diff --git a/manifests/grafana-dashboardDefinitions.yaml b/manifests/grafana-dashboardDefinitions.yaml
index 5a9f181ddd6d180198fa6d598ddc2efe9a17c8e9..e6d5d9c0bf84f6aa51c451aa6c36ec6cf61c0f54 100644
--- a/manifests/grafana-dashboardDefinitions.yaml
+++ b/manifests/grafana-dashboardDefinitions.yaml
@@ -3551,7 +3551,7 @@ items:
],
"query": "label_values(kube_pod_info, cluster)",
- "refresh": 1,
+ "refresh": 2,
"regex": "",
"sort": 0,
"tagValuesQuery": "",
@@ -4919,7 +4919,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "sum(namespace:kube_pod_container_resource_requests_cpu_cores:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{resource=\"cpu\",cluster=\"$cluster\"})",
+ "expr": "sum(namespace_cpu:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{resource=\"cpu\",cluster=\"$cluster\"})",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
@@ -5087,7 +5087,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "1 - sum(:node_memory_MemAvailable_bytes:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{resource=\"memory\",cluster=\"$cluster\"\"})",
+ "expr": "1 - sum(:node_memory_MemAvailable_bytes:sum{cluster=\"$cluster\"}) / sum(node_memory_MemTotal_bytes{resource=\"memory\",cluster=\"$cluster\"})",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
@@ -5171,7 +5171,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "sum(namespace:kube_pod_container_resource_requests_memory_bytes:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{resource=\"memory\",cluster=\"$cluster\"})",
+ "expr": "sum(namespace_memory:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{resource=\"memory\",cluster=\"$cluster\"})",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
@@ -5650,7 +5650,7 @@ items:
"step": 10
},
{
- "expr": "sum(namespace:kube_pod_container_resource_requests_cpu_cores:sum{cluster=\"$cluster\"}) by (namespace)",
+ "expr": "sum(namespace_cpu:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -7357,7 +7357,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_requests{namespace=\"$namespace\", resource=\"cpu\"})",
+ "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
@@ -7441,7 +7441,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_limits{namespace=\"$namespace\", resource=\"cpu\"})",
+ "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
@@ -7525,7 +7525,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_requests{namespace=\"$namespace\", resource=\"memory\"})",
+ "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"})",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
@@ -7609,7 +7609,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_limits{namespace=\"$namespace\", resource=\"memory\"})",
+ "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"})",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
@@ -7985,7 +7985,7 @@ items:
"step": 10
},
{
- "expr": "sum(kube_pod_container_resource_requests{namespace=\"$namespace\", resource=\"cpu\"}) by (pod)",
+ "expr": "sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -7994,7 +7994,7 @@ items:
"step": 10
},
{
- "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(kube_pod_container_resource_requests{namespace=\"$namespace\", resource=\"cpu\"}) by (pod)",
+ "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -8003,7 +8003,7 @@ items:
"step": 10
},
{
- "expr": "sum(kube_pod_container_resource_limits{namespace=\"$namespace\", resource=\"cpu\"}) by (pod)",
+ "expr": "sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -8012,7 +8012,7 @@ items:
"step": 10
},
{
- "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(kube_pod_container_resource_limits{namespace=\"$namespace\", resource=\"cpu\"}) by (pod)",
+ "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -8450,7 +8450,7 @@ items:
"step": 10
},
{
- "expr": "sum(kube_pod_container_resource_requests{namespace=\"$namespace\", resource=\"memory\"}) by (pod)",
+ "expr": "sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -8459,7 +8459,7 @@ items:
"step": 10
},
{
- "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(kube_pod_container_resource_requests{namespace=\"$namespace\", resource=\"memory\"}) by (pod)",
+ "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -8468,7 +8468,7 @@ items:
"step": 10
},
{
- "expr": "sum(kube_pod_container_resource_limits{namespace=\"$namespace\", resource=\"memory\"}) by (pod)",
+ "expr": "sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -8477,7 +8477,7 @@ items:
"step": 10
},
{
- "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(kube_pod_container_resource_limits{namespace=\"$namespace\", resource=\"memory\"}) by (pod)",
+ "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -9456,7 +9456,7 @@ items:
],
"query": "label_values(kube_pod_info, cluster)",
- "refresh": 1,
+ "refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
@@ -9483,7 +9483,7 @@ items:
],
"query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
- "refresh": 1,
+ "refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
@@ -10423,7 +10423,7 @@ items:
],
"query": "label_values(kube_pod_info, cluster)",
- "refresh": 1,
+ "refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
@@ -10450,7 +10450,7 @@ items:
],
"query": "label_values(kube_pod_info{cluster=\"$cluster\"}, node)",
- "refresh": 1,
+ "refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
@@ -12121,7 +12121,7 @@ items:
],
"query": "label_values(kube_pod_info, cluster)",
- "refresh": 1,
+ "refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
@@ -12148,7 +12148,7 @@ items:
],
"query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
- "refresh": 1,
+ "refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
@@ -14069,7 +14069,7 @@ items:
],
"query": "label_values(kube_pod_info, cluster)",
- "refresh": 1,
+ "refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
@@ -14096,7 +14096,7 @@ items:
],
"query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
- "refresh": 1,
+ "refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
@@ -14123,7 +14123,7 @@ items:
],
"query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\"}, workload)",
- "refresh": 1,
+ "refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
@@ -14150,7 +14150,7 @@ items:
],
"query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\"}, workload_type)",
- "refresh": 1,
+ "refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
@@ -16231,7 +16231,7 @@ items:
],
"query": "label_values(kube_pod_info, cluster)",
- "refresh": 1,
+ "refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
@@ -16262,7 +16262,7 @@ items:
],
"query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\"}, workload_type)",
- "refresh": 1,
+ "refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 0,
@@ -16290,7 +16290,7 @@ items:
],
"query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
- "refresh": 1,
+ "refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
@@ -20153,7 +20153,7 @@ items:
],
"query": "label_values(kube_pod_info, cluster)",
- "refresh": 1,
+ "refresh": 2,
"regex": "",
"sort": 0,
"tagValuesQuery": "",
@@ -20184,7 +20184,7 @@ items:
],
"query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)",
- "refresh": 1,
+ "refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
@@ -21846,7 +21846,7 @@ items:
],
"query": "label_values(kube_pod_info, cluster)",
- "refresh": 1,
+ "refresh": 2,
"regex": "",
"sort": 0,
"tagValuesQuery": "",
@@ -21877,7 +21877,7 @@ items:
],
"query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)",
- "refresh": 1,
+ "refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
@@ -21909,7 +21909,7 @@ items:
],
"query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\"}, workload_type)",
- "refresh": 1,
+ "refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 0,
@@ -26548,7 +26548,7 @@ items:
],
"query": "label_values(kube_pod_info, cluster)",
- "refresh": 1,
+ "refresh": 2,
"regex": "",
"sort": 0,
"tagValuesQuery": "",
@@ -26579,7 +26579,7 @@ items:
],
"query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)",
- "refresh": 1,
+ "refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
@@ -26611,7 +26611,7 @@ items:
],
"query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}, pod)",
- "refresh": 1,
+ "refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
@@ -34070,7 +34070,7 @@ items:
],
"query": "label_values(kube_pod_info, cluster)",
- "refresh": 1,
+ "refresh": 2,
"regex": "",
"sort": 0,
"tagValuesQuery": "",
@@ -34101,7 +34101,7 @@ items:
],
"query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)",
- "refresh": 1,
+ "refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
@@ -34133,7 +34133,7 @@ items:
],
"query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\"}, workload)",
- "refresh": 1,
+ "refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
@@ -34165,7 +34165,7 @@ items:
],
"query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\"}, workload_type)",
- "refresh": 1,
+ "refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 0,
diff --git a/manifests/kubernetes-prometheusRule.yaml b/manifests/kubernetes-prometheusRule.yaml
index 6445fa0d6c90346d260f6b624495ea4bd4f372a2..e83cd08459df05bd88e272a182b08a36fb34ec19 100644
--- a/manifests/kubernetes-prometheusRule.yaml
+++ b/manifests/kubernetes-prometheusRule.yaml
@@ -226,7 +226,7 @@ spec:
<
kube_hpa_spec_max_replicas{job="kube-state-metrics"})
and
- changes(kube_hpa_status_current_replicas[15m]) == 0
+ changes(kube_hpa_status_current_replicas{job="kube-state-metrics"}[15m]) == 0
for: 15m
labels:
severity: warning
@@ -264,7 +264,7 @@ spec:
runbook_url: https://github.com/prometheus-operator/kube-prometheus/wiki/kubememoryovercommit
summary: Cluster has overcommitted memory resource requests.
expr: |
- sum(namespace_memory:kube_pod_container_resource_requests_bytes:sum{})
+ sum(namespace_memory:kube_pod_container_resource_requests:sum{})
/
sum(kube_node_status_allocatable{resource="memory"})
>
@@ -498,7 +498,7 @@ spec:
runbook_url: https://github.com/prometheus-operator/kube-prometheus/wiki/aggregatedapierrors
summary: An aggregated API has reported errors.
expr: |
- sum by(name, namespace)(increase(aggregator_unavailable_apiservice_count[10m])) > 4
+ sum by(name, namespace)(increase(aggregator_unavailable_apiservice_total[10m])) > 4
labels:
severity: warning
- alert: AggregatedAPIDown