feat(container): update image kube-prometheus-stack to v70.10.0#368
Open
renovate[bot] wants to merge 1 commit into
Open
feat(container): update image kube-prometheus-stack to v70.10.0#368renovate[bot] wants to merge 1 commit into
renovate[bot] wants to merge 1 commit into
Conversation
--- kubernetes/apps/observability/kube-prometheus-stack/app Kustomization: flux-system/kube-prometheus-stack HelmRelease: observability/kube-prometheus-stack
+++ kubernetes/apps/observability/kube-prometheus-stack/app Kustomization: flux-system/kube-prometheus-stack HelmRelease: observability/kube-prometheus-stack
@@ -13,13 +13,13 @@
spec:
chart: kube-prometheus-stack
sourceRef:
kind: HelmRepository
name: prometheus-community
namespace: flux-system
- version: 70.0.2
+ version: 70.10.0
dependsOn:
- name: prometheus-operator-crds
namespace: observability
- name: openebs
namespace: storage
install: |
renovate
Bot
force-pushed
the
renovate/kube-prometheus-stack-70.x
branch
from
ebe804c to
6df0722
Compare
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/kube-prometheus-stack-70.x
branch
from
6df0722 to
5b5b715
Compare
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/kube-prometheus-stack-70.x
branch
from
5b5b715 to
fd16474
Compare
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/kube-prometheus-stack-70.x
branch
from
fd16474 to
02092cc
Compare
--- HelmRelease: observability/kube-prometheus-stack ConfigMap: observability/kube-prometheus-stack-k8s-resources-cluster
+++ HelmRelease: observability/kube-prometheus-stack ConfigMap: observability/kube-prometheus-stack-k8s-resources-cluster
@@ -28,23 +28,23 @@
--"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":4,"x":16,"y":0},"id":5,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(namespace_memory:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"})
/ sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"memory\",cluster=\"$cluster\"})","instant":true}],"title":"Memory
Requests Commitment","type":"stat"},{"datasource":{"type":"datasource","uid":"--
Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":4,"x":20,"y":0},"id":6,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(namespace_memory:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"})
/ sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"memory\",cluster=\"$cluster\"})","instant":true}],"title":"Memory
Limits Commitment","type":"stat"},{"datasource":{"type":"datasource","uid":"--
- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true}}},"gridPos":{"h":6,"w":24,"x":0,"y":6},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"})
+ Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true}}},"gridPos":{"h":6,"w":24,"x":0,"y":6},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\"})
by (namespace)","legendFormat":"__auto"}],"title":"CPU Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"--
Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Namespace"},"properties":[{"id":"links","value":[{"title":"Drill
down to pods","url":"/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?${datasource:queryparam}&var-cluster=$cluster&var-namespace=${__data.fields.Namespace}"}]}]}]},"gridPos":{"h":6,"w":24,"x":0,"y":12},"id":8,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_pod_owner{job=\"kube-state-metrics\",
cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"count(avg(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\"})
- by (workload, namespace)) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"})
+ by (workload, namespace)) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\"})
by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(namespace_cpu:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"})
- by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"})
+ by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\"})
by (namespace) / sum(namespace_cpu:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"})
by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(namespace_cpu:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"})
- by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"})
+ by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\"})
by (namespace) / sum(namespace_cpu:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"})
by (namespace)","format":"table","instant":true}],"title":"CPU Quota","transformations":[{"id":"joinByField","options":{"byField":"namespace","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time
1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true,"Time
7":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time
6":5,"Time 7":6,"Value #A":8,"Value #B":9,"Value #C":10,"Value #D":11,"Value #E":12,"Value
#F":13,"Value #G":14,"namespace":7},"renameByName":{"Value #A":"Pods","Value #B":"Workloads","Value
--- HelmRelease: observability/kube-prometheus-stack ConfigMap: observability/kube-prometheus-stack-k8s-resources-multicluster
+++ HelmRelease: observability/kube-prometheus-stack ConfigMap: observability/kube-prometheus-stack-k8s-resources-multicluster
@@ -28,21 +28,21 @@
--"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":4,"x":16,"y":0},"id":5,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\",
resource=\"memory\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",
resource=\"memory\"})","instant":true}],"title":"Memory Requests Commitment","type":"stat"},{"datasource":{"type":"datasource","uid":"--
Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":4,"x":20,"y":0},"id":6,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\",
resource=\"memory\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",
resource=\"memory\"})","instant":true}],"title":"Memory Limits Commitment","type":"stat"},{"datasource":{"type":"datasource","uid":"--
- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"}}},"gridPos":{"h":7,"w":24,"x":0,"y":1},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate)
+ Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"}}},"gridPos":{"h":7,"w":24,"x":0,"y":1},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m)
by (cluster)","legendFormat":"__auto"}],"title":"CPU Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"--
Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Cluster"},"properties":[{"id":"links","value":[{"title":"Drill
- down","url":"/d/efa86fd1d0c121a26444b636a3f509a8/kubernetes-compute-resources-cluster?${datasource:queryparam}&var-cluster=${__data.fields.Cluster}"}]}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":2},"id":8,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate)
+ down","url":"/d/efa86fd1d0c121a26444b636a3f509a8/kubernetes-compute-resources-cluster?${datasource:queryparam}&var-cluster=${__data.fields.Cluster}"}]}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":2},"id":8,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m)
by (cluster)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\",
- resource=\"cpu\"}) by (cluster)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate)
+ resource=\"cpu\"}) by (cluster)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m)
by (cluster) / sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\",
resource=\"cpu\"}) by (cluster)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\",
- resource=\"cpu\"}) by (cluster)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate)
+ resource=\"cpu\"}) by (cluster)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m)
by (cluster) / sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\",
resource=\"cpu\"}) by (cluster)","format":"table","instant":true}],"title":"CPU
Quota","transformations":[{"id":"joinByField","options":{"byField":"cluster","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time
1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true},"indexByName":{"Time
1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Value #A":6,"Value #B":7,"Value
#C":8,"Value #D":9,"Value #E":10,"cluster":5},"renameByName":{"Value #A":"CPU
--- HelmRelease: observability/kube-prometheus-stack ConfigMap: observability/kube-prometheus-stack-k8s-resources-namespace
+++ HelmRelease: observability/kube-prometheus-stack ConfigMap: observability/kube-prometheus-stack-k8s-resources-namespace
@@ -11,17 +11,17 @@
app.kubernetes.io/instance: kube-prometheus-stack
app.kubernetes.io/part-of: kube-prometheus-stack
release: kube-prometheus-stack
heritage: Helm
data:
k8s-resources-namespace.json: '{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"--
- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":6,"x":0,"y":0},"id":1,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\",
+ Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":6,"x":0,"y":0},"id":1,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\",
namespace=\"$namespace\"}) / sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\",
cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})","instant":true}],"title":"CPU
Utilisation (from requests)","type":"stat"},{"datasource":{"type":"datasource","uid":"--
- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":6,"x":6,"y":0},"id":2,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\",
+ Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":6,"x":6,"y":0},"id":2,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\",
namespace=\"$namespace\"}) / sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\",
cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})","instant":true}],"title":"CPU
Utilisation (from limits)","type":"stat"},{"datasource":{"type":"datasource","uid":"--
Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":6,"x":12,"y":0},"id":3,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\",
metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\",
image!=\"\"}) / sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\",
@@ -29,25 +29,25 @@
Utilisation (from requests)","type":"stat"},{"datasource":{"type":"datasource","uid":"--
Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":6,"x":18,"y":0},"id":4,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\",
metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\",
image!=\"\"}) / sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\",
cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"})","instant":true}],"title":"Memory
Utilisation (from limits)","type":"stat"},{"datasource":{"type":"datasource","uid":"--
- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true}},"overrides":[{"matcher":{"id":"byFrameRefID","options":"B"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"red","mode":"fixed"}}]},{"matcher":{"id":"byFrameRefID","options":"C"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"orange","mode":"fixed"}}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":7},"id":5,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\",
+ Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true}},"overrides":[{"matcher":{"id":"byFrameRefID","options":"B"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"red","mode":"fixed"}}]},{"matcher":{"id":"byFrameRefID","options":"C"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"orange","mode":"fixed"}}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":7},"id":5,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\",
namespace=\"$namespace\"}) by (pod)","legendFormat":"__auto"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"scalar(max(kube_resourcequota{cluster=\"$cluster\",
namespace=\"$namespace\", type=\"hard\",resource=\"requests.cpu\"}))","legendFormat":"quota
- requests"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"scalar(max(kube_resourcequota{cluster=\"$cluster\",
namespace=\"$namespace\", type=\"hard\",resource=\"limits.cpu\"}))","legendFormat":"quota
- limits"}],"title":"CPU Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"--
Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Pod"},"properties":[{"id":"links","value":[{"title":"Drill
- down to pods","url":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":14},"id":6,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\",
+ down to pods","url":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":14},"id":6,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\",
namespace=\"$namespace\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\",
- namespace=\"$namespace\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\",
+ namespace=\"$namespace\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\",
namespace=\"$namespace\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\",
namespace=\"$namespace\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\",
- namespace=\"$namespace\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\",
+ namespace=\"$namespace\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\",
namespace=\"$namespace\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\",
namespace=\"$namespace\"}) by (pod)","format":"table","instant":true}],"title":"CPU
Quota","transformations":[{"id":"joinByField","options":{"byField":"pod","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time
1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true},"indexByName":{"Time
1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Value #A":6,"Value #B":7,"Value
#C":8,"Value #D":9,"Value #E":10,"pod":5},"renameByName":{"Value #A":"CPU Usage","Value
--- HelmRelease: observability/kube-prometheus-stack ConfigMap: observability/kube-prometheus-stack-k8s-resources-node
+++ HelmRelease: observability/kube-prometheus-stack ConfigMap: observability/kube-prometheus-stack-k8s-resources-node
@@ -14,21 +14,21 @@
heritage: Helm
data:
k8s-resources-node.json: '{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"--
Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true,"stacking":{"mode":"normal"}}},"overrides":[{"matcher":{"id":"byName","options":"max
capacity"},"properties":[{"id":"color","value":{"fixedColor":"red","mode":"fixed"}},{"id":"custom.stacking","value":{"mode":"none"}},{"id":"custom.hideFrom","value":{"legend":false,"tooltip":true,"viz":false}},{"id":"custom.lineStyle","value":{"dash":[10,10],"fill":"dash"}}]}]},"gridPos":{"h":6,"w":24,"x":0,"y":0},"id":1,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_node_status_capacity{cluster=\"$cluster\",
job=\"kube-state-metrics\", node=~\"$node\", resource=\"cpu\"})","legendFormat":"max
- capacity"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\",
+ capacity"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\",
node=~\"$node\"}) by (pod)","legendFormat":"{{pod}}"}],"title":"CPU Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"--
Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Pod"},"properties":[{"id":"links","value":[{"title":"Drill
- down to pods","url":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":6,"w":24,"x":0,"y":6},"id":2,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\",
+ down to pods","url":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":6,"w":24,"x":0,"y":6},"id":2,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\",
node=~\"$node\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\",
- node=~\"$node\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\",
+ node=~\"$node\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\",
node=~\"$node\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\",
node=~\"$node\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\",
- node=~\"$node\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\",
+ node=~\"$node\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\",
node=~\"$node\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\",
node=~\"$node\"}) by (pod)","format":"table","instant":true}],"title":"CPU Quota","transformations":[{"id":"joinByField","options":{"byField":"pod","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time
1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true},"renameByName":{"Value
#A":"CPU Usage","Value #B":"CPU Requests","Value #C":"CPU Requests %","Value #D":"CPU
Limits","Value #E":"CPU Limits %","pod":"Pod"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"--
Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true,"stacking":{"mode":"normal"}},"unit":"bytes"},"overrides":[{"matcher":{"id":"byName","options":"max
--- HelmRelease: observability/kube-prometheus-stack ConfigMap: observability/kube-prometheus-stack-k8s-resources-pod
+++ HelmRelease: observability/kube-prometheus-stack ConfigMap: observability/kube-prometheus-stack-k8s-resources-pod
@@ -11,29 +11,29 @@
app.kubernetes.io/instance: kube-prometheus-stack
app.kubernetes.io/part-of: kube-prometheus-stack
release: kube-prometheus-stack
heritage: Helm
data:
k8s-resources-pod.json: '{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"--
- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true}},"overrides":[{"matcher":{"id":"byFrameRefID","options":"B"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"red","mode":"fixed"}}]},{"matcher":{"id":"byFrameRefID","options":"C"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"orange","mode":"fixed"}}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":0},"id":1,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{namespace=\"$namespace\",
+ Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true}},"overrides":[{"matcher":{"id":"byFrameRefID","options":"B"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"red","mode":"fixed"}}]},{"matcher":{"id":"byFrameRefID","options":"C"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"orange","mode":"fixed"}}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":0},"id":1,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{namespace=\"$namespace\",
pod=\"$pod\", cluster=\"$cluster\", container!=\"\"}) by (container)","legendFormat":"__auto"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\",
cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}\n)\n","legendFormat":"requests"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\",
cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}\n)\n","legendFormat":"limits"}],"title":"CPU
Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed
--"},"fieldConfig":{"defaults":{"custom":{"axisColorMode":"thresholds","axisSoftMax":1,"axisSoftMin":0,"fillOpacity":10,"showPoints":"never","spanNulls":true,"thresholdsStyle":{"mode":"dashed+area"}},"unit":"percentunit"},"overrides":[{"matcher":{"id":"byFrameRefID","options":"A"},"properties":[{"id":"thresholds","value":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":0.25}]}},{"id":"color","value":{"mode":"thresholds","seriesBy":"lastNotNull"}}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":7},"id":2,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(increase(container_cpu_cfs_throttled_periods_total{job=\"kubelet\",
metrics_path=\"/metrics/cadvisor\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\",
cluster=\"$cluster\"}[$__rate_interval])) by (container) /sum(increase(container_cpu_cfs_periods_total{job=\"kubelet\",
metrics_path=\"/metrics/cadvisor\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\",
cluster=\"$cluster\"}[$__rate_interval])) by (container)","legendFormat":"__auto"}],"title":"CPU
Throttling","type":"timeseries"},{"datasource":{"type":"datasource","uid":"--
- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":14},"id":3,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\",
+ Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":14},"id":3,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\",
namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\",
- namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\",
+ namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\",
namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\",
namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\",
- namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\",
+ namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\",
namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\",
namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container)","format":"table","instant":true}],"title":"CPU
Quota","transformations":[{"id":"joinByField","options":{"byField":"container","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time
1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true},"indexByName":{"Time
1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Value #A":6,"Value #B":7,"Value
#C":8,"Value #D":9,"Value #E":10,"container":5},"renameByName":{"Value #A":"CPU
--- HelmRelease: observability/kube-prometheus-stack ConfigMap: observability/kube-prometheus-stack-k8s-resources-workload
+++ HelmRelease: observability/kube-prometheus-stack ConfigMap: observability/kube-prometheus-stack-k8s-resources-workload
@@ -11,37 +11,37 @@
app.kubernetes.io/instance: kube-prometheus-stack
app.kubernetes.io/part-of: kube-prometheus-stack
release: kube-prometheus-stack
heritage: Helm
data:
k8s-resources-workload.json: '{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"--
- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true}}},"gridPos":{"h":7,"w":24,"x":0,"y":0},"id":1,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\",
+ Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true}}},"gridPos":{"h":7,"w":24,"x":0,"y":0},"id":1,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\",
namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type)
namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\",
workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","legendFormat":"__auto"}],"title":"CPU
Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed
--"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Pod"},"properties":[{"id":"links","value":[{"title":"Drill
- down to pods","url":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":7},"id":2,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\",
+ down to pods","url":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":7},"id":2,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\",
namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type)
namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\",
workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\",
cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload,
workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",
namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n)
- by (pod)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\",
+ by (pod)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\",
namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type)
namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\",
workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\",
cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload,
workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",
namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n)
by (pod)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\",
cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload,
workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",
namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n)
- by (pod)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\",
+ by (pod)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\",
namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type)
namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\",
workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\",
cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload,
workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",
namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n)
--- HelmRelease: observability/kube-prometheus-stack ConfigMap: observability/kube-prometheus-stack-k8s-resources-workloads-namespace
+++ HelmRelease: observability/kube-prometheus-stack ConfigMap: observability/kube-prometheus-stack-k8s-resources-workloads-namespace
@@ -11,40 +11,40 @@
app.kubernetes.io/instance: kube-prometheus-stack
app.kubernetes.io/part-of: kube-prometheus-stack
release: kube-prometheus-stack
heritage: Helm
data:
k8s-resources-workloads-namespace.json: '{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"--
- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true}},"overrides":[{"matcher":{"id":"byFrameRefID","options":"B"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"red","mode":"fixed"}}]},{"matcher":{"id":"byFrameRefID","options":"C"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"orange","mode":"fixed"}}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":0},"id":1,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\",
+ Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true}},"overrides":[{"matcher":{"id":"byFrameRefID","options":"B"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"red","mode":"fixed"}}]},{"matcher":{"id":"byFrameRefID","options":"C"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"orange","mode":"fixed"}}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":0},"id":1,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\",
namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type)
namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\",
workload_type=~\"$type\"}\n) by (workload, workload_type)\n","legendFormat":"{{workload}}
- {{workload_type}}"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"scalar(max(kube_resourcequota{cluster=\"$cluster\",
namespace=\"$namespace\", type=\"hard\",resource=~\"requests.cpu|cpu\"}))","legendFormat":"quota
- requests"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"scalar(max(kube_resourcequota{cluster=\"$cluster\",
namespace=\"$namespace\", type=\"hard\",resource=~\"limits.cpu\"}))","legendFormat":"quota
- limits"}],"title":"CPU Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"--
Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Workload"},"properties":[{"id":"links","value":[{"title":"Drill
down to workloads","url":"/d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-type=${__data.fields.Type}&var-workload=${__data.fields.Workload}"}]}]},{"matcher":{"id":"byName","options":"Running
Pods"},"properties":[{"id":"unit","value":"none"}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":7},"id":2,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",
- namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload, workload_type)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\",
+ namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload, workload_type)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\",
namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type)
namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\",
workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\",
cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload,
workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",
- namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\",
+ namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\",
namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type)
namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\",
workload_type=~\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\",
cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload,
workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",
namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\",
cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload,
workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",
- namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\",
+ namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"$cluster\",
namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type)
namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\",
workload_type=~\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\",
cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload,
workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",
namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true}],"title":"CPU
--- HelmRelease: observability/kube-prometheus-stack ConfigMap: observability/kube-prometheus-stack-namespace-by-pod
+++ HelmRelease: observability/kube-prometheus-stack ConfigMap: observability/kube-prometheus-stack-namespace-by-pod
@@ -11,18 +11,18 @@
app.kubernetes.io/instance: kube-prometheus-stack
app.kubernetes.io/part-of: kube-prometheus-stack
release: kube-prometheus-stack
heritage: Helm
data:
namespace-by-pod.json: '{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"--
- Mixed --"},"fieldConfig":{"defaults":{"displayName":"$namespace","max":10000000000,"min":0,"thresholds":{"steps":[{"color":"dark-green","index":0,"value":null},{"color":"dark-yellow","index":1,"value":5000000000},{"color":"dark-red","index":2,"value":7000000000}]},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":0,"y":0},"id":1,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum
+ Mixed --"},"fieldConfig":{"defaults":{"displayName":"$namespace","max":10000000000,"min":0,"thresholds":{"steps":[{"color":"dark-green","index":0,"value":null},{"color":"dark-yellow","index":1,"value":5000000000},{"color":"dark-red","index":2,"value":7000000000}]},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":0,"y":0},"id":1,"interval":"1m","pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum
(\n rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n *
on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod)
(\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Current
Rate of Bytes Received","type":"gauge"},{"datasource":{"type":"datasource","uid":"--
- Mixed --"},"fieldConfig":{"defaults":{"displayName":"$namespace","max":10000000000,"min":0,"thresholds":{"steps":[{"color":"dark-green","index":0,"value":null},{"color":"dark-yellow","index":1,"value":5000000000},{"color":"dark-red","index":2,"value":7000000000}]},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":12,"y":0},"id":2,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum
+ Mixed --"},"fieldConfig":{"defaults":{"displayName":"$namespace","max":10000000000,"min":0,"thresholds":{"steps":[{"color":"dark-green","index":0,"value":null},{"color":"dark-yellow","index":1,"value":5000000000},{"color":"dark-red","index":2,"value":7000000000}]},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":12,"y":0},"id":2,"interval":"1m","pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum
(\n rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n *
on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod)
(\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Current
Rate of Bytes Transmitted","type":"gauge"},{"datasource":{"type":"datasource","uid":"--
Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/Bandwidth/"},"properties":[{"id":"unit","value":"Bps"}]},{"matcher":{"id":"byRegexp","options":"/Packets/"},"properties":[{"id":"unit","value":"pps"}]},{"matcher":{"id":"byName","options":"Pod"},"properties":[{"id":"links","value":[{"title":"Drill
down","url":"/d/7a18067ce943a40ae25454675c19ff5c/kubernetes-networking-pod?${datasource:queryparam}&var-cluster=${cluster}&var-namespace=${namespace}&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":9,"w":24,"x":0,"y":9},"id":3,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum
--- HelmRelease: observability/kube-prometheus-stack ConfigMap: observability/kube-prometheus-stack-namespace-by-workload
+++ HelmRelease: observability/kube-prometheus-stack ConfigMap: observability/kube-prometheus-stack-namespace-by-workload
@@ -11,19 +11,19 @@
app.kubernetes.io/instance: kube-prometheus-stack
app.kubernetes.io/part-of: kube-prometheus-stack
release: kube-prometheus-stack
heritage: Helm
data:
namespace-by-workload.json: '{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"--
- Mixed --"},"fieldConfig":{"defaults":{"color":{"fixedColor":"green","mode":"fixed"},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":0,"y":0},"id":1,"options":{"displayMode":"basic","showUnfilled":false},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n*
+ Mixed --"},"fieldConfig":{"defaults":{"color":{"fixedColor":"green","mode":"fixed"},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":0,"y":0},"id":1,"interval":"1m","options":{"displayMode":"basic","showUnfilled":false},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n*
on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod)
(\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n*
on (cluster,namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\",
workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Current
Rate of Bytes Received","type":"bargauge"},{"datasource":{"type":"datasource","uid":"--
- Mixed --"},"fieldConfig":{"defaults":{"color":{"fixedColor":"green","mode":"fixed"},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":12,"y":0},"id":2,"options":{"displayMode":"basic","showUnfilled":false},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n*
+ Mixed --"},"fieldConfig":{"defaults":{"color":{"fixedColor":"green","mode":"fixed"},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":12,"y":0},"id":2,"interval":"1m","options":{"displayMode":"basic","showUnfilled":false},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n*
on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod)
(\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n*
on (cluster,namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\",
workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Current
Rate of Bytes Transmitted","type":"bargauge"},{"datasource":{"type":"datasource","uid":"--
Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/Bytes/"},"properties":[{"id":"unit","value":"binBps"}]},{"matcher":{"id":"byRegexp","options":"/Packets/"},"properties":[{"id":"unit","value":"pps"}]},{"matcher":{"id":"byName","options":"Workload"},"properties":[{"id":"links","value":[{"title":"Drill
--- HelmRelease: observability/kube-prometheus-stack ConfigMap: observability/kube-prometheus-stack-pod-total
+++ HelmRelease: observability/kube-prometheus-stack ConfigMap: observability/kube-prometheus-stack-pod-total
@@ -11,16 +11,16 @@
app.kubernetes.io/instance: kube-prometheus-stack
app.kubernetes.io/part-of: kube-prometheus-stack
release: kube-prometheus-stack
heritage: Helm
data:
pod-total.json: '{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"--
- Mixed --"},"fieldConfig":{"defaults":{"displayName":"$pod","max":10000000000,"min":0,"thresholds":{"steps":[{"color":"dark-green","index":0,"value":null},{"color":"dark-yellow","index":1,"value":5000000000},{"color":"dark-red","index":2,"value":7000000000}]},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":0,"y":0},"id":1,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\",
+ Mixed --"},"fieldConfig":{"defaults":{"displayName":"$pod","max":10000000000,"min":0,"thresholds":{"steps":[{"color":"dark-green","index":0,"value":null},{"color":"dark-yellow","index":1,"value":5000000000},{"color":"dark-red","index":2,"value":7000000000}]},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":0,"y":0},"id":1,"interval":"1m","pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\",
pod=~\"$pod\"}[$__rate_interval]))","legendFormat":"__auto"}],"title":"Current
Rate of Bytes Received","type":"gauge"},{"datasource":{"type":"datasource","uid":"--
- Mixed --"},"fieldConfig":{"defaults":{"displayName":"$pod","max":10000000000,"min":0,"thresholds":{"steps":[{"color":"dark-green","index":0,"value":null},{"color":"dark-yellow","index":1,"value":5000000000},{"color":"dark-red","index":2,"value":7000000000}]},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":12,"y":0},"id":2,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\",
+ Mixed --"},"fieldConfig":{"defaults":{"displayName":"$pod","max":10000000000,"min":0,"thresholds":{"steps":[{"color":"dark-green","index":0,"value":null},{"color":"dark-yellow","index":1,"value":5000000000},{"color":"dark-red","index":2,"value":7000000000}]},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":12,"y":0},"id":2,"interval":"1m","pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\",
pod=~\"$pod\"}[$__rate_interval]))","legendFormat":"__auto"}],"title":"Current
Rate of Bytes Transmitted","type":"gauge"},{"datasource":{"type":"datasource","uid":"--
Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":0,"y":9},"id":3,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\",
pod=~\"$pod\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Receive
Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed
--"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":12,"y":9},"id":4,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\",
--- HelmRelease: observability/kube-prometheus-stack ConfigMap: observability/kube-prometheus-stack-workload-total
+++ HelmRelease: observability/kube-prometheus-stack ConfigMap: observability/kube-prometheus-stack-workload-total
@@ -11,28 +11,28 @@
app.kubernetes.io/instance: kube-prometheus-stack
app.kubernetes.io/part-of: kube-prometheus-stack
release: kube-prometheus-stack
heritage: Helm
data:
workload-total.json: '{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"--
- Mixed --"},"fieldConfig":{"defaults":{"color":{"fixedColor":"green","mode":"fixed"},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":0,"y":0},"id":1,"options":{"displayMode":"basic","showUnfilled":false},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_bytes_total{job=\"kubelet\",
+ Mixed --"},"fieldConfig":{"defaults":{"color":{"fixedColor":"green","mode":"fixed"},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":0,"y":0},"id":1,"interval":"1m","options":{"displayMode":"basic","showUnfilled":false},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_bytes_total{job=\"kubelet\",
metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n*
on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\",
workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Current
Rate of Bytes Received","type":"bargauge"},{"datasource":{"type":"datasource","uid":"--
- Mixed --"},"fieldConfig":{"defaults":{"color":{"fixedColor":"green","mode":"fixed"},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":12,"y":0},"id":2,"options":{"displayMode":"basic","showUnfilled":false},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_transmit_bytes_total{job=\"kubelet\",
+ Mixed --"},"fieldConfig":{"defaults":{"color":{"fixedColor":"green","mode":"fixed"},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":12,"y":0},"id":2,"interval":"1m","options":{"displayMode":"basic","showUnfilled":false},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_transmit_bytes_total{job=\"kubelet\",
metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n*
on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\",
workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Current
Rate of Bytes Transmitted","type":"bargauge"},{"datasource":{"type":"datasource","uid":"--
- Mixed --"},"fieldConfig":{"defaults":{"color":{"fixedColor":"green","mode":"fixed"},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":0,"y":9},"id":3,"options":{"displayMode":"basic","showUnfilled":false},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(avg(rate(container_network_receive_bytes_total{job=\"kubelet\",
+ Mixed --"},"fieldConfig":{"defaults":{"color":{"fixedColor":"green","mode":"fixed"},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":0,"y":9},"id":3,"interval":"1m","options":{"displayMode":"basic","showUnfilled":false},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(avg(rate(container_network_receive_bytes_total{job=\"kubelet\",
metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n*
on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\",
workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Average
Rate of Bytes Received","type":"bargauge"},{"datasource":{"type":"datasource","uid":"--
- Mixed --"},"fieldConfig":{"defaults":{"color":{"fixedColor":"green","mode":"fixed"},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":12,"y":9},"id":4,"options":{"displayMode":"basic","showUnfilled":false},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(avg(rate(container_network_transmit_bytes_total{job=\"kubelet\",
+ Mixed --"},"fieldConfig":{"defaults":{"color":{"fixedColor":"green","mode":"fixed"},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":12,"y":9},"id":4,"interval":"1m","options":{"displayMode":"basic","showUnfilled":false},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(avg(rate(container_network_transmit_bytes_total{job=\"kubelet\",
metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n*
on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\",
workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Average
Rate of Bytes Transmitted","type":"bargauge"},{"datasource":{"type":"datasource","uid":"--
Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":0,"y":18},"id":5,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_bytes_total{job=\"kubelet\",
metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n*
--- HelmRelease: observability/kube-prometheus-stack DaemonSet: observability/node-exporter
+++ HelmRelease: observability/kube-prometheus-stack DaemonSet: observability/node-exporter
@@ -40,13 +40,13 @@
runAsGroup: 65534
runAsNonRoot: true
runAsUser: 65534
serviceAccountName: node-exporter
containers:
- name: node-exporter
- image: quay.io/prometheus/node-exporter:v1.9.0
+ image: quay.io/prometheus/node-exporter:v1.9.1
imagePullPolicy: IfNotPresent
args:
- --path.procfs=/host/proc
- --path.sysfs=/host/sys
- --path.rootfs=/host/root
- --path.udev.data=/host/root/run/udev/data
--- HelmRelease: observability/kube-prometheus-stack Deployment: observability/kube-state-metrics
+++ HelmRelease: observability/kube-prometheus-stack Deployment: observability/kube-state-metrics
@@ -37,12 +37,13 @@
fsGroup: 65534
runAsGroup: 65534
runAsNonRoot: true
runAsUser: 65534
seccompProfile:
type: RuntimeDefault
+ dnsPolicy: ClusterFirst
containers:
- name: kube-state-metrics
args:
- --port=8080
- --resources=certificatesigningrequests,configmaps,cronjobs,daemonsets,deployments,endpoints,horizontalpodautoscalers,ingresses,jobs,leases,limitranges,mutatingwebhookconfigurations,namespaces,networkpolicies,nodes,persistentvolumeclaims,persistentvolumes,poddisruptionbudgets,pods,replicasets,replicationcontrollers,resourcequotas,secrets,services,statefulsets,storageclasses,validatingwebhookconfigurations,volumeattachments
- --metric-labels-allowlist=pods=[*],nodes=[*],deployments=[*],persistentvolumeclaims=[*]
--- HelmRelease: observability/kube-prometheus-stack Deployment: observability/kube-prometheus-stack-operator
+++ HelmRelease: observability/kube-prometheus-stack Deployment: observability/kube-prometheus-stack-operator
@@ -43,13 +43,13 @@
- --localhost=127.0.0.1
- --prometheus-config-reloader=quay.io/prometheus-operator/prometheus-config-reloader:v0.81.0
- --config-reloader-cpu-request=0
- --config-reloader-cpu-limit=0
- --config-reloader-memory-request=0
- --config-reloader-memory-limit=0
- - --thanos-default-base-image=quay.io/thanos/thanos:v0.37.2
+ - --thanos-default-base-image=quay.io/thanos/thanos:v0.38.0
- --secret-field-selector=type!=kubernetes.io/dockercfg,type!=kubernetes.io/service-account-token,type!=helm.sh/release.v1
- --web.enable-tls=true
- --web.cert-file=/cert/cert
- --web.key-file=/cert/key
- --web.listen-address=:10250
- --web.tls-min-version=VersionTLS13
--- HelmRelease: observability/kube-prometheus-stack Prometheus: observability/kube-prometheus-stack
+++ HelmRelease: observability/kube-prometheus-stack Prometheus: observability/kube-prometheus-stack
@@ -17,14 +17,14 @@
alertmanagers:
- namespace: observability
name: kube-prometheus-stack-alertmanager
port: http-web
pathPrefix: /
apiVersion: v2
- image: quay.io/prometheus/prometheus:v3.2.1
- version: v3.2.1
+ image: quay.io/prometheus/prometheus:v3.3.0
+ version: v3.3.0
externalUrl: http://prometheus...PLACEHOLDER_SECRET_DOMAIN../
paused: false
replicas: 1
shards: 1
logLevel: info
logFormat: logfmt
--- HelmRelease: observability/kube-prometheus-stack PrometheusRule: observability/kube-prometheus-stack-alertmanager.rules
+++ HelmRelease: observability/kube-prometheus-stack PrometheusRule: observability/kube-prometheus-stack-alertmanager.rules
@@ -50,15 +50,15 @@
to send {{ $value | humanizePercentage }} of notifications to {{ $labels.integration
}}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerfailedtosendalerts
summary: An Alertmanager instance failed to send notifications.
expr: |-
(
- rate(alertmanager_notifications_failed_total{job="kube-prometheus-stack-alertmanager",namespace="observability"}[5m])
+ rate(alertmanager_notifications_failed_total{job="kube-prometheus-stack-alertmanager",namespace="observability"}[15m])
/
- ignoring (reason) group_left rate(alertmanager_notifications_total{job="kube-prometheus-stack-alertmanager",namespace="observability"}[5m])
+ ignoring (reason) group_left rate(alertmanager_notifications_total{job="kube-prometheus-stack-alertmanager",namespace="observability"}[15m])
)
> 0.01
for: 5m
labels:
severity: warning
- alert: AlertmanagerClusterFailedToSendAlerts
@@ -68,15 +68,15 @@
humanizePercentage }}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclusterfailedtosendalerts
summary: All Alertmanager instances in a cluster failed to send notifications
to a critical integration.
expr: |-
min by (namespace,service, integration) (
- rate(alertmanager_notifications_failed_total{job="kube-prometheus-stack-alertmanager",namespace="observability", integration=~`.*`}[5m])
+ rate(alertmanager_notifications_failed_total{job="kube-prometheus-stack-alertmanager",namespace="observability", integration=~`.*`}[15m])
/
- ignoring (reason) group_left rate(alertmanager_notifications_total{job="kube-prometheus-stack-alertmanager",namespace="observability", integration=~`.*`}[5m])
+ ignoring (reason) group_left rate(alertmanager_notifications_total{job="kube-prometheus-stack-alertmanager",namespace="observability", integration=~`.*`}[15m])
)
> 0.01
for: 5m
labels:
severity: critical
- alert: AlertmanagerClusterFailedToSendAlerts
@@ -86,15 +86,15 @@
humanizePercentage }}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclusterfailedtosendalerts
summary: All Alertmanager instances in a cluster failed to send notifications
to a non-critical integration.
expr: |-
min by (namespace,service, integration) (
- rate(alertmanager_notifications_failed_total{job="kube-prometheus-stack-alertmanager",namespace="observability", integration!~`.*`}[5m])
+ rate(alertmanager_notifications_failed_total{job="kube-prometheus-stack-alertmanager",namespace="observability", integration!~`.*`}[15m])
/
- ignoring (reason) group_left rate(alertmanager_notifications_total{job="kube-prometheus-stack-alertmanager",namespace="observability", integration!~`.*`}[5m])
+ ignoring (reason) group_left rate(alertmanager_notifications_total{job="kube-prometheus-stack-alertmanager",namespace="observability", integration!~`.*`}[15m])
)
> 0.01
for: 5m
labels:
severity: warning
- alert: AlertmanagerConfigInconsistent
--- HelmRelease: observability/kube-prometheus-stack PrometheusRule: observability/kube-prometheus-stack-k8s.rules.container-cpu-usage-seconds-tot
+++ HelmRelease: observability/kube-prometheus-stack PrometheusRule: observability/kube-prometheus-stack-k8s.rules.container-cpu-usage-seconds-tot
@@ -14,12 +14,19 @@
spec:
groups:
- name: k8s.rules.container_cpu_usage_seconds_total
rules:
- expr: |-
sum by (cluster, namespace, pod, container) (
+ rate(container_cpu_usage_seconds_total{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}[5m])
+ ) * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (
+ 1, max by (cluster, namespace, pod, node) (kube_pod_info{node!=""})
+ )
+ record: node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m
+ - expr: |-
+ sum by (cluster, namespace, pod, container) (
irate(container_cpu_usage_seconds_total{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}[5m])
) * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (
1, max by (cluster, namespace, pod, node) (kube_pod_info{node!=""})
)
record: node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate
--- HelmRelease: observability/kube-prometheus-stack PrometheusRule: observability/kube-prometheus-stack-kube-apiserver-availability.rules
+++ HelmRelease: observability/kube-prometheus-stack PrometheusRule: observability/kube-prometheus-stack-kube-apiserver-availability.rules
@@ -39,28 +39,24 @@
- expr: |-
1 - (
(
# write too slow
sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~"POST|PUT|PATCH|DELETE"})
-
- sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"POST|PUT|PATCH|DELETE",le=~"1(\\.0)?"})
+ sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"POST|PUT|PATCH|DELETE",le=~"1(\\.0)?"} or vector(0))
) +
(
# read too slow
sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~"LIST|GET"})
-
(
- (
- sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope=~"resource|",le=~"1(\\.0)?"})
- or
- vector(0)
- )
+ sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope=~"resource|",le=~"1(\\.0)?"} or vector(0))
+
- sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="namespace",le=~"5(\\.0)?"})
+ sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="namespace",le=~"5(\\.0)?"} or vector(0))
+
- sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="cluster",le=~"30(\\.0)?"})
+ sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="cluster",le=~"30(\\.0)?"} or vector(0))
)
) +
# errors
sum by (cluster) (code:apiserver_request_total:increase30d{code=~"5.."} or vector(0))
)
/
@@ -71,21 +67,17 @@
- expr: |-
1 - (
sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~"LIST|GET"})
-
(
# too slow
- (
- sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope=~"resource|",le=~"1(\\.0)?"})
- or
- vector(0)
- )
+ sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope=~"resource|",le=~"1(\\.0)?"} or vector(0))
+
- sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="namespace",le=~"5(\\.0)?"})
+ sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="namespace",le=~"5(\\.0)?"} or vector(0))
+
- sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="cluster",le=~"30(\\.0)?"})
+ sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="cluster",le=~"30(\\.0)?"} or vector(0))
)
+
# errors
sum by (cluster) (code:apiserver_request_total:increase30d{verb="read",code=~"5.."} or vector(0))
)
/
@@ -96,13 +88,13 @@
- expr: |-
1 - (
(
# too slow
sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~"POST|PUT|PATCH|DELETE"})
-
- sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"POST|PUT|PATCH|DELETE",le=~"1(\\.0)?"})
+ sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"POST|PUT|PATCH|DELETE",le=~"1(\\.0)?"} or vector(0))
)
+
# errors
sum by (cluster) (code:apiserver_request_total:increase30d{verb="write",code=~"5.."} or vector(0))
)
/
--- HelmRelease: observability/kube-prometheus-stack PrometheusRule: observability/kube-prometheus-stack-kubernetes-resources
+++ HelmRelease: observability/kube-prometheus-stack PrometheusRule: observability/kube-prometheus-stack-kubernetes-resources
@@ -15,13 +15,14 @@
groups:
- name: kubernetes-resources
rules:
- alert: KubeCPUOvercommit
annotations:
description: Cluster {{ $labels.cluster }} has overcommitted CPU resource
- requests for Pods by {{ $value }} CPU shares and cannot tolerate node failure.
+ requests for Pods by {{ printf "%.2f" $value }} CPU shares and cannot tolerate
+ node failure.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecpuovercommit
summary: Cluster has overcommitted CPU resource requests.
expr: |-
sum(namespace_cpu:kube_pod_container_resource_requests:sum{}) by (cluster) - (sum(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster) - max(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster)) > 0
and
(sum(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster) - max(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster)) > 0
@@ -55,13 +56,13 @@
> 1.5
for: 5m
labels:
severity: warning
- alert: KubeMemoryQuotaOvercommit
annotations:
- description: Cluster {{ $labels.cluster }} has overcommitted memory resource
+ description: Cluster {{ $labels.cluster }} has overcommitted memory resource
requests for Namespaces.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubememoryquotaovercommit
summary: Cluster has overcommitted memory resource requests.
expr: |-
sum(min without(resource) (kube_resourcequota{job="kube-state-metrics", type="hard", resource=~"(memory|requests.memory)"})) by (cluster)
/
@@ -118,13 +119,13 @@
{{ $labels.namespace }} for container {{ $labels.container }} in pod {{
$labels.pod }} on cluster {{ $labels.cluster }}.'
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/cputhrottlinghigh
summary: Processes experience elevated CPU throttling.
expr: |-
sum(increase(container_cpu_cfs_throttled_periods_total{container!="", job="kubelet", metrics_path="/metrics/cadvisor", }[5m])) without (id, metrics_path, name, image, endpoint, job, node)
- /
+ / on (cluster, namespace, pod, container, instance) group_left
sum(increase(container_cpu_cfs_periods_total{job="kubelet", metrics_path="/metrics/cadvisor", }[5m])) without (id, metrics_path, name, image, endpoint, job, node)
> ( 25 / 100 )
for: 15m
labels:
severity: info
--- HelmRelease: observability/kube-prometheus-stack PrometheusRule: observability/kube-prometheus-stack-kubernetes-system-kubelet
+++ HelmRelease: observability/kube-prometheus-stack PrometheusRule: observability/kube-prometheus-stack-kubernetes-system-kubelet
@@ -25,12 +25,26 @@
kube_node_status_condition{job="kube-state-metrics",condition="Ready",status="true"} == 0
and on (cluster, node)
kube_node_spec_unschedulable{job="kube-state-metrics"} == 0
for: 15m
labels:
severity: warning
+ - alert: KubeNodePressure
+ annotations:
+ description: '{{ $labels.node }} on cluster {{ $labels.cluster }} has active
+ Condition {{ $labels.condition }}. This is caused by resource usage exceeding
+ eviction thresholds.'
+ runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodepressure
+ summary: Node has as active Condition.
+ expr: |-
+ kube_node_status_condition{job="kube-state-metrics",condition=~"(MemoryPressure|DiskPressure|PIDPressure)",status="true"} == 1
+ and on (cluster, node)
+ kube_node_spec_unschedulable{job="kube-state-metrics"} == 0
+ for: 10m
+ labels:
+ severity: info
- alert: KubeNodeUnreachable
annotations:
description: '{{ $labels.node }} is unreachable and some workloads may be
rescheduled on cluster {{ $labels.cluster }}.'
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodeunreachable
summary: Node is unreachable.
@@ -73,12 +87,30 @@
sum(changes(kube_node_status_condition{job="kube-state-metrics",status="true",condition="Ready"}[15m])) by (cluster, node) > 2
and on (cluster, node)
kube_node_spec_unschedulable{job="kube-state-metrics"} == 0
for: 15m
labels:
severity: warning
+ - alert: KubeNodeEviction
+ annotations:
+ description: Node {{ $labels.node }} on {{ $labels.cluster }} is evicting
+ Pods due to {{ $labels.eviction_signal }}. Eviction occurs when eviction
+ thresholds are crossed, typically caused by Pods exceeding RAM/ephemeral-storage
+ limits.
+ runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodeeviction
+ summary: Node is evicting pods.
+ expr: |-
+ sum(rate(kubelet_evictions{job="kubelet", metrics_path="/metrics"}[15m])) by (cluster, eviction_signal, instance)
+ * on (cluster, instance) group_left(node)
+ max by (cluster, instance, node) (
+ kubelet_node_name{job="kubelet", metrics_path="/metrics"}
+ )
+ > 0
+ for: 0s
+ labels:
+ severity: info
- alert: KubeletPlegDurationHigh
annotations:
description: The Kubelet Pod Lifecycle Event Generator has a 99th percentile
duration of {{ $value }} seconds on node {{ $labels.node }} on cluster {{
$labels.cluster }}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletplegdurationhigh
--- HelmRelease: observability/kube-prometheus-stack ServiceMonitor: observability/kube-prometheus-stack-apiserver
+++ HelmRelease: observability/kube-prometheus-stack ServiceMonitor: observability/kube-prometheus-stack-apiserver
@@ -15,13 +15,13 @@
endpoints:
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
port: https
scheme: https
metricRelabelings:
- action: drop
- regex: (etcd_request|apiserver_request_slo|apiserver_request_sli|apiserver_request)_duration_seconds_bucket;(0\.15|0\.2|0\.3|0\.35|0\.4|0\.45|0\.6|0\.7|0\.8|0\.9|1\.25|1\.5|1\.75|2|3|3\.5|4|4\.5|6|7|8|9|15|20|30|40|45|50)(\.0)?
+ regex: (etcd_request|apiserver_request_slo|apiserver_request_sli|apiserver_request)_duration_seconds_bucket;(0\.15|0\.2|0\.3|0\.35|0\.4|0\.45|0\.6|0\.7|0\.8|0\.9|1\.25|1\.5|1\.75|2|3|3\.5|4|4\.5|6|7|8|9|15|20|40|45|50)(\.0)?
sourceLabels:
- __name__
- le
tlsConfig:
caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
serverName: kubernetes
--- HelmRelease: observability/kube-prometheus-stack Job: observability/kube-prometheus-stack-admission-create
+++ HelmRelease: observability/kube-prometheus-stack Job: observability/kube-prometheus-stack-admission-create
@@ -30,13 +30,13 @@
heritage: Helm
app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator
app.kubernetes.io/component: prometheus-operator-webhook
spec:
containers:
- name: create
- image: registry.k8s.io/ingress-nginx/kube-webhook-certgen:v1.5.1
+ image: registry.k8s.io/ingress-nginx/kube-webhook-certgen:v1.5.2
imagePullPolicy: IfNotPresent
args:
- create
- --host=kube-prometheus-stack-operator,kube-prometheus-stack-operator.observability.svc
- --namespace=observability
- --secret-name=kube-prometheus-stack-admission
--- HelmRelease: observability/kube-prometheus-stack Job: observability/kube-prometheus-stack-admission-patch
+++ HelmRelease: observability/kube-prometheus-stack Job: observability/kube-prometheus-stack-admission-patch
@@ -30,13 +30,13 @@
heritage: Helm
app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator
app.kubernetes.io/component: prometheus-operator-webhook
spec:
containers:
- name: patch
- image: registry.k8s.io/ingress-nginx/kube-webhook-certgen:v1.5.1
+ image: registry.k8s.io/ingress-nginx/kube-webhook-certgen:v1.5.2
imagePullPolicy: IfNotPresent
args:
- patch
- --webhook-name=kube-prometheus-stack-admission
- --namespace=observability
- --secret-name=kube-prometheus-stack-admission |
renovate
Bot
force-pushed
the
renovate/kube-prometheus-stack-70.x
branch
from
02092cc to
78f36d6
Compare
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/kube-prometheus-stack-70.x
branch
from
78f36d6 to
e7b3ea7
Compare
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/kube-prometheus-stack-70.x
branch
from
e7b3ea7 to
231c1cb
Compare
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/kube-prometheus-stack-70.x
branch
from
231c1cb to
3c1f3a5
Compare
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/kube-prometheus-stack-70.x
branch
from
3c1f3a5 to
b9911b4
Compare
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/kube-prometheus-stack-70.x
branch
from
b9911b4 to
eff6239
Compare
renovate
Bot
changed the title
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/kube-prometheus-stack-70.x
branch
2 times, most recently
from
eb55aae to
3722f9e
Compare
renovate
Bot
changed the title
renovate
Bot
changed the title
renovate
Bot
changed the title
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/kube-prometheus-stack-70.x
branch
2 times, most recently
from
57926c7 to
d5c6839
Compare
renovate
Bot
changed the title
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/kube-prometheus-stack-70.x
branch
from
368170a to
d5c6839
Compare
renovate
Bot
changed the title
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/kube-prometheus-stack-70.x
branch
2 times, most recently
from
d5c6839 to
38e102e
Compare
renovate
Bot
changed the title
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/kube-prometheus-stack-70.x
branch
2 times, most recently
from
38e102e to
505fc66
Compare
renovate
Bot
changed the title
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/kube-prometheus-stack-70.x
branch
2 times, most recently
from
505fc66 to
edcbe0b
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR contains the following updates:
70.0.2→70.10.0Release Notes
prometheus-community/helm-charts (kube-prometheus-stack)
v70.10.0Compare Source
kube-prometheus-stack collects Kubernetes manifests, Grafana dashboards, and Prometheus rules combined with documentation and scripts to provide easy to operate end-to-end Kubernetes cluster monitoring with Prometheus using the Prometheus Operator.
What's Changed
Full Changelog: prometheus-community/helm-charts@prometheus-blackbox-exporter-9.5.0...kube-prometheus-stack-70.10.0
v70.9.0Compare Source
kube-prometheus-stack collects Kubernetes manifests, Grafana dashboards, and Prometheus rules combined with documentation and scripts to provide easy to operate end-to-end Kubernetes cluster monitoring with Prometheus using the Prometheus Operator.
What's Changed
Full Changelog: prometheus-community/helm-charts@kube-state-metrics-5.33.0...kube-prometheus-stack-70.9.0
v70.8.0Compare Source
kube-prometheus-stack collects Kubernetes manifests, Grafana dashboards, and Prometheus rules combined with documentation and scripts to provide easy to operate end-to-end Kubernetes cluster monitoring with Prometheus using the Prometheus Operator.
What's Changed
New Contributors
Full Changelog: prometheus-community/helm-charts@prometheus-smartctl-exporter-0.14.0...kube-prometheus-stack-70.8.0
v70.7.0Compare Source
kube-prometheus-stack collects Kubernetes manifests, Grafana dashboards, and Prometheus rules combined with documentation and scripts to provide easy to operate end-to-end Kubernetes cluster monitoring with Prometheus using the Prometheus Operator.
What's Changed
Full Changelog: prometheus-community/helm-charts@prometheus-windows-exporter-0.10.0...kube-prometheus-stack-70.7.0
v70.6.0Compare Source
kube-prometheus-stack collects Kubernetes manifests, Grafana dashboards, and Prometheus rules combined with documentation and scripts to provide easy to operate end-to-end Kubernetes cluster monitoring with Prometheus using the Prometheus Operator.
What's Changed
New Contributors
Full Changelog: prometheus-community/helm-charts@prometheus-27.9.0...kube-prometheus-stack-70.6.0
v70.5.0Compare Source
kube-prometheus-stack collects Kubernetes manifests, Grafana dashboards, and Prometheus rules combined with documentation and scripts to provide easy to operate end-to-end Kubernetes cluster monitoring with Prometheus using the Prometheus Operator.
What's Changed
Full Changelog: prometheus-community/helm-charts@prometheus-operator-crds-19.1.0...kube-prometheus-stack-70.5.0
v70.4.2Compare Source
kube-prometheus-stack collects Kubernetes manifests, Grafana dashboards, and Prometheus rules combined with documentation and scripts to provide easy to operate end-to-end Kubernetes cluster monitoring with Prometheus using the Prometheus Operator.
What's Changed
Full Changelog: prometheus-community/helm-charts@kube-state-metrics-5.31.1...kube-prometheus-stack-70.4.2
v70.4.1Compare Source
kube-prometheus-stack collects Kubernetes manifests, Grafana dashboards, and Prometheus rules combined with documentation and scripts to provide easy to operate end-to-end Kubernetes cluster monitoring with Prometheus using the Prometheus Operator.
What's Changed
New Contributors
Full Changelog: prometheus-community/helm-charts@kube-prometheus-stack-70.4.0...kube-prometheus-stack-70.4.1
v70.4.0Compare Source
kube-prometheus-stack collects Kubernetes manifests, Grafana dashboards, and Prometheus rules combined with documentation and scripts to provide easy to operate end-to-end Kubernetes cluster monitoring with Prometheus using the Prometheus Operator.
What's Changed
Full Changelog: prometheus-community/helm-charts@prometheus-elasticsearch-exporter-6.7.1...kube-prometheus-stack-70.4.0
v70.3.0Compare Source
kube-prometheus-stack collects Kubernetes manifests, Grafana dashboards, and Prometheus rules combined with documentation and scripts to provide easy to operate end-to-end Kubernetes cluster monitoring with Prometheus using the Prometheus Operator.
What's Changed
New Contributors
Full Changelog: prometheus-community/helm-charts@prometheus-operator-admission-webhook-0.21.0...kube-prometheus-stack-70.3.0
v70.2.1Compare Source
kube-prometheus-stack collects Kubernetes manifests, Grafana dashboards, and Prometheus rules combined with documentation and scripts to provide easy to operate end-to-end Kubernetes cluster monitoring with Prometheus using the Prometheus Operator.
What's Changed
New Contributors
Full Changelog: prometheus-community/helm-charts@prometheus-snmp-exporter-9.1.0...kube-prometheus-stack-70.2.1
v70.2.0Compare Source
kube-prometheus-stack collects Kubernetes manifests, Grafana dashboards, and Prometheus rules combined with documentation and scripts to provide easy to operate end-to-end Kubernetes cluster monitoring with Prometheus using the Prometheus Operator.
What's Changed
Full Changelog: prometheus-community/helm-charts@prometheus-27.6.0...kube-prometheus-stack-70.2.0
v70.1.1Compare Source
kube-prometheus-stack collects Kubernetes manifests, Grafana dashboards, and Prometheus rules combined with documentation and scripts to provide easy to operate end-to-end Kubernetes cluster monitoring with Prometheus using the Prometheus Operator.
What's Changed
Full Changelog: prometheus-community/helm-charts@kube-prometheus-stack-70.1.0...kube-prometheus-stack-70.1.1
v70.1.0Compare Source
kube-prometheus-stack collects Kubernetes manifests, Grafana dashboards, and Prometheus rules combined with documentation and scripts to provide easy to operate end-to-end Kubernetes cluster monitoring with Prometheus using the Prometheus Operator.
What's Changed
Full Changelog: prometheus-community/helm-charts@kube-prometheus-stack-70.0.3...kube-prometheus-stack-70.1.0
v70.0.3Compare Source
kube-prometheus-stack collects Kubernetes manifests, Grafana dashboards, and Prometheus rules combined with documentation and scripts to provide easy to operate end-to-end Kubernetes cluster monitoring with Prometheus using the Prometheus Operator.
What's Changed
Full Changelog: prometheus-community/helm-charts@prometheus-cloudwatch-exporter-0.27.0...kube-prometheus-stack-70.0.3
Configuration
📅 Schedule: Branch creation - "every weekend" (UTC), Automerge - At any time (no schedule defined).
🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.
♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.
🔕 Ignore: Close this PR and you won't be reminded about this update again.
This PR was generated by Mend Renovate. View the repository job log.