Skip to content

Instantly share code, notes, and snippets.

@yangchuansheng

yangchuansheng/prometheus-rules-others.yaml

Created August 5, 2020 09:22
Show Gist options
  • Star 2 You must be signed in to star a gist
  • Fork 1 You must be signed in to fork a gist
  • Save yangchuansheng/102595fc50436cf4a2ce18744467718c to your computer and use it in GitHub Desktop.
Save yangchuansheng/102595fc50436cf4a2ce18744467718c to your computer and use it in GitHub Desktop.
Download ZIP
prometheus-rules-others.yaml
Raw
prometheus-rules-others.yaml
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
labels:
prometheus: others
role: alert-rules
name: prometheus-others-rules
namespace: monitoring
spec:
groups:
- 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=~"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=~"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
- name: k8s.rules
rules:
- expr: |
sum(rate(container_cpu_usage_seconds_total{job="kubelet", metrics_path="/metrics/cadvisor", image!="", container!="POD"}[5m])) by (namespace)
record: namespace:container_cpu_usage_seconds_total:sum_rate
- expr: |
sum by (cluster, namespace, pod, container) (
rate(container_cpu_usage_seconds_total{job="kubelet", metrics_path="/metrics/cadvisor", image!="", container!="POD"}[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_rate
- expr: |
container_memory_working_set_bytes{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,
max by(namespace, pod, node) (kube_pod_info{node!=""})
)
record: node_namespace_pod_container:container_memory_working_set_bytes
- expr: |
container_memory_rss{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,
max by(namespace, pod, node) (kube_pod_info{node!=""})
)
record: node_namespace_pod_container:container_memory_rss
- expr: |
container_memory_cache{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,
max by(namespace, pod, node) (kube_pod_info{node!=""})
)
record: node_namespace_pod_container:container_memory_cache
- expr: |
container_memory_swap{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,
max by(namespace, pod, node) (kube_pod_info{node!=""})
)
record: node_namespace_pod_container:container_memory_swap
- expr: |
sum(container_memory_usage_bytes{job="kubelet", metrics_path="/metrics/cadvisor", image!="", container!="POD"}) by (namespace)
record: namespace:container_memory_usage_bytes:sum
- expr: |
sum by (namespace) (
sum by (namespace, pod) (
max by (namespace, pod, container) (
kube_pod_container_resource_requests_memory_bytes{job="kube-state-metrics"}
) * on(namespace, pod) group_left() max by (namespace, pod) (
kube_pod_status_phase{phase=~"Pending|Running"} == 1
)
)
)
record: namespace:kube_pod_container_resource_requests_memory_bytes:sum
- expr: |
sum by (namespace) (
sum by (namespace, pod) (
max by (namespace, pod, container) (
kube_pod_container_resource_requests_cpu_cores{job="kube-state-metrics"}
) * on(namespace, pod) group_left() max by (namespace, pod) (
kube_pod_status_phase{phase=~"Pending|Running"} == 1
)
)
)
record: namespace:kube_pod_container_resource_requests_cpu_cores:sum
- expr: |
max by (cluster, namespace, workload, pod) (
label_replace(
label_replace(
kube_pod_owner{job="kube-state-metrics", owner_kind="ReplicaSet"},
"replicaset", "$1", "owner_name", "(.*)"
) * on(replicaset, namespace) group_left(owner_name) topk by(replicaset, namespace) (
1, max by (replicaset, namespace, owner_name) (
kube_replicaset_owner{job="kube-state-metrics"}
)
),
"workload", "$1", "owner_name", "(.*)"
)
)
labels:
workload_type: deployment
record: mixin_pod_workload
- expr: |
max by (cluster, namespace, workload, pod) (
label_replace(
kube_pod_owner{job="kube-state-metrics", owner_kind="DaemonSet"},
"workload", "$1", "owner_name", "(.*)"
)
)
labels:
workload_type: daemonset
record: mixin_pod_workload
- expr: |
max by (cluster, namespace, workload, pod) (
label_replace(
kube_pod_owner{job="kube-state-metrics", owner_kind="StatefulSet"},
"workload", "$1", "owner_name", "(.*)"
)
)
labels:
workload_type: statefulset
record: mixin_pod_workload
- name: node.rules
rules:
- expr: |
sum(min(kube_pod_info{node!=""}) by (cluster, node))
record: ':kube_pod_info_node_count:'
- expr: |
topk by(namespace, pod) (1,
max by (node, namespace, pod) (
label_replace(kube_pod_info{job="kube-state-metrics",node!=""}, "pod", "$1", "pod", "(.*)")
))
record: 'node_namespace_pod:kube_pod_info:'
- expr: |
count by (cluster, node) (sum by (node, cpu) (
node_cpu_seconds_total{job="node-exporter"}
* on (namespace, pod) group_left(node)
node_namespace_pod:kube_pod_info:
))
record: node:node_num_cpu:sum
- expr: |
sum(
node_memory_MemAvailable_bytes{job="node-exporter"} or
(
node_memory_Buffers_bytes{job="node-exporter"} +
node_memory_Cached_bytes{job="node-exporter"} +
node_memory_MemFree_bytes{job="node-exporter"} +
node_memory_Slab_bytes{job="node-exporter"}
)
) by (cluster)
record: :node_memory_MemAvailable_bytes:sum
- name: kube-prometheus-node-recording.rules
rules:
- expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait"}[3m])) BY
(instance)
record: instance:node_cpu:rate:sum
- expr: sum((node_filesystem_size_bytes{mountpoint="/"} - node_filesystem_free_bytes{mountpoint="/"}))
BY (instance)
record: instance:node_filesystem_usage: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"}[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"}[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
- name: kube-state-metrics
rules:
- alert: KubeStateMetricsListErrors
annotations:
message: 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.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatemetricslisterrors
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:
message: 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.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatemetricswatcherrors
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
- 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.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemspacefillingup
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.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemspacefillingup
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.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemalmostoutofspace
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.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemalmostoutofspace
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.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemfilesfillingup
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.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemfilesfillingup
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.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemalmostoutoffiles
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.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemalmostoutoffiles
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.'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodenetworkreceiveerrs
summary: Network interface is reporting many receive errors.
expr: |
increase(node_network_receive_errs_total[2m]) > 10
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.'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodenetworktransmiterrs
summary: Network interface is reporting many transmit errors.
expr: |
increase(node_network_transmit_errs_total[2m]) > 10
for: 1h
labels:
severity: warning
- alert: NodeHighNumberConntrackEntriesUsed
annotations:
description: '{{ $value | humanizePercentage }} of conntrack entries are used.'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodehighnumberconntrackentriesused
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.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodetextfilecollectorscrapeerror
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.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodeclockskewdetected
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.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodeclocknotsynchronising
summary: Clock not synchronising.
expr: |
min_over_time(node_timex_sync_status[5m]) == 0
for: 10m
labels:
severity: warning
- name: kubernetes-apps
rules:
- alert: KubePodCrashLooping
annotations:
message: Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container
}}) is restarting {{ printf "%.2f" $value }} times / 5 minutes.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodcrashlooping
expr: |
rate(kube_pod_container_status_restarts_total{job="kube-state-metrics"}[5m]) * 60 * 5 > 0
for: 15m
labels:
severity: warning
- alert: KubePodNotReady
annotations:
message: Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-ready
state for longer than 15 minutes.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodnotready
expr: |
sum by (namespace, pod) (
max by(namespace, pod) (
kube_pod_status_phase{job="kube-state-metrics", phase=~"Pending|Unknown"}
) * on(namespace, pod) group_left(owner_kind) topk by(namespace, pod) (
1, max by(namespace, pod, owner_kind) (kube_pod_owner{owner_kind!="Job"})
)
) > 0
for: 15m
labels:
severity: warning
- alert: KubeDeploymentGenerationMismatch
annotations:
message: Deployment generation for {{ $labels.namespace }}/{{ $labels.deployment
}} does not match, this indicates that the Deployment has failed but has
not been rolled back.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentgenerationmismatch
expr: |
kube_deployment_status_observed_generation{job="kube-state-metrics"}
!=
kube_deployment_metadata_generation{job="kube-state-metrics"}
for: 15m
labels:
severity: warning
- alert: KubeDeploymentReplicasMismatch
annotations:
message: Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has not
matched the expected number of replicas for longer than 15 minutes.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentreplicasmismatch
expr: |
(
kube_deployment_spec_replicas{job="kube-state-metrics"}
!=
kube_deployment_status_replicas_available{job="kube-state-metrics"}
) and (
changes(kube_deployment_status_replicas_updated{job="kube-state-metrics"}[5m])
==
0
)
for: 15m
labels:
severity: warning
- alert: KubeStatefulSetReplicasMismatch
annotations:
message: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} has
not matched the expected number of replicas for longer than 15 minutes.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetreplicasmismatch
expr: |
(
kube_statefulset_status_replicas_ready{job="kube-state-metrics"}
!=
kube_statefulset_status_replicas{job="kube-state-metrics"}
) and (
changes(kube_statefulset_status_replicas_updated{job="kube-state-metrics"}[5m])
==
0
)
for: 15m
labels:
severity: warning
- alert: KubeStatefulSetGenerationMismatch
annotations:
message: StatefulSet generation for {{ $labels.namespace }}/{{ $labels.statefulset
}} does not match, this indicates that the StatefulSet has failed but has
not been rolled back.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetgenerationmismatch
expr: |
kube_statefulset_status_observed_generation{job="kube-state-metrics"}
!=
kube_statefulset_metadata_generation{job="kube-state-metrics"}
for: 15m
labels:
severity: warning
- alert: KubeStatefulSetUpdateNotRolledOut
annotations:
message: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} update
has not been rolled out.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetupdatenotrolledout
expr: |
(
max without (revision) (
kube_statefulset_status_current_revision{job="kube-state-metrics"}
unless
kube_statefulset_status_update_revision{job="kube-state-metrics"}
)
*
(
kube_statefulset_replicas{job="kube-state-metrics"}
!=
kube_statefulset_status_replicas_updated{job="kube-state-metrics"}
)
) and (
changes(kube_statefulset_status_replicas_updated{job="kube-state-metrics"}[5m])
==
0
)
for: 15m
labels:
severity: warning
- alert: KubeDaemonSetRolloutStuck
annotations:
message: Only {{ $value | humanizePercentage }} of the desired Pods of DaemonSet
{{ $labels.namespace }}/{{ $labels.daemonset }} are scheduled and ready.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetrolloutstuck
expr: |
kube_daemonset_status_number_ready{job="kube-state-metrics"}
/
kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics"} < 1.00
for: 15m
labels:
severity: warning
- alert: KubeContainerWaiting
annotations:
message: Pod {{ $labels.namespace }}/{{ $labels.pod }} container {{ $labels.container}}
has been in waiting state for longer than 1 hour.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontainerwaiting
expr: |
sum by (namespace, pod, container) (kube_pod_container_status_waiting_reason{job="kube-state-metrics"}) > 0
for: 1h
labels:
severity: warning
- alert: KubeDaemonSetNotScheduled
annotations:
message: '{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset
}} are not scheduled.'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetnotscheduled
expr: |
kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics"}
-
kube_daemonset_status_current_number_scheduled{job="kube-state-metrics"} > 0
for: 10m
labels:
severity: warning
- alert: KubeDaemonSetMisScheduled
annotations:
message: '{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset
}} are running where they are not supposed to run.'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetmisscheduled
expr: |
kube_daemonset_status_number_misscheduled{job="kube-state-metrics"} > 0
for: 15m
labels:
severity: warning
- alert: KubeCronJobRunning
annotations:
message: CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is taking more
than 1h to complete.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecronjobrunning
expr: |
time() - kube_cronjob_next_schedule_time{job="kube-state-metrics"} > 3600
for: 1h
labels:
severity: warning
- alert: KubeJobCompletion
annotations:
message: Job {{ $labels.namespace }}/{{ $labels.job_name }} is taking more
than one hour to complete.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobcompletion
expr: |
kube_job_spec_completions{job="kube-state-metrics"} - kube_job_status_succeeded{job="kube-state-metrics"} > 0
for: 1h
labels:
severity: warning
- alert: KubeJobFailed
annotations:
message: Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobfailed
expr: |
kube_job_failed{job="kube-state-metrics"} > 0
for: 15m
labels:
severity: warning
- alert: KubeHpaReplicasMismatch
annotations:
message: HPA {{ $labels.namespace }}/{{ $labels.hpa }} has not matched the
desired number of replicas for longer than 15 minutes.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubehpareplicasmismatch
expr: |
(kube_hpa_status_desired_replicas{job="kube-state-metrics"}
!=
kube_hpa_status_current_replicas{job="kube-state-metrics"})
and
changes(kube_hpa_status_current_replicas[15m]) == 0
for: 15m
labels:
severity: warning
- alert: KubeHpaMaxedOut
annotations:
message: HPA {{ $labels.namespace }}/{{ $labels.hpa }} has been running at
max replicas for longer than 15 minutes.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubehpamaxedout
expr: |
kube_hpa_status_current_replicas{job="kube-state-metrics"}
==
kube_hpa_spec_max_replicas{job="kube-state-metrics"}
for: 15m
labels:
severity: warning
- name: kubernetes-resources
rules:
- alert: KubeCPUOvercommit
annotations:
message: Cluster has overcommitted CPU resource requests for Pods and cannot
tolerate node failure.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuovercommit
expr: |
sum(namespace:kube_pod_container_resource_requests_cpu_cores:sum{})
/
sum(kube_node_status_allocatable_cpu_cores)
>
(count(kube_node_status_allocatable_cpu_cores)-1) / count(kube_node_status_allocatable_cpu_cores)
for: 5m
labels:
severity: warning
- alert: KubeMemoryOvercommit
annotations:
message: Cluster has overcommitted memory resource requests for Pods and cannot
tolerate node failure.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememoryovercommit
expr: |
sum(namespace:kube_pod_container_resource_requests_memory_bytes:sum{})
/
sum(kube_node_status_allocatable_memory_bytes)
>
(count(kube_node_status_allocatable_memory_bytes)-1)
/
count(kube_node_status_allocatable_memory_bytes)
for: 5m
labels:
severity: warning
- alert: KubeCPUQuotaOvercommit
annotations:
message: Cluster has overcommitted CPU resource requests for Namespaces.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuquotaovercommit
expr: |
sum(kube_resourcequota{job="kube-state-metrics", type="hard", resource="cpu"})
/
sum(kube_node_status_allocatable_cpu_cores)
> 1.5
for: 5m
labels:
severity: warning
- alert: KubeMemoryQuotaOvercommit
annotations:
message: Cluster has overcommitted memory resource requests for Namespaces.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememoryquotaovercommit
expr: |
sum(kube_resourcequota{job="kube-state-metrics", type="hard", resource="memory"})
/
sum(kube_node_status_allocatable_memory_bytes{job="node-exporter"})
> 1.5
for: 5m
labels:
severity: warning
- alert: KubeQuotaExceeded
annotations:
message: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage
}} of its {{ $labels.resource }} quota.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubequotaexceeded
expr: |
kube_resourcequota{job="kube-state-metrics", type="used"}
/ ignoring(instance, job, type)
(kube_resourcequota{job="kube-state-metrics", type="hard"} > 0)
> 0.90
for: 15m
labels:
severity: warning
- alert: CPUThrottlingHigh
annotations:
message: '{{ $value | humanizePercentage }} throttling of CPU in namespace
{{ $labels.namespace }} for container {{ $labels.container }} in pod {{
$labels.pod }}.'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-cputhrottlinghigh
expr: |
sum(increase(container_cpu_cfs_throttled_periods_total{container!="", }[5m])) by (container, pod, namespace)
/
sum(increase(container_cpu_cfs_periods_total{}[5m])) by (container, pod, namespace)
> ( 25 / 100 )
for: 15m
labels:
severity: warning
- name: prometheus
rules:
- alert: PrometheusBadConfig
annotations:
description: Prometheus {{$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: PrometheusErrorSendingAlertsToAnyAlertmanager
annotations:
description: '{{ printf "%.1f" $value }}% minimum errors while sending alerts
from Prometheus {{$labels.namespace}}/{{$labels.pod}} to any Alertmanager.'
summary: Prometheus encounters more than 3% errors sending alerts to any Alertmanager.
expr: |
min without(alertmanager) (
rate(prometheus_notifications_errors_total{job="prometheus-k8s",namespace="monitoring"}[5m])
/
rate(prometheus_notifications_sent_total{job="prometheus-k8s",namespace="monitoring"}[5m])
)
* 100
> 3
for: 15m
labels:
severity: critical
- alert: PrometheusNotConnectedToAlertmanagers
annotations:
description: Prometheus {{$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}}/{{$labels.pod}} is not ingesting
samples.
summary: Prometheus is not ingesting samples.
expr: |
rate(prometheus_tsdb_head_samples_appended_total{job="prometheus-k8s",namespace="monitoring"}[5m]) <= 0
for: 10m
labels:
severity: warning
- alert: PrometheusDuplicateTimestamps
annotations:
description: Prometheus {{$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}}:{{ $labels.url
}}.
summary: Prometheus remote write is behind.
expr: |
# Without max_over_time, failed scrapes could create false negatives, see
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
(
max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job="prometheus-k8s",namespace="monitoring"}[5m])
- on(job, instance) group_right
max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job="prometheus-k8s",namespace="monitoring"}[5m])
)
> 120
for: 15m
labels:
severity: critical
- alert: PrometheusRemoteWriteDesiredShards
annotations:
description: Prometheus {{$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
- name: alertmanager.rules
rules:
- alert: AlertmanagerConfigInconsistent
annotations:
message: |
The configuration of the instances of the Alertmanager cluster `{{ $labels.namespace }}/{{ $labels.service }}` are out of sync.
{{ range printf "alertmanager_config_hash{namespace=\"%s\",service=\"%s\"}" $labels.namespace $labels.service | query }}
Configuration hash for pod {{ .Labels.pod }} is "{{ printf "%.f" .Value }}"
{{ end }}
expr: |
count by(namespace,service) (count_values by(namespace,service) ("config_hash", alertmanager_config_hash{job="alertmanager-main",namespace="monitoring"})) != 1
for: 5m
labels:
severity: critical
- alert: AlertmanagerFailedReload
annotations:
message: Reloading Alertmanager's configuration has failed for {{ $labels.namespace
}}/{{ $labels.pod}}.
expr: |
alertmanager_config_last_reload_successful{job="alertmanager-main",namespace="monitoring"} == 0
for: 10m
labels:
severity: warning
- alert: AlertmanagerMembersInconsistent
annotations:
message: Alertmanager has not found all other members of the cluster.
expr: |
alertmanager_cluster_members{job="alertmanager-main",namespace="monitoring"}
!= on (service) GROUP_LEFT()
count by (service) (alertmanager_cluster_members{job="alertmanager-main",namespace="monitoring"})
for: 5m
labels:
severity: critical
- 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: prometheus-operator
rules:
- alert: PrometheusOperatorReconcileErrors
annotations:
message: Errors while reconciling {{ $labels.controller }} in {{ $labels.namespace
}} Namespace.
expr: |
rate(prometheus_operator_reconcile_errors_total{job="prometheus-operator",namespace="monitoring"}[5m]) > 0.1
for: 10m
labels:
severity: warning
- alert: PrometheusOperatorNodeLookupErrors
annotations:
message: Errors while reconciling Prometheus in {{ $labels.namespace }} Namespace.
expr: |
rate(prometheus_operator_node_address_lookup_errors_total{job="prometheus-operator",namespace="monitoring"}[5m]) > 0.1
for: 10m
labels:
severity: warning
- name: Host and hardware
rules:
- alert: HostOutOfMemory
expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10
for: 5m
labels:
severity: warning
annotations:
summary: "Host out of memory (instance {{ $labels.instance }})"
description: "Node memory is filling up (< 10% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostMemoryUnderMemoryPressure
expr: rate(node_vmstat_pgmajfault[1m]) > 1000
for: 5m
labels:
severity: warning
annotations:
summary: "Host memory under memory pressure (instance {{ $labels.instance }})"
description: "The node is under heavy memory pressure. High rate of major page faults\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment