Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update kubernetes-mixin digest to bdbf7f4 #10

Merged
merged 2 commits into from
Nov 8, 2024
Merged

Update kubernetes-mixin digest to bdbf7f4 #10

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e798a84
Update kubernetes-mixin digest to bdbf7f4
renovate[bot] Nov 8, 2024
ff5385f
Update files after Renovate update
bonddim-actions[bot] Nov 8, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions docs/azure/prometheusAlerts.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,13 +122,13 @@
},
{
"alert": "KubeContainerWaiting",
"expr": "sum by (namespace, pod, container, cluster) (kube_pod_container_status_waiting_reason{job=\"kube-state-metrics\"}) > 0",
"expr": "kube_pod_container_status_waiting_reason{reason!=\"CrashLoopBackOff\", job=\"kube-state-metrics\"} > 0",
"for": "1h",
"labels": {
"severity": "warning"
},
"annotations": {
"description": "pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on container {{ $labels.container}} has been in waiting state for longer than 1 hour.",
"description": "pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on container {{ $labels.container}} has been in waiting state for longer than 1 hour. (reason: \"{{ $labels.reason }}\").",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontainerwaiting",
"summary": "Pod container waiting longer than 1 hour"
}
Expand Down Expand Up @@ -308,7 +308,7 @@
},
{
"alert": "CPUThrottlingHigh",
"expr": "sum(increase(container_cpu_cfs_throttled_periods_total{container!=\"\", }[5m])) by (cluster, container, pod, namespace) / sum(increase(container_cpu_cfs_periods_total{}[5m])) by (cluster, container, pod, namespace) > (25 / 100)",
"expr": "sum(increase(container_cpu_cfs_throttled_periods_total{container!=\"\", job=\"cadvisor\", }[5m])) without (id, metrics_path, name, image, endpoint, job, node) / sum(increase(container_cpu_cfs_periods_total{job=\"cadvisor\", }[5m])) without (id, metrics_path, name, image, endpoint, job, node) > (25 / 100)",
"for": "15m",
"labels": {
"severity": "info"
Expand Down Expand Up @@ -492,7 +492,7 @@
"rules": [
{
"alert": "KubeClientCertificateExpiration",
"expr": "apiserver_client_certificate_expiration_seconds_count{job=\"kube-apiserver\"} > 0 and on(cluster, job) histogram_quantile(0.01, sum by (cluster, job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"kube-apiserver\"}[5m]))) < 604800",
"expr": "histogram_quantile(0.01, sum without (namespace, service, endpoint) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"kube-apiserver\"}[5m]))) < 604800 and on(job, cluster, instance) apiserver_client_certificate_expiration_seconds_count{job=\"kube-apiserver\"} > 0",
"for": "5m",
"labels": {
"severity": "warning"
Expand All @@ -505,7 +505,7 @@
},
{
"alert": "KubeClientCertificateExpiration",
"expr": "apiserver_client_certificate_expiration_seconds_count{job=\"kube-apiserver\"} > 0 and on(cluster, job) histogram_quantile(0.01, sum by (cluster, job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"kube-apiserver\"}[5m]))) < 86400",
"expr": "histogram_quantile(0.01, sum without (namespace, service, endpoint) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"kube-apiserver\"}[5m]))) < 86400 and on(job, cluster, instance) apiserver_client_certificate_expiration_seconds_count{job=\"kube-apiserver\"} > 0",
"for": "5m",
"labels": {
"severity": "critical"
Expand Down
10 changes: 5 additions & 5 deletions docs/azure/prometheusAlerts.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,12 +93,12 @@ groups:
summary: DaemonSet rollout is stuck.
- alert: "KubeContainerWaiting"
expr: |-
sum by (namespace, pod, container, cluster) (kube_pod_container_status_waiting_reason{job="kube-state-metrics"}) > 0
kube_pod_container_status_waiting_reason{reason!="CrashLoopBackOff", job="kube-state-metrics"} > 0
for: 1h
labels:
severity: warning
annotations:
description: pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on container {{ $labels.container}} has been in waiting state for longer than 1 hour.
description: 'pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on container {{ $labels.container}} has been in waiting state for longer than 1 hour. (reason: "{{ $labels.reason }}").'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontainerwaiting
summary: Pod container waiting longer than 1 hour
- alert: "KubeDaemonSetNotScheduled"
Expand Down Expand Up @@ -234,7 +234,7 @@ groups:
summary: Namespace quota has exceeded the limits.
- alert: "CPUThrottlingHigh"
expr: |-
sum(increase(container_cpu_cfs_throttled_periods_total{container!="", }[5m])) by (cluster, container, pod, namespace) / sum(increase(container_cpu_cfs_periods_total{}[5m])) by (cluster, container, pod, namespace) > (25 / 100)
sum(increase(container_cpu_cfs_throttled_periods_total{container!="", job="cadvisor", }[5m])) without (id, metrics_path, name, image, endpoint, job, node) / sum(increase(container_cpu_cfs_periods_total{job="cadvisor", }[5m])) without (id, metrics_path, name, image, endpoint, job, node) > (25 / 100)
for: 15m
labels:
severity: info
Expand Down Expand Up @@ -370,7 +370,7 @@ groups:
rules:
- alert: "KubeClientCertificateExpiration"
expr: |-
apiserver_client_certificate_expiration_seconds_count{job="kube-apiserver"} > 0 and on(cluster, job) histogram_quantile(0.01, sum by (cluster, job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="kube-apiserver"}[5m]))) < 604800
histogram_quantile(0.01, sum without (namespace, service, endpoint) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="kube-apiserver"}[5m]))) < 604800 and on(job, cluster, instance) apiserver_client_certificate_expiration_seconds_count{job="kube-apiserver"} > 0
for: 5m
labels:
severity: warning
Expand All @@ -380,7 +380,7 @@ groups:
summary: Client certificate is about to expire.
- alert: "KubeClientCertificateExpiration"
expr: |-
apiserver_client_certificate_expiration_seconds_count{job="kube-apiserver"} > 0 and on(cluster, job) histogram_quantile(0.01, sum by (cluster, job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="kube-apiserver"}[5m]))) < 86400
histogram_quantile(0.01, sum without (namespace, service, endpoint) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="kube-apiserver"}[5m]))) < 86400 and on(job, cluster, instance) apiserver_client_certificate_expiration_seconds_count{job="kube-apiserver"} > 0
for: 5m
labels:
severity: critical
Expand Down
10 changes: 5 additions & 5 deletions docs/default/prometheusAlerts.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,13 +122,13 @@
},
{
"alert": "KubeContainerWaiting",
"expr": "sum by (namespace, pod, container, cluster) (kube_pod_container_status_waiting_reason{job=\"kube-state-metrics\"}) > 0",
"expr": "kube_pod_container_status_waiting_reason{reason!=\"CrashLoopBackOff\", job=\"kube-state-metrics\"} > 0",
"for": "1h",
"labels": {
"severity": "warning"
},
"annotations": {
"description": "pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on container {{ $labels.container}} has been in waiting state for longer than 1 hour.",
"description": "pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on container {{ $labels.container}} has been in waiting state for longer than 1 hour. (reason: \"{{ $labels.reason }}\").",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontainerwaiting",
"summary": "Pod container waiting longer than 1 hour"
}
Expand Down Expand Up @@ -308,7 +308,7 @@
},
{
"alert": "CPUThrottlingHigh",
"expr": "sum(increase(container_cpu_cfs_throttled_periods_total{container!=\"\", }[5m])) by (cluster, container, pod, namespace) / sum(increase(container_cpu_cfs_periods_total{}[5m])) by (cluster, container, pod, namespace) > (25 / 100)",
"expr": "sum(increase(container_cpu_cfs_throttled_periods_total{container!=\"\", job=\"cadvisor\", }[5m])) without (id, metrics_path, name, image, endpoint, job, node) / sum(increase(container_cpu_cfs_periods_total{job=\"cadvisor\", }[5m])) without (id, metrics_path, name, image, endpoint, job, node) > (25 / 100)",
"for": "15m",
"labels": {
"severity": "info"
Expand Down Expand Up @@ -492,7 +492,7 @@
"rules": [
{
"alert": "KubeClientCertificateExpiration",
"expr": "apiserver_client_certificate_expiration_seconds_count{job=\"kube-apiserver\"} > 0 and on(cluster, job) histogram_quantile(0.01, sum by (cluster, job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"kube-apiserver\"}[5m]))) < 604800",
"expr": "histogram_quantile(0.01, sum without (namespace, service, endpoint) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"kube-apiserver\"}[5m]))) < 604800 and on(job, cluster, instance) apiserver_client_certificate_expiration_seconds_count{job=\"kube-apiserver\"} > 0",
"for": "5m",
"labels": {
"severity": "warning"
Expand All @@ -505,7 +505,7 @@
},
{
"alert": "KubeClientCertificateExpiration",
"expr": "apiserver_client_certificate_expiration_seconds_count{job=\"kube-apiserver\"} > 0 and on(cluster, job) histogram_quantile(0.01, sum by (cluster, job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"kube-apiserver\"}[5m]))) < 86400",
"expr": "histogram_quantile(0.01, sum without (namespace, service, endpoint) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"kube-apiserver\"}[5m]))) < 86400 and on(job, cluster, instance) apiserver_client_certificate_expiration_seconds_count{job=\"kube-apiserver\"} > 0",
"for": "5m",
"labels": {
"severity": "critical"
Expand Down
10 changes: 5 additions & 5 deletions docs/default/prometheusAlerts.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,12 +93,12 @@ groups:
summary: DaemonSet rollout is stuck.
- alert: "KubeContainerWaiting"
expr: |-
sum by (namespace, pod, container, cluster) (kube_pod_container_status_waiting_reason{job="kube-state-metrics"}) > 0
kube_pod_container_status_waiting_reason{reason!="CrashLoopBackOff", job="kube-state-metrics"} > 0
for: 1h
labels:
severity: warning
annotations:
description: pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on container {{ $labels.container}} has been in waiting state for longer than 1 hour.
description: 'pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on container {{ $labels.container}} has been in waiting state for longer than 1 hour. (reason: "{{ $labels.reason }}").'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontainerwaiting
summary: Pod container waiting longer than 1 hour
- alert: "KubeDaemonSetNotScheduled"
Expand Down Expand Up @@ -234,7 +234,7 @@ groups:
summary: Namespace quota has exceeded the limits.
- alert: "CPUThrottlingHigh"
expr: |-
sum(increase(container_cpu_cfs_throttled_periods_total{container!="", }[5m])) by (cluster, container, pod, namespace) / sum(increase(container_cpu_cfs_periods_total{}[5m])) by (cluster, container, pod, namespace) > (25 / 100)
sum(increase(container_cpu_cfs_throttled_periods_total{container!="", job="cadvisor", }[5m])) without (id, metrics_path, name, image, endpoint, job, node) / sum(increase(container_cpu_cfs_periods_total{job="cadvisor", }[5m])) without (id, metrics_path, name, image, endpoint, job, node) > (25 / 100)
for: 15m
labels:
severity: info
Expand Down Expand Up @@ -370,7 +370,7 @@ groups:
rules:
- alert: "KubeClientCertificateExpiration"
expr: |-
apiserver_client_certificate_expiration_seconds_count{job="kube-apiserver"} > 0 and on(cluster, job) histogram_quantile(0.01, sum by (cluster, job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="kube-apiserver"}[5m]))) < 604800
histogram_quantile(0.01, sum without (namespace, service, endpoint) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="kube-apiserver"}[5m]))) < 604800 and on(job, cluster, instance) apiserver_client_certificate_expiration_seconds_count{job="kube-apiserver"} > 0
for: 5m
labels:
severity: warning
Expand All @@ -380,7 +380,7 @@ groups:
summary: Client certificate is about to expire.
- alert: "KubeClientCertificateExpiration"
expr: |-
apiserver_client_certificate_expiration_seconds_count{job="kube-apiserver"} > 0 and on(cluster, job) histogram_quantile(0.01, sum by (cluster, job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="kube-apiserver"}[5m]))) < 86400
histogram_quantile(0.01, sum without (namespace, service, endpoint) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="kube-apiserver"}[5m]))) < 86400 and on(job, cluster, instance) apiserver_client_certificate_expiration_seconds_count{job="kube-apiserver"} > 0
for: 5m
labels:
severity: critical
Expand Down
10 changes: 5 additions & 5 deletions docs/multicluster/prometheusAlerts.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,13 +122,13 @@
},
{
"alert": "KubeContainerWaiting",
"expr": "sum by (namespace, pod, container, cluster) (kube_pod_container_status_waiting_reason{job=\"kube-state-metrics\"}) > 0",
"expr": "kube_pod_container_status_waiting_reason{reason!=\"CrashLoopBackOff\", job=\"kube-state-metrics\"} > 0",
"for": "1h",
"labels": {
"severity": "warning"
},
"annotations": {
"description": "pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on container {{ $labels.container}} has been in waiting state for longer than 1 hour.",
"description": "pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on container {{ $labels.container}} has been in waiting state for longer than 1 hour. (reason: \"{{ $labels.reason }}\").",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontainerwaiting",
"summary": "Pod container waiting longer than 1 hour"
}
Expand Down Expand Up @@ -308,7 +308,7 @@
},
{
"alert": "CPUThrottlingHigh",
"expr": "sum(increase(container_cpu_cfs_throttled_periods_total{container!=\"\", }[5m])) by (cluster, container, pod, namespace) / sum(increase(container_cpu_cfs_periods_total{}[5m])) by (cluster, container, pod, namespace) > (25 / 100)",
"expr": "sum(increase(container_cpu_cfs_throttled_periods_total{container!=\"\", job=\"cadvisor\", }[5m])) without (id, metrics_path, name, image, endpoint, job, node) / sum(increase(container_cpu_cfs_periods_total{job=\"cadvisor\", }[5m])) without (id, metrics_path, name, image, endpoint, job, node) > (25 / 100)",
"for": "15m",
"labels": {
"severity": "info"
Expand Down Expand Up @@ -492,7 +492,7 @@
"rules": [
{
"alert": "KubeClientCertificateExpiration",
"expr": "apiserver_client_certificate_expiration_seconds_count{job=\"kube-apiserver\"} > 0 and on(cluster, job) histogram_quantile(0.01, sum by (cluster, job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"kube-apiserver\"}[5m]))) < 604800",
"expr": "histogram_quantile(0.01, sum without (namespace, service, endpoint) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"kube-apiserver\"}[5m]))) < 604800 and on(job, cluster, instance) apiserver_client_certificate_expiration_seconds_count{job=\"kube-apiserver\"} > 0",
"for": "5m",
"labels": {
"severity": "warning"
Expand All @@ -505,7 +505,7 @@
},
{
"alert": "KubeClientCertificateExpiration",
"expr": "apiserver_client_certificate_expiration_seconds_count{job=\"kube-apiserver\"} > 0 and on(cluster, job) histogram_quantile(0.01, sum by (cluster, job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"kube-apiserver\"}[5m]))) < 86400",
"expr": "histogram_quantile(0.01, sum without (namespace, service, endpoint) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"kube-apiserver\"}[5m]))) < 86400 and on(job, cluster, instance) apiserver_client_certificate_expiration_seconds_count{job=\"kube-apiserver\"} > 0",
"for": "5m",
"labels": {
"severity": "critical"
Expand Down
10 changes: 5 additions & 5 deletions docs/multicluster/prometheusAlerts.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,12 +93,12 @@ groups:
summary: DaemonSet rollout is stuck.
- alert: "KubeContainerWaiting"
expr: |-
sum by (namespace, pod, container, cluster) (kube_pod_container_status_waiting_reason{job="kube-state-metrics"}) > 0
kube_pod_container_status_waiting_reason{reason!="CrashLoopBackOff", job="kube-state-metrics"} > 0
for: 1h
labels:
severity: warning
annotations:
description: pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on container {{ $labels.container}} has been in waiting state for longer than 1 hour.
description: 'pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on container {{ $labels.container}} has been in waiting state for longer than 1 hour. (reason: "{{ $labels.reason }}").'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontainerwaiting
summary: Pod container waiting longer than 1 hour
- alert: "KubeDaemonSetNotScheduled"
Expand Down Expand Up @@ -234,7 +234,7 @@ groups:
summary: Namespace quota has exceeded the limits.
- alert: "CPUThrottlingHigh"
expr: |-
sum(increase(container_cpu_cfs_throttled_periods_total{container!="", }[5m])) by (cluster, container, pod, namespace) / sum(increase(container_cpu_cfs_periods_total{}[5m])) by (cluster, container, pod, namespace) > (25 / 100)
sum(increase(container_cpu_cfs_throttled_periods_total{container!="", job="cadvisor", }[5m])) without (id, metrics_path, name, image, endpoint, job, node) / sum(increase(container_cpu_cfs_periods_total{job="cadvisor", }[5m])) without (id, metrics_path, name, image, endpoint, job, node) > (25 / 100)
for: 15m
labels:
severity: info
Expand Down Expand Up @@ -370,7 +370,7 @@ groups:
rules:
- alert: "KubeClientCertificateExpiration"
expr: |-
apiserver_client_certificate_expiration_seconds_count{job="kube-apiserver"} > 0 and on(cluster, job) histogram_quantile(0.01, sum by (cluster, job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="kube-apiserver"}[5m]))) < 604800
histogram_quantile(0.01, sum without (namespace, service, endpoint) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="kube-apiserver"}[5m]))) < 604800 and on(job, cluster, instance) apiserver_client_certificate_expiration_seconds_count{job="kube-apiserver"} > 0
for: 5m
labels:
severity: warning
Expand All @@ -380,7 +380,7 @@ groups:
summary: Client certificate is about to expire.
- alert: "KubeClientCertificateExpiration"
expr: |-
apiserver_client_certificate_expiration_seconds_count{job="kube-apiserver"} > 0 and on(cluster, job) histogram_quantile(0.01, sum by (cluster, job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="kube-apiserver"}[5m]))) < 86400
histogram_quantile(0.01, sum without (namespace, service, endpoint) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="kube-apiserver"}[5m]))) < 86400 and on(job, cluster, instance) apiserver_client_certificate_expiration_seconds_count{job="kube-apiserver"} > 0
for: 5m
labels:
severity: critical
Expand Down
2 changes: 1 addition & 1 deletion jsonnetfile.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
"subdir": ""
}
},
"version": "c70f03daec5d7578ef697c9f5b93ea88a41fe0d7"
"version": "bdbf7f45cedf37d07567be7519fa4139043f9335"
}
],
"legacyImports": true,
Expand Down
Loading
Loading