0.03
for: 1m
labels:
@@ -718,12 +718,12 @@ spec:
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumefullinfourdays
expr: |
(
kubelet_volume_stats_available_bytes{job="kubelet"}
kubelet_volume_stats_available_bytes{job="kubelet", metrics_path="/metrics"}
/
kubelet_volume_stats_capacity_bytes{job="kubelet"}
kubelet_volume_stats_capacity_bytes{job="kubelet", metrics_path="/metrics"}
) < 0.15
and
predict_linear(kubelet_volume_stats_available_bytes{job="kubelet"}[6h], 4 * 24 * 3600) < 0
predict_linear(kubelet_volume_stats_available_bytes{job="kubelet", metrics_path="/metrics"}[6h], 4 * 24 * 3600) < 0
for: 1h
labels:
severity: critical
@@ -1050,7 +1050,7 @@ spec:
}} of its Pod capacity.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubelettoomanypods
expr: |
max(max(kubelet_running_pod_count{job="kubelet"}) by(instance) * on(instance) group_left(node) kubelet_node_name{job="kubelet"}) by(node) / max(kube_node_status_capacity_pods{job="kube-state-metrics"}) by(node) > 0.95
max(max(kubelet_running_pod_count{job="kubelet", metrics_path="/metrics"}) by(instance) * on(instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"}) by(node) / max(kube_node_status_capacity_pods{job="kube-state-metrics"}) by(node) > 0.95
for: 15m
labels:
severity: warning
@@ -1059,7 +1059,7 @@ spec:
message: Kubelet has disappeared from Prometheus target discovery.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletdown
expr: |
absent(up{job="kubelet"} == 1)
absent(up{job="kubelet", metrics_path="/metrics"} == 1)
for: 15m
labels:
severity: critical