mirror of
https://github.com/carlosedp/cluster-monitoring.git
synced 2024-11-20 19:07:17 +01:00
Update libs. Re-add Kube-state-metrics override due to reverted threshold parameter on lib
This commit is contained in:
CarlosEDP
parent
de1c46dd63
commit
d4114769e2
2
Makefile
2
Makefile
@ -11,7 +11,7 @@ manifests: jsonnet
|
||||
rm -rf manifests
|
||||
./scripts/build.sh main.jsonnet $(JSONNET_BIN)
|
||||
|
||||
update:
|
||||
update: jsonnet_bundler
|
||||
jb update
|
||||
|
||||
vendor: jsonnet_bundler jsonnetfile.json jsonnetfile.lock.json
|
||||
|
||||
@ -120,6 +120,38 @@ local k = import 'ksonnet/ksonnet.beta.3/k.libsonnet';
|
||||
|
||||
grafanaDashboards+:: $._config.grafanaDashboards,
|
||||
|
||||
kubeStateMetrics+:: {
|
||||
// Override command for addon-resizer due to change from parameter --threshold to --acceptance-offset
|
||||
deployment+: {
|
||||
spec+: {
|
||||
template+: {
|
||||
spec+: {
|
||||
containers:
|
||||
std.map(
|
||||
function(c)
|
||||
if std.startsWith(c.name, 'addon-resizer') then
|
||||
c {
|
||||
command: [
|
||||
'/pod_nanny',
|
||||
'--container=kube-state-metrics',
|
||||
'--cpu=100m',
|
||||
'--extra-cpu=2m',
|
||||
'--memory=150Mi',
|
||||
'--extra-memory=30Mi',
|
||||
'--acceptance-offset=5',
|
||||
'--deployment=kube-state-metrics',
|
||||
],
|
||||
}
|
||||
else
|
||||
c,
|
||||
super.containers,
|
||||
),
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
|
||||
// Create ingress objects per application
|
||||
ingress+: {
|
||||
local secret = k.core.v1.secret,
|
||||
|
||||
@ -8,7 +8,7 @@
|
||||
"subdir": "contrib/kube-prometheus/jsonnet/kube-prometheus"
|
||||
}
|
||||
},
|
||||
"version": "99e5661f8d46ec2173f65b69eeb97f6e52d38e0d"
|
||||
"version": "650359b3e627ae97a1f18cbd10d7ed9b2293c240"
|
||||
},
|
||||
{
|
||||
"name": "ksonnet",
|
||||
@ -28,7 +28,7 @@
|
||||
"subdir": ""
|
||||
}
|
||||
},
|
||||
"version": "9069b2c1be0ce32f63f9a01c4a4f8d69bc4e37d5"
|
||||
"version": "19db38fc449df024446059f21d5a329babaa3927"
|
||||
},
|
||||
{
|
||||
"name": "grafonnet",
|
||||
@ -38,7 +38,7 @@
|
||||
"subdir": "grafonnet"
|
||||
}
|
||||
},
|
||||
"version": "11022f5e920ac1ea960556193e3f0ab57d70d7c5"
|
||||
"version": "d270f529db9eb750425a173188c534ab92532f47"
|
||||
},
|
||||
{
|
||||
"name": "grafana-builder",
|
||||
@ -48,7 +48,7 @@
|
||||
"subdir": "grafana-builder"
|
||||
}
|
||||
},
|
||||
"version": "5cc4bfab6e2453266e47d01b78cbae0b2643426e"
|
||||
"version": "e30a6040f3d7270655a980ab04d16142da4b429d"
|
||||
},
|
||||
{
|
||||
"name": "grafana",
|
||||
@ -58,7 +58,7 @@
|
||||
"subdir": "grafana"
|
||||
}
|
||||
},
|
||||
"version": "9ddf5a198b0f7c898dc061158ea427112acbae11"
|
||||
"version": "de2ec3f0f9115da2d47dc6b86af9b402e2bf146d"
|
||||
},
|
||||
{
|
||||
"name": "prometheus-operator",
|
||||
@ -78,7 +78,7 @@
|
||||
"subdir": "Documentation/etcd-mixin"
|
||||
}
|
||||
},
|
||||
"version": "e1ca3b4434945e57e8e3a451cdbde74a903cc8e1"
|
||||
"version": "7a5acb4a43aa06bd9e32ab59a46271ab88d497e4"
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
apiVersion: v1
|
||||
data:
|
||||
alertmanager.yaml: Imdsb2JhbCI6CiAgInJlc29sdmVfdGltZW91dCI6ICI1bSIKInJlY2VpdmVycyI6Ci0gIm5hbWUiOiAibnVsbCIKInJvdXRlIjoKICAiZ3JvdXBfYnkiOgogIC0gImpvYiIKICAiZ3JvdXBfaW50ZXJ2YWwiOiAiNW0iCiAgImdyb3VwX3dhaXQiOiAiMzBzIgogICJyZWNlaXZlciI6ICJudWxsIgogICJyZXBlYXRfaW50ZXJ2YWwiOiAiMTJoIgogICJyb3V0ZXMiOgogIC0gIm1hdGNoIjoKICAgICAgImFsZXJ0bmFtZSI6ICJEZWFkTWFuc1N3aXRjaCIKICAgICJyZWNlaXZlciI6ICJudWxsIg==
|
||||
alertmanager.yaml: Imdsb2JhbCI6CiAgInJlc29sdmVfdGltZW91dCI6ICI1bSIKInJlY2VpdmVycyI6Ci0gIm5hbWUiOiAibnVsbCIKInJvdXRlIjoKICAiZ3JvdXBfYnkiOgogIC0gImpvYiIKICAiZ3JvdXBfaW50ZXJ2YWwiOiAiNW0iCiAgImdyb3VwX3dhaXQiOiAiMzBzIgogICJyZWNlaXZlciI6ICJudWxsIgogICJyZXBlYXRfaW50ZXJ2YWwiOiAiMTJoIgogICJyb3V0ZXMiOgogIC0gIm1hdGNoIjoKICAgICAgImFsZXJ0bmFtZSI6ICJXYXRjaGRvZyIKICAgICJyZWNlaXZlciI6ICJudWxsIg==
|
||||
kind: Secret
|
||||
metadata:
|
||||
name: alertmanager-main
|
||||
|
||||
@ -12736,7 +12736,7 @@ items:
|
||||
],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "CPU Utilizaion",
|
||||
"title": "CPU Utilization",
|
||||
"tooltip": {
|
||||
"shared": false,
|
||||
"sort": 0,
|
||||
@ -14361,11 +14361,25 @@ items:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (container_name) (rate(container_cpu_usage_seconds_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\", image!=\"\",container_name!=\"POD\",pod_name=\"$pod\"}[1m]))",
|
||||
"expr": "sum by (container_name) (rate(container_cpu_usage_seconds_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\", image!=\"\", pod_name=\"$pod\", container_name=~\"$container\", container_name!=\"POD\"}[1m]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{ container_name }}",
|
||||
"legendFormat": "Current: {{ container_name }}",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "sum by(container) (kube_pod_container_resource_requests_cpu_cores{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Requested: {{ container }}",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum by(container) (kube_pod_container_resource_limits_cpu_cores{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Limit: {{ container }}",
|
||||
"refId": "C"
|
||||
}
|
||||
],
|
||||
"thresholds": [
|
||||
|
||||
@ -37,7 +37,7 @@ spec:
|
||||
record: namespace_name:container_memory_usage_bytes:sum
|
||||
- expr: |
|
||||
sum by (namespace, label_name) (
|
||||
sum(kube_pod_container_resource_requests_memory_bytes{job="kube-state-metrics"}) by (namespace, pod)
|
||||
sum(kube_pod_container_resource_requests_memory_bytes{job="kube-state-metrics"} * on (endpoint, instance, job, namespace, pod, service) group_left(phase) (kube_pod_status_phase{phase=~"^(Pending|Running)$"} == 1)) by (namespace, pod)
|
||||
* on (namespace, pod) group_left(label_name)
|
||||
label_replace(kube_pod_labels{job="kube-state-metrics"}, "pod_name", "$1", "pod", "(.*)")
|
||||
)
|
||||
@ -629,7 +629,7 @@ spec:
|
||||
message: Cluster has overcommitted CPU resource requests for Namespaces.
|
||||
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuovercommit
|
||||
expr: |
|
||||
sum(kube_resourcequota{job="kube-state-metrics", type="hard", resource="requests.cpu"})
|
||||
sum(kube_resourcequota{job="kube-state-metrics", type="hard", resource="cpu"})
|
||||
/
|
||||
sum(node:node_num_cpu:sum)
|
||||
> 1.5
|
||||
@ -641,7 +641,7 @@ spec:
|
||||
message: Cluster has overcommitted memory resource requests for Namespaces.
|
||||
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememovercommit
|
||||
expr: |
|
||||
sum(kube_resourcequota{job="kube-state-metrics", type="hard", resource="requests.memory"})
|
||||
sum(kube_resourcequota{job="kube-state-metrics", type="hard", resource="memory"})
|
||||
/
|
||||
sum(node_memory_MemTotal_bytes{job="node-exporter"})
|
||||
> 1.5
|
||||
@ -842,7 +842,7 @@ spec:
|
||||
in less than 7 days.
|
||||
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration
|
||||
expr: |
|
||||
histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 604800
|
||||
apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 604800
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: KubeClientCertificateExpiration
|
||||
@ -851,7 +851,7 @@ spec:
|
||||
in less than 24 hours.
|
||||
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration
|
||||
expr: |
|
||||
histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 86400
|
||||
apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 86400
|
||||
labels:
|
||||
severity: critical
|
||||
- name: alertmanager.rules
|
||||
|
||||
Loading…
Reference in New Issue
Block a user