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

regenerate

Browse Source
This commit is contained in:
paulfantom
2021-01-15 11:58:04 +01:00
parent d4c48539a0
commit 092b22d62b
11 changed files with 1479 additions and 1413 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
README.md
View File

@@ -217,25 +217,30 @@ local kp =
// (import 'kube-prometheus/kube-prometheus-custom-metrics.libsonnet') +
// (import 'kube-prometheus/kube-prometheus-external-metrics.libsonnet') +
{
_config+:: {
namespace: 'monitoring',
values+:: {
common+: {
namespace: 'monitoring',
},
},
};
{ ['setup/0namespace-' + name]: kp.kubePrometheus[name] for name in std.objectFields(kp.kubePrometheus) } +
{ 'setup/0namespace-namespace': kp.kubePrometheus.namespace } +
{
['setup/prometheus-operator-' + name]: kp.prometheusOperator[name]
for name in std.filter((function(name) name != 'serviceMonitor'), std.objectFields(kp.prometheusOperator))
for name in std.filter((function(name) name != 'serviceMonitor' && name != 'prometheusRule'), std.objectFields(kp.prometheusOperator))
} +
// serviceMonitor is separated so that it can be created after the CRDs are ready
// serviceMonitor and prometheusRule are separated so that they can be created after the CRDs are ready
{ 'prometheus-operator-serviceMonitor': kp.prometheusOperator.serviceMonitor } +
{ 'prometheus-operator-prometheusRule': kp.prometheusOperator.prometheusRule } +
{ 'kube-prometheus-prometheusRule': kp.kubePrometheus.prometheusRule } +
{ ['node-exporter-' + name]: kp.nodeExporter[name] for name in std.objectFields(kp.nodeExporter) } +
{ ['blackbox-exporter-' + name]: kp.blackboxExporter[name] for name in std.objectFields(kp.blackboxExporter) } +
{ ['kube-state-metrics-' + name]: kp.kubeStateMetrics[name] for name in std.objectFields(kp.kubeStateMetrics) } +
{ ['alertmanager-' + name]: kp.alertmanager[name] for name in std.objectFields(kp.alertmanager) } +
{ ['prometheus-' + name]: kp.prometheus[name] for name in std.objectFields(kp.prometheus) } +
{ ['prometheus-adapter-' + name]: kp.prometheusAdapter[name] for name in std.objectFields(kp.prometheusAdapter) } +
{ ['grafana-' + name]: kp.grafana[name] for name in std.objectFields(kp.grafana) }
{ ['grafana-' + name]: kp.grafana[name] for name in std.objectFields(kp.grafana) } +
{ ['kubernetes-' + name]: kp.kubernetesMixin[name] for name in std.objectFields(kp.kubernetesMixin) }
```
And here's the [build.sh](build.sh) script (which uses `vendor/` to render all manifests in a json structure of `{filename: manifest-content}`):

17
docs/developing-prometheus-rules-and-grafana-dashboards.md
View File

@@ -21,25 +21,30 @@ local kp =
// (import 'kube-prometheus/kube-prometheus-custom-metrics.libsonnet') +
// (import 'kube-prometheus/kube-prometheus-external-metrics.libsonnet') +
{
_config+:: {
namespace: 'monitoring',
values+:: {
common+: {
namespace: 'monitoring',
},
},
};
{ ['setup/0namespace-' + name]: kp.kubePrometheus[name] for name in std.objectFields(kp.kubePrometheus) } +
{ 'setup/0namespace-namespace': kp.kubePrometheus.namespace } +
{
['setup/prometheus-operator-' + name]: kp.prometheusOperator[name]
for name in std.filter((function(name) name != 'serviceMonitor'), std.objectFields(kp.prometheusOperator))
for name in std.filter((function(name) name != 'serviceMonitor' && name != 'prometheusRule'), std.objectFields(kp.prometheusOperator))
} +
// serviceMonitor is separated so that it can be created after the CRDs are ready
// serviceMonitor and prometheusRule are separated so that they can be created after the CRDs are ready
{ 'prometheus-operator-serviceMonitor': kp.prometheusOperator.serviceMonitor } +
{ 'prometheus-operator-prometheusRule': kp.prometheusOperator.prometheusRule } +
{ 'kube-prometheus-prometheusRule': kp.kubePrometheus.prometheusRule } +
{ ['node-exporter-' + name]: kp.nodeExporter[name] for name in std.objectFields(kp.nodeExporter) } +
{ ['blackbox-exporter-' + name]: kp.blackboxExporter[name] for name in std.objectFields(kp.blackboxExporter) } +
{ ['kube-state-metrics-' + name]: kp.kubeStateMetrics[name] for name in std.objectFields(kp.kubeStateMetrics) } +
{ ['alertmanager-' + name]: kp.alertmanager[name] for name in std.objectFields(kp.alertmanager) } +
{ ['prometheus-' + name]: kp.prometheus[name] for name in std.objectFields(kp.prometheus) } +
{ ['prometheus-adapter-' + name]: kp.prometheusAdapter[name] for name in std.objectFields(kp.prometheusAdapter) } +
{ ['grafana-' + name]: kp.grafana[name] for name in std.objectFields(kp.grafana) }
{ ['grafana-' + name]: kp.grafana[name] for name in std.objectFields(kp.grafana) } +
{ ['kubernetes-' + name]: kp.kubernetesMixin[name] for name in std.objectFields(kp.kubernetesMixin) }
```
## Prometheus rules

8
kustomization.yaml
View File

@@ -2,6 +2,7 @@ apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization
resources:
- ./manifests/alertmanager-alertmanager.yaml
- ./manifests/alertmanager-prometheusRule.yaml
- ./manifests/alertmanager-secret.yaml
- ./manifests/alertmanager-service.yaml
- ./manifests/alertmanager-serviceAccount.yaml
@@ -20,15 +21,19 @@ resources:
- ./manifests/grafana-service.yaml
- ./manifests/grafana-serviceAccount.yaml
- ./manifests/grafana-serviceMonitor.yaml
- ./manifests/kube-prometheus-prometheusRule.yaml
- ./manifests/kube-state-metrics-clusterRole.yaml
- ./manifests/kube-state-metrics-clusterRoleBinding.yaml
- ./manifests/kube-state-metrics-deployment.yaml
- ./manifests/kube-state-metrics-prometheusRule.yaml
- ./manifests/kube-state-metrics-service.yaml
- ./manifests/kube-state-metrics-serviceAccount.yaml
- ./manifests/kube-state-metrics-serviceMonitor.yaml
- ./manifests/kubernetes-prometheusRule.yaml
- ./manifests/node-exporter-clusterRole.yaml
- ./manifests/node-exporter-clusterRoleBinding.yaml
- ./manifests/node-exporter-daemonset.yaml
- ./manifests/node-exporter-prometheusRule.yaml
- ./manifests/node-exporter-service.yaml
- ./manifests/node-exporter-serviceAccount.yaml
- ./manifests/node-exporter-serviceMonitor.yaml
@@ -46,13 +51,14 @@ resources:
- ./manifests/prometheus-adapter-serviceMonitor.yaml
- ./manifests/prometheus-clusterRole.yaml
- ./manifests/prometheus-clusterRoleBinding.yaml
- ./manifests/prometheus-operator-prometheusRule.yaml
- ./manifests/prometheus-operator-serviceMonitor.yaml
- ./manifests/prometheus-prometheus.yaml
- ./manifests/prometheus-prometheusRule.yaml
- ./manifests/prometheus-roleBindingConfig.yaml
- ./manifests/prometheus-roleBindingSpecificNamespaces.yaml
- ./manifests/prometheus-roleConfig.yaml
- ./manifests/prometheus-roleSpecificNamespaces.yaml
- ./manifests/prometheus-rules.yaml
- ./manifests/prometheus-service.yaml
- ./manifests/prometheus-serviceAccount.yaml
- ./manifests/prometheus-serviceMonitor.yaml

116
manifests/alertmanager-prometheusRule.yaml Normal file
View File

@@ -0,0 +1,116 @@
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
labels:
app.kubernetes.io/component: alert-router
app.kubernetes.io/name: alertmanager
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 0.21.0
prometheus: k8s
role: alert-rules
name: main-rules
namespace: monitoring
spec:
groups:
- name: alertmanager.rules
rules:
- alert: AlertmanagerFailedReload
annotations:
description: Configuration has failed to load for {{ $labels.namespace }}/{{ $labels.pod}}.
summary: Reloading an Alertmanager configuration has failed.
expr: |
# Without max_over_time, failed scrapes could create false negatives, see
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
max_over_time(alertmanager_config_last_reload_successful{job="alertmanager-main",namespace="monitoring"}[5m]) == 0
for: 10m
labels:
severity: critical
- alert: AlertmanagerMembersInconsistent
annotations:
description: Alertmanager {{ $labels.namespace }}/{{ $labels.pod}} has only found {{ $value }} members of the {{$labels.job}} cluster.
summary: A member of an Alertmanager cluster has not found all other cluster members.
expr: |
# Without max_over_time, failed scrapes could create false negatives, see
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
max_over_time(alertmanager_cluster_members{job="alertmanager-main",namespace="monitoring"}[5m])
< on (namespace,service) group_left
count by (namespace,service) (max_over_time(alertmanager_cluster_members{job="alertmanager-main",namespace="monitoring"}[5m]))
for: 10m
labels:
severity: critical
- alert: AlertmanagerFailedToSendAlerts
annotations:
description: Alertmanager {{ $labels.namespace }}/{{ $labels.pod}} failed to send {{ $value | humanizePercentage }} of notifications to {{ $labels.integration }}.
summary: An Alertmanager instance failed to send notifications.
expr: |
(
rate(alertmanager_notifications_failed_total{job="alertmanager-main",namespace="monitoring"}[5m])
/
rate(alertmanager_notifications_total{job="alertmanager-main",namespace="monitoring"}[5m])
)
> 0.01
for: 5m
labels:
severity: warning
- alert: AlertmanagerClusterFailedToSendAlerts
annotations:
description: The minimum notification failure rate to {{ $labels.integration }} sent from any instance in the {{$labels.job}} cluster is {{ $value | humanizePercentage }}.
summary: All Alertmanager instances in a cluster failed to send notifications.
expr: |
min by (namespace,service) (
rate(alertmanager_notifications_failed_total{job="alertmanager-main",namespace="monitoring"}[5m])
/
rate(alertmanager_notifications_total{job="alertmanager-main",namespace="monitoring"}[5m])
)
> 0.01
for: 5m
labels:
severity: critical
- alert: AlertmanagerConfigInconsistent
annotations:
description: Alertmanager instances within the {{$labels.job}} cluster have different configurations.
summary: Alertmanager instances within the same cluster have different configurations.
expr: |
count by (namespace,service) (
count_values by (namespace,service) ("config_hash", alertmanager_config_hash{job="alertmanager-main",namespace="monitoring"})
)
!= 1
for: 20m
labels:
severity: critical
- alert: AlertmanagerClusterDown
annotations:
description: '{{ $value | humanizePercentage }} of Alertmanager instances within the {{$labels.job}} cluster have been up for less than half of the last 5m.'
summary: Half or more of the Alertmanager instances within the same cluster are down.
expr: |
(
count by (namespace,service) (
avg_over_time(up{job="alertmanager-main",namespace="monitoring"}[5m]) < 0.5
)
/
count by (namespace,service) (
up{job="alertmanager-main",namespace="monitoring"}
)
)
>= 0.5
for: 5m
labels:
severity: critical
- alert: AlertmanagerClusterCrashlooping
annotations:
description: '{{ $value | humanizePercentage }} of Alertmanager instances within the {{$labels.job}} cluster have restarted at least 5 times in the last 10m.'
summary: Half or more of the Alertmanager instances within the same cluster are crashlooping.
expr: |
(
count by (namespace,service) (
changes(process_start_time_seconds{job="alertmanager-main",namespace="monitoring"}[10m]) > 4
)
/
count by (namespace,service) (
up{job="alertmanager-main",namespace="monitoring"}
)
)
>= 0.5
for: 5m
labels:
severity: critical

2
manifests/grafana-deployment.yaml
View File

@@ -13,7 +13,7 @@ spec:
template:
metadata:
annotations:
checksum/grafana-dashboards: a9e19e1ab605dc374f30edda771e6917
checksum/grafana-dashboards: b02ae450c84445cbaca8c685eefaec6c
checksum/grafana-datasources: 48faab41f579fc8efde6034391496f6a
labels:
app: grafana

63
manifests/kube-prometheus-prometheusRule.yaml Normal file
View File

@@ -0,0 +1,63 @@
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
labels:
app.kubernetes.io/component: exporter
app.kubernetes.io/name: kube-prometheus
app.kubernetes.io/part-of: kube-prometheus
prometheus: k8s
role: alert-rules
name: kube-prometheus-rules
namespace: monitoring
spec:
groups:
- name: general.rules
rules:
- alert: TargetDown
annotations:
message: '{{ printf "%.4g" $value }}% of the {{ $labels.job }}/{{ $labels.service }} targets in {{ $labels.namespace }} namespace are down.'
expr: 100 * (count(up == 0) BY (job, namespace, service) / count(up) BY (job, namespace, service)) > 10
for: 10m
labels:
severity: warning
- alert: Watchdog
annotations:
message: |
This is an alert meant to ensure that the entire alerting pipeline is functional.
This alert is always firing, therefore it should always be firing in Alertmanager
and always fire against a receiver. There are integrations with various notification
mechanisms that send a notification when this alert is not firing. For example the
"DeadMansSnitch" integration in PagerDuty.
expr: vector(1)
labels:
severity: none
- name: node-network
rules:
- alert: NodeNetworkInterfaceFlapping
annotations:
message: Network interface "{{ $labels.device }}" changing it's up status often on node-exporter {{ $labels.namespace }}/{{ $labels.pod }}"
expr: |
changes(node_network_up{job="node-exporter",device!~"veth.+"}[2m]) > 2
for: 2m
labels:
severity: warning
- name: kube-prometheus-node-recording.rules
rules:
- expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[3m])) BY (instance)
record: instance:node_cpu:rate:sum
- expr: sum(rate(node_network_receive_bytes_total[3m])) BY (instance)
record: instance:node_network_receive_bytes:rate:sum
- expr: sum(rate(node_network_transmit_bytes_total[3m])) BY (instance)
record: instance:node_network_transmit_bytes:rate:sum
- expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m])) WITHOUT (cpu, mode) / ON(instance) GROUP_LEFT() count(sum(node_cpu_seconds_total) BY (instance, cpu)) BY (instance)
record: instance:node_cpu:ratio
- expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m]))
record: cluster:node_cpu:sum_rate5m
- expr: cluster:node_cpu_seconds_total:rate5m / count(sum(node_cpu_seconds_total) BY (instance, cpu))
record: cluster:node_cpu:ratio
- name: kube-prometheus-general.rules
rules:
- expr: count without(instance, pod, node) (up == 1)
record: count:up1
- expr: count without(instance, pod, node) (up == 0)
record: count:up0

40
manifests/kube-state-metrics-prometheusRule.yaml Normal file
View File

@@ -0,0 +1,40 @@
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
labels:
app.kubernetes.io/component: exporter
app.kubernetes.io/name: kube-state-metrics
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 1.9.7
prometheus: k8s
role: alert-rules
name: kube-state-metrics-rules
namespace: monitoring
spec:
groups:
- name: kube-state-metrics
rules:
- alert: KubeStateMetricsListErrors
annotations:
description: kube-state-metrics is experiencing errors at an elevated rate in list operations. This is likely causing it to not be able to expose metrics about Kubernetes objects correctly or at all.
summary: kube-state-metrics is experiencing errors in list operations.
expr: |
(sum(rate(kube_state_metrics_list_total{job="kube-state-metrics",result="error"}[5m]))
/
sum(rate(kube_state_metrics_list_total{job="kube-state-metrics"}[5m])))
> 0.01
for: 15m
labels:
severity: critical
- alert: KubeStateMetricsWatchErrors
annotations:
description: kube-state-metrics is experiencing errors at an elevated rate in watch operations. This is likely causing it to not be able to expose metrics about Kubernetes objects correctly or at all.
summary: kube-state-metrics is experiencing errors in watch operations.
expr: |
(sum(rate(kube_state_metrics_watch_total{job="kube-state-metrics",result="error"}[5m]))
/
sum(rate(kube_state_metrics_watch_total{job="kube-state-metrics"}[5m])))
> 0.01
for: 15m
labels:
severity: critical

2071
manifests/prometheus-rules.yaml → manifests/kubernetes-prometheusRule.yaml
View File

File diff suppressed because it is too large Load Diff

266
manifests/node-exporter-prometheusRule.yaml Normal file
View File

@@ -0,0 +1,266 @@
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
labels:
app.kubernetes.io/component: exporter
app.kubernetes.io/name: node-exporter
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 1.0.1
prometheus: k8s
role: alert-rules
name: node-exporter-rules
namespace: monitoring
spec:
groups:
- name: node-exporter
rules:
- alert: NodeFilesystemSpaceFillingUp
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left and is filling up.
summary: Filesystem is predicted to run out of space within the next 24 hours.
expr: |
(
node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 40
and
predict_linear(node_filesystem_avail_bytes{job="node-exporter",fstype!=""}[6h], 24*60*60) < 0
and
node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
)
for: 1h
labels:
severity: warning
- alert: NodeFilesystemSpaceFillingUp
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left and is filling up fast.
summary: Filesystem is predicted to run out of space within the next 4 hours.
expr: |
(
node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 15
and
predict_linear(node_filesystem_avail_bytes{job="node-exporter",fstype!=""}[6h], 4*60*60) < 0
and
node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
)
for: 1h
labels:
severity: critical
- alert: NodeFilesystemAlmostOutOfSpace
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left.
summary: Filesystem has less than 5% space left.
expr: |
(
node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 5
and
node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
)
for: 1h
labels:
severity: warning
- alert: NodeFilesystemAlmostOutOfSpace
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left.
summary: Filesystem has less than 3% space left.
expr: |
(
node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 3
and
node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
)
for: 1h
labels:
severity: critical
- alert: NodeFilesystemFilesFillingUp
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left and is filling up.
summary: Filesystem is predicted to run out of inodes within the next 24 hours.
expr: |
(
node_filesystem_files_free{job="node-exporter",fstype!=""} / node_filesystem_files{job="node-exporter",fstype!=""} * 100 < 40
and
predict_linear(node_filesystem_files_free{job="node-exporter",fstype!=""}[6h], 24*60*60) < 0
and
node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
)
for: 1h
labels:
severity: warning
- alert: NodeFilesystemFilesFillingUp
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left and is filling up fast.
summary: Filesystem is predicted to run out of inodes within the next 4 hours.
expr: |
(
node_filesystem_files_free{job="node-exporter",fstype!=""} / node_filesystem_files{job="node-exporter",fstype!=""} * 100 < 20
and
predict_linear(node_filesystem_files_free{job="node-exporter",fstype!=""}[6h], 4*60*60) < 0
and
node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
)
for: 1h
labels:
severity: critical
- alert: NodeFilesystemAlmostOutOfFiles
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left.
summary: Filesystem has less than 5% inodes left.
expr: |
(
node_filesystem_files_free{job="node-exporter",fstype!=""} / node_filesystem_files{job="node-exporter",fstype!=""} * 100 < 5
and
node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
)
for: 1h
labels:
severity: warning
- alert: NodeFilesystemAlmostOutOfFiles
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left.
summary: Filesystem has less than 3% inodes left.
expr: |
(
node_filesystem_files_free{job="node-exporter",fstype!=""} / node_filesystem_files{job="node-exporter",fstype!=""} * 100 < 3
and
node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
)
for: 1h
labels:
severity: critical
- alert: NodeNetworkReceiveErrs
annotations:
description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} receive errors in the last two minutes.'
summary: Network interface is reporting many receive errors.
expr: |
rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01
for: 1h
labels:
severity: warning
- alert: NodeNetworkTransmitErrs
annotations:
description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} transmit errors in the last two minutes.'
summary: Network interface is reporting many transmit errors.
expr: |
rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01
for: 1h
labels:
severity: warning
- alert: NodeHighNumberConntrackEntriesUsed
annotations:
description: '{{ $value | humanizePercentage }} of conntrack entries are used.'
summary: Number of conntrack are getting close to the limit.
expr: |
(node_nf_conntrack_entries / node_nf_conntrack_entries_limit) > 0.75
labels:
severity: warning
- alert: NodeTextFileCollectorScrapeError
annotations:
description: Node Exporter text file collector failed to scrape.
summary: Node Exporter text file collector failed to scrape.
expr: |
node_textfile_scrape_error{job="node-exporter"} == 1
labels:
severity: warning
- alert: NodeClockSkewDetected
annotations:
message: Clock on {{ $labels.instance }} is out of sync by more than 300s. Ensure NTP is configured correctly on this host.
summary: Clock skew detected.
expr: |
(
node_timex_offset_seconds > 0.05
and
deriv(node_timex_offset_seconds[5m]) >= 0
)
or
(
node_timex_offset_seconds < -0.05
and
deriv(node_timex_offset_seconds[5m]) <= 0
)
for: 10m
labels:
severity: warning
- alert: NodeClockNotSynchronising
annotations:
message: Clock on {{ $labels.instance }} is not synchronising. Ensure NTP is configured on this host.
summary: Clock not synchronising.
expr: |
min_over_time(node_timex_sync_status[5m]) == 0
and
node_timex_maxerror_seconds >= 16
for: 10m
labels:
severity: warning
- alert: NodeRAIDDegraded
annotations:
description: RAID array '{{ $labels.device }}' on {{ $labels.instance }} is in degraded state due to one or more disks failures. Number of spare drives is insufficient to fix issue automatically.
summary: RAID Array is degraded
expr: |
node_md_disks_required - ignoring (state) (node_md_disks{state="active"}) > 0
for: 15m
labels:
severity: critical
- alert: NodeRAIDDiskFailure
annotations:
description: At least one device in RAID array on {{ $labels.instance }} failed. Array '{{ $labels.device }}' needs attention and possibly a disk swap.
summary: Failed device in RAID array
expr: |
node_md_disks{state="fail"} > 0
labels:
severity: warning
- name: node-exporter.rules
rules:
- expr: |
count without (cpu) (
count without (mode) (
node_cpu_seconds_total{job="node-exporter"}
)
)
record: instance:node_num_cpu:sum
- expr: |
1 - avg without (cpu, mode) (
rate(node_cpu_seconds_total{job="node-exporter", mode="idle"}[1m])
)
record: instance:node_cpu_utilisation:rate1m
- expr: |
(
node_load1{job="node-exporter"}
/
instance:node_num_cpu:sum{job="node-exporter"}
)
record: instance:node_load1_per_cpu:ratio
- expr: |
1 - (
node_memory_MemAvailable_bytes{job="node-exporter"}
/
node_memory_MemTotal_bytes{job="node-exporter"}
)
record: instance:node_memory_utilisation:ratio
- expr: |
rate(node_vmstat_pgmajfault{job="node-exporter"}[1m])
record: instance:node_vmstat_pgmajfault:rate1m
- expr: |
rate(node_disk_io_time_seconds_total{job="node-exporter", device=~"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+"}[1m])
record: instance_device:node_disk_io_time_seconds:rate1m
- expr: |
rate(node_disk_io_time_weighted_seconds_total{job="node-exporter", device=~"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+"}[1m])
record: instance_device:node_disk_io_time_weighted_seconds:rate1m
- expr: |
sum without (device) (
rate(node_network_receive_bytes_total{job="node-exporter", device!="lo"}[1m])
)
record: instance:node_network_receive_bytes_excluding_lo:rate1m
- expr: |
sum without (device) (
rate(node_network_transmit_bytes_total{job="node-exporter", device!="lo"}[1m])
)
record: instance:node_network_transmit_bytes_excluding_lo:rate1m
- expr: |
sum without (device) (
rate(node_network_receive_drop_total{job="node-exporter", device!="lo"}[1m])
)
record: instance:node_network_receive_drop_excluding_lo:rate1m
- expr: |
sum without (device) (
rate(node_network_transmit_drop_total{job="node-exporter", device!="lo"}[1m])
)
record: instance:node_network_transmit_drop_excluding_lo:rate1m

79
manifests/prometheus-operator-prometheusRule.yaml Normal file
View File

@@ -0,0 +1,79 @@
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
labels:
app.kubernetes.io/component: controller
app.kubernetes.io/name: prometheus-operator
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 0.45.0
prometheus: k8s
role: alert-rules
name: prometheus-operator-rules
namespace: monitoring
spec:
groups:
- name: prometheus-operator
rules:
- alert: PrometheusOperatorListErrors
annotations:
description: Errors while performing List operations in controller {{$labels.controller}} in {{$labels.namespace}} namespace.
summary: Errors while performing list operations in controller.
expr: |
(sum by (controller,namespace) (rate(prometheus_operator_list_operations_failed_total{job="prometheus-operator",namespace="monitoring"}[10m])) / sum by (controller,namespace) (rate(prometheus_operator_list_operations_total{job="prometheus-operator",namespace="monitoring"}[10m]))) > 0.4
for: 15m
labels:
severity: warning
- alert: PrometheusOperatorWatchErrors
annotations:
description: Errors while performing watch operations in controller {{$labels.controller}} in {{$labels.namespace}} namespace.
summary: Errors while performing watch operations in controller.
expr: |
(sum by (controller,namespace) (rate(prometheus_operator_watch_operations_failed_total{job="prometheus-operator",namespace="monitoring"}[10m])) / sum by (controller,namespace) (rate(prometheus_operator_watch_operations_total{job="prometheus-operator",namespace="monitoring"}[10m]))) > 0.4
for: 15m
labels:
severity: warning
- alert: PrometheusOperatorSyncFailed
annotations:
description: Controller {{ $labels.controller }} in {{ $labels.namespace }} namespace fails to reconcile {{ $value }} objects.
summary: Last controller reconciliation failed
expr: |
min_over_time(prometheus_operator_syncs{status="failed",job="prometheus-operator",namespace="monitoring"}[5m]) > 0
for: 10m
labels:
severity: warning
- alert: PrometheusOperatorReconcileErrors
annotations:
description: '{{ $value | humanizePercentage }} of reconciling operations failed for {{ $labels.controller }} controller in {{ $labels.namespace }} namespace.'
summary: Errors while reconciling controller.
expr: |
(sum by (controller,namespace) (rate(prometheus_operator_reconcile_errors_total{job="prometheus-operator",namespace="monitoring"}[5m]))) / (sum by (controller,namespace) (rate(prometheus_operator_reconcile_operations_total{job="prometheus-operator",namespace="monitoring"}[5m]))) > 0.1
for: 10m
labels:
severity: warning
- alert: PrometheusOperatorNodeLookupErrors
annotations:
description: Errors while reconciling Prometheus in {{ $labels.namespace }} Namespace.
summary: Errors while reconciling Prometheus.
expr: |
rate(prometheus_operator_node_address_lookup_errors_total{job="prometheus-operator",namespace="monitoring"}[5m]) > 0.1
for: 10m
labels:
severity: warning
- alert: PrometheusOperatorNotReady
annotations:
description: Prometheus operator in {{ $labels.namespace }} namespace isn't ready to reconcile {{ $labels.controller }} resources.
summary: Prometheus operator not ready
expr: |
min by(namespace, controller) (max_over_time(prometheus_operator_ready{job="prometheus-operator",namespace="monitoring"}[5m]) == 0)
for: 5m
labels:
severity: warning
- alert: PrometheusOperatorRejectedResources
annotations:
description: Prometheus operator in {{ $labels.namespace }} namespace rejected {{ printf "%0.0f" $value }} {{ $labels.controller }}/{{ $labels.resource }} resources.
summary: Resources rejected by Prometheus operator
expr: |
min_over_time(prometheus_operator_managed_resources{state="rejected",job="prometheus-operator",namespace="monitoring"}[5m]) > 0
for: 5m
labels:
severity: warning

213
manifests/prometheus-prometheusRule.yaml Normal file
View File

@@ -0,0 +1,213 @@
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
labels:
app.kubernetes.io/component: prometheus
app.kubernetes.io/name: prometheus
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 2.24.0
prometheus: k8s
role: alert-rules
name: k8s-rules
namespace: monitoring
spec:
groups:
- name: prometheus
rules:
- alert: PrometheusBadConfig
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to reload its configuration.
summary: Failed Prometheus configuration reload.
expr: |
# Without max_over_time, failed scrapes could create false negatives, see
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
max_over_time(prometheus_config_last_reload_successful{job="prometheus-k8s",namespace="monitoring"}[5m]) == 0
for: 10m
labels:
severity: critical
- alert: PrometheusNotificationQueueRunningFull
annotations:
description: Alert notification queue of Prometheus {{$labels.namespace}}/{{$labels.pod}} is running full.
summary: Prometheus alert notification queue predicted to run full in less than 30m.
expr: |
# Without min_over_time, failed scrapes could create false negatives, see
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
(
predict_linear(prometheus_notifications_queue_length{job="prometheus-k8s",namespace="monitoring"}[5m], 60 * 30)
>
min_over_time(prometheus_notifications_queue_capacity{job="prometheus-k8s",namespace="monitoring"}[5m])
)
for: 15m
labels:
severity: warning
- alert: PrometheusErrorSendingAlertsToSomeAlertmanagers
annotations:
description: '{{ printf "%.1f" $value }}% errors while sending alerts from Prometheus {{$labels.namespace}}/{{$labels.pod}} to Alertmanager {{$labels.alertmanager}}.'
summary: Prometheus has encountered more than 1% errors sending alerts to a specific Alertmanager.
expr: |
(
rate(prometheus_notifications_errors_total{job="prometheus-k8s",namespace="monitoring"}[5m])
/
rate(prometheus_notifications_sent_total{job="prometheus-k8s",namespace="monitoring"}[5m])
)
* 100
> 1
for: 15m
labels:
severity: warning
- alert: PrometheusNotConnectedToAlertmanagers
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not connected to any Alertmanagers.
summary: Prometheus is not connected to any Alertmanagers.
expr: |
# Without max_over_time, failed scrapes could create false negatives, see
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
max_over_time(prometheus_notifications_alertmanagers_discovered{job="prometheus-k8s",namespace="monitoring"}[5m]) < 1
for: 10m
labels:
severity: warning
- alert: PrometheusTSDBReloadsFailing
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected {{$value | humanize}} reload failures over the last 3h.
summary: Prometheus has issues reloading blocks from disk.
expr: |
increase(prometheus_tsdb_reloads_failures_total{job="prometheus-k8s",namespace="monitoring"}[3h]) > 0
for: 4h
labels:
severity: warning
- alert: PrometheusTSDBCompactionsFailing
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected {{$value | humanize}} compaction failures over the last 3h.
summary: Prometheus has issues compacting blocks.
expr: |
increase(prometheus_tsdb_compactions_failed_total{job="prometheus-k8s",namespace="monitoring"}[3h]) > 0
for: 4h
labels:
severity: warning
- alert: PrometheusNotIngestingSamples
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not ingesting samples.
summary: Prometheus is not ingesting samples.
expr: |
(
rate(prometheus_tsdb_head_samples_appended_total{job="prometheus-k8s",namespace="monitoring"}[5m]) <= 0
and
(
sum without(scrape_job) (prometheus_target_metadata_cache_entries{job="prometheus-k8s",namespace="monitoring"}) > 0
or
sum without(rule_group) (prometheus_rule_group_rules{job="prometheus-k8s",namespace="monitoring"}) > 0
)
)
for: 10m
labels:
severity: warning
- alert: PrometheusDuplicateTimestamps
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping {{ printf "%.4g" $value }} samples/s with different values but duplicated timestamp.
summary: Prometheus is dropping samples with duplicate timestamps.
expr: |
rate(prometheus_target_scrapes_sample_duplicate_timestamp_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
for: 10m
labels:
severity: warning
- alert: PrometheusOutOfOrderTimestamps
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping {{ printf "%.4g" $value }} samples/s with timestamps arriving out of order.
summary: Prometheus drops samples with out-of-order timestamps.
expr: |
rate(prometheus_target_scrapes_sample_out_of_order_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
for: 10m
labels:
severity: warning
- alert: PrometheusRemoteStorageFailures
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} failed to send {{ printf "%.1f" $value }}% of the samples to {{ $labels.remote_name}}:{{ $labels.url }}
summary: Prometheus fails to send samples to remote storage.
expr: |
(
rate(prometheus_remote_storage_failed_samples_total{job="prometheus-k8s",namespace="monitoring"}[5m])
/
(
rate(prometheus_remote_storage_failed_samples_total{job="prometheus-k8s",namespace="monitoring"}[5m])
+
rate(prometheus_remote_storage_succeeded_samples_total{job="prometheus-k8s",namespace="monitoring"}[5m])
)
)
* 100
> 1
for: 15m
labels:
severity: critical
- alert: PrometheusRemoteWriteBehind
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write is {{ printf "%.1f" $value }}s behind for {{ $labels.remote_name}}:{{ $labels.url }}.
summary: Prometheus remote write is behind.
expr: |
# Without max_over_time, failed scrapes could create false negatives, see
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
(
max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job="prometheus-k8s",namespace="monitoring"}[5m])
- ignoring(remote_name, url) group_right
max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job="prometheus-k8s",namespace="monitoring"}[5m])
)
> 120
for: 15m
labels:
severity: critical
- alert: PrometheusRemoteWriteDesiredShards
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write desired shards calculation wants to run {{ $value }} shards for queue {{ $labels.remote_name}}:{{ $labels.url }}, which is more than the max of {{ printf `prometheus_remote_storage_shards_max{instance="%s",job="prometheus-k8s",namespace="monitoring"}` $labels.instance | query | first | value }}.
summary: Prometheus remote write desired shards calculation wants to run more than configured max shards.
expr: |
# Without max_over_time, failed scrapes could create false negatives, see
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
(
max_over_time(prometheus_remote_storage_shards_desired{job="prometheus-k8s",namespace="monitoring"}[5m])
>
max_over_time(prometheus_remote_storage_shards_max{job="prometheus-k8s",namespace="monitoring"}[5m])
)
for: 15m
labels:
severity: warning
- alert: PrometheusRuleFailures
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to evaluate {{ printf "%.0f" $value }} rules in the last 5m.
summary: Prometheus is failing rule evaluations.
expr: |
increase(prometheus_rule_evaluation_failures_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
for: 15m
labels:
severity: critical
- alert: PrometheusMissingRuleEvaluations
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has missed {{ printf "%.0f" $value }} rule group evaluations in the last 5m.
summary: Prometheus is missing rule evaluations due to slow rule group evaluation.
expr: |
increase(prometheus_rule_group_iterations_missed_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
for: 15m
labels:
severity: warning
- alert: PrometheusTargetLimitHit
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has dropped {{ printf "%.0f" $value }} targets because the number of targets exceeded the configured target_limit.
summary: Prometheus has dropped targets because some scrape configs have exceeded the targets limit.
expr: |
increase(prometheus_target_scrape_pool_exceeded_target_limit_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
for: 15m
labels:
severity: warning
- alert: PrometheusErrorSendingAlertsToAnyAlertmanager
annotations:
description: '{{ printf "%.1f" $value }}% minimum errors while sending alerts from Prometheus {{$labels.namespace}}/{{$labels.pod}} to any Alertmanager.'
summary: Prometheus encounters more than 3% errors sending alerts to any Alertmanager.
expr: |
min without (alertmanager) (
rate(prometheus_notifications_errors_total{job="prometheus-k8s",namespace="monitoring"}[5m])
/
rate(prometheus_notifications_sent_total{job="prometheus-k8s",namespace="monitoring"}[5m])
)
* 100
> 3
for: 15m
labels:
severity: critical