typhoon/addons/prometheus/rules.yaml

500 lines
22 KiB
YAML
Raw Normal View History

apiVersion: v1
kind: ConfigMap
metadata:
name: prometheus-rules
namespace: monitoring
data:
# Rules adapted from those provided by coreos/prometheus-operator and SoundCloud
alertmanager.rules.yaml: |+
groups:
- name: ./alertmanager.rules
rules:
- alert: AlertmanagerConfigInconsistent
expr: count_values("config_hash", alertmanager_config_hash) BY (service) / ON(service)
GROUP_LEFT() label_replace(prometheus_operator_alertmanager_spec_replicas, "service",
"alertmanager-$1", "alertmanager", "(.*)") != 1
for: 5m
labels:
severity: critical
annotations:
description: The configuration of the instances of the Alertmanager cluster
`{{$labels.service}}` are out of sync.
summary: Alertmanager configurations are inconsistent
- alert: AlertmanagerDownOrMissing
expr: label_replace(prometheus_operator_alertmanager_spec_replicas, "job", "alertmanager-$1",
"alertmanager", "(.*)") / ON(job) GROUP_RIGHT() sum(up) BY (job) != 1
for: 5m
labels:
severity: warning
annotations:
description: An unexpected number of Alertmanagers are scraped or Alertmanagers
disappeared from discovery.
summary: Alertmanager down or not discovered
- alert: FailedReload
expr: alertmanager_config_last_reload_successful == 0
for: 10m
labels:
severity: warning
annotations:
description: Reloading Alertmanager's configuration has failed for {{ $labels.namespace
}}/{{ $labels.pod}}.
summary: Alertmanager configuration reload has failed
etcd3.rules.yaml: |+
groups:
- name: ./etcd3.rules
rules:
- alert: InsufficientMembers
expr: count(up{job="etcd"} == 0) > (count(up{job="etcd"}) / 2 - 1)
for: 3m
labels:
severity: critical
annotations:
description: If one more etcd member goes down the cluster will be unavailable
summary: etcd cluster insufficient members
- alert: NoLeader
expr: etcd_server_has_leader{job="etcd"} == 0
for: 1m
labels:
severity: critical
annotations:
description: etcd member {{ $labels.instance }} has no leader
summary: etcd member has no leader
- alert: HighNumberOfLeaderChanges
expr: increase(etcd_server_leader_changes_seen_total{job="etcd"}[1h]) > 3
labels:
severity: warning
annotations:
description: etcd instance {{ $labels.instance }} has seen {{ $value }} leader
changes within the last hour
summary: a high number of leader changes within the etcd cluster are happening
- alert: HighNumberOfFailedGRPCRequests
expr: sum(rate(etcd_grpc_requests_failed_total{job="etcd"}[5m])) BY (grpc_method)
/ sum(rate(etcd_grpc_total{job="etcd"}[5m])) BY (grpc_method) > 0.01
for: 10m
labels:
severity: warning
annotations:
description: '{{ $value }}% of requests for {{ $labels.grpc_method }} failed
on etcd instance {{ $labels.instance }}'
summary: a high number of gRPC requests are failing
- alert: HighNumberOfFailedGRPCRequests
expr: sum(rate(etcd_grpc_requests_failed_total{job="etcd"}[5m])) BY (grpc_method)
/ sum(rate(etcd_grpc_total{job="etcd"}[5m])) BY (grpc_method) > 0.05
for: 5m
labels:
severity: critical
annotations:
description: '{{ $value }}% of requests for {{ $labels.grpc_method }} failed
on etcd instance {{ $labels.instance }}'
summary: a high number of gRPC requests are failing
- alert: GRPCRequestsSlow
expr: histogram_quantile(0.99, rate(etcd_grpc_unary_requests_duration_seconds_bucket[5m]))
> 0.15
for: 10m
labels:
severity: critical
annotations:
description: on etcd instance {{ $labels.instance }} gRPC requests to {{ $labels.grpc_method
}} are slow
summary: slow gRPC requests
- alert: HighNumberOfFailedHTTPRequests
expr: sum(rate(etcd_http_failed_total{job="etcd"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job="etcd"}[5m]))
BY (method) > 0.01
for: 10m
labels:
severity: warning
annotations:
description: '{{ $value }}% of requests for {{ $labels.method }} failed on etcd
instance {{ $labels.instance }}'
summary: a high number of HTTP requests are failing
- alert: HighNumberOfFailedHTTPRequests
expr: sum(rate(etcd_http_failed_total{job="etcd"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job="etcd"}[5m]))
BY (method) > 0.05
for: 5m
labels:
severity: critical
annotations:
description: '{{ $value }}% of requests for {{ $labels.method }} failed on etcd
instance {{ $labels.instance }}'
summary: a high number of HTTP requests are failing
- alert: HTTPRequestsSlow
expr: histogram_quantile(0.99, rate(etcd_http_successful_duration_seconds_bucket[5m]))
> 0.15
for: 10m
labels:
severity: warning
annotations:
description: on etcd instance {{ $labels.instance }} HTTP requests to {{ $labels.method
}} are slow
summary: slow HTTP requests
- alert: EtcdMemberCommunicationSlow
expr: histogram_quantile(0.99, rate(etcd_network_member_round_trip_time_seconds_bucket[5m]))
> 0.15
for: 10m
labels:
severity: warning
annotations:
description: etcd instance {{ $labels.instance }} member communication with
{{ $labels.To }} is slow
summary: etcd member communication is slow
- alert: HighNumberOfFailedProposals
expr: increase(etcd_server_proposals_failed_total{job="etcd"}[1h]) > 5
labels:
severity: warning
annotations:
description: etcd instance {{ $labels.instance }} has seen {{ $value }} proposal
failures within the last hour
summary: a high number of proposals within the etcd cluster are failing
- alert: HighFsyncDurations
expr: histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[5m]))
> 0.5
for: 10m
labels:
severity: warning
annotations:
description: etcd instance {{ $labels.instance }} fync durations are high
summary: high fsync durations
- alert: HighCommitDurations
expr: histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket[5m]))
> 0.25
for: 10m
labels:
severity: warning
annotations:
description: etcd instance {{ $labels.instance }} commit durations are high
summary: high commit durations
general.rules.yaml: |+
groups:
- name: ./general.rules
rules:
- alert: TargetDown
expr: 100 * (count(up == 0) BY (job) / count(up) BY (job)) > 10
for: 10m
labels:
severity: warning
annotations:
description: '{{ $value }}% or more of {{ $labels.job }} targets are down.'
summary: Targets are down
- alert: TooManyOpenFileDescriptors
expr: 100 * (process_open_fds / process_max_fds) > 95
for: 10m
labels:
severity: critical
annotations:
description: '{{ $labels.job }}: {{ $labels.namespace }}/{{ $labels.pod }} ({{
$labels.instance }}) is using {{ $value }}% of the available file/socket descriptors.'
summary: too many open file descriptors
- record: instance:fd_utilization
expr: process_open_fds / process_max_fds
- alert: FdExhaustionClose
expr: predict_linear(instance:fd_utilization[1h], 3600 * 4) > 1
for: 10m
labels:
severity: warning
annotations:
description: '{{ $labels.job }}: {{ $labels.namespace }}/{{ $labels.pod }} ({{
$labels.instance }}) instance will exhaust in file/socket descriptors soon'
summary: file descriptors soon exhausted
- alert: FdExhaustionClose
expr: predict_linear(instance:fd_utilization[10m], 3600) > 1
for: 10m
labels:
severity: critical
annotations:
description: '{{ $labels.job }}: {{ $labels.namespace }}/{{ $labels.pod }} ({{
$labels.instance }}) instance will exhaust in file/socket descriptors soon'
summary: file descriptors soon exhausted
kube-apiserver.rules.yaml: |+
groups:
- name: ./kube-apiserver.rules
rules:
- alert: K8SApiserverDown
expr: absent(up{job="kubernetes-apiservers"} == 1)
for: 5m
labels:
severity: critical
annotations:
description: Prometheus failed to scrape API server(s), or all API servers have
disappeared from service discovery.
summary: API server unreachable
- alert: K8SApiServerLatency
expr: histogram_quantile(0.99, sum(rate(apiserver_request_latencies_bucket{subresource!="log",verb!~"^(?:CONNECT|WATCHLIST|WATCH|PROXY)$"}[10m]))
by (le)) / 1e+06 > 1
for: 10m
labels:
severity: warning
annotations:
description: 99th percentile Latency for {{ $labels.verb }} requests to the
kube-apiserver is higher than 1s.
summary: Kubernetes apiserver latency is high
kube-controller-manager.rules.yaml: |+
groups:
- name: ./kube-controller-manager.rules
rules:
- alert: K8SControllerManagerDown
expr: absent(up{kubernetes_name="kube-controller-manager"} == 1)
for: 5m
labels:
severity: critical
annotations:
description: There is no running K8S controller manager. Deployments and replication
controllers are not making progress.
summary: Controller manager is down
kube-scheduler.rules.yaml: |+
groups:
- name: ./kube-scheduler.rules
rules:
- alert: K8SSchedulerDown
expr: absent(up{kubernetes_name="kube-scheduler"} == 1)
for: 5m
labels:
severity: critical
annotations:
description: There is no running K8S scheduler. New pods are not being assigned
to nodes.
summary: Scheduler is down
kubelet.rules.yaml: |+
groups:
- name: ./kubelet.rules
rules:
- alert: K8SNodeNotReady
expr: kube_node_status_condition{condition="Ready",status="true"} == 0
for: 1h
labels:
severity: warning
annotations:
description: The Kubelet on {{ $labels.node }} has not checked in with the API,
or has set itself to NotReady, for more than an hour
summary: Node status is NotReady
- alert: K8SManyNodesNotReady
expr: count(kube_node_status_condition{condition="Ready",status="true"} == 0)
> 1 and (count(kube_node_status_condition{condition="Ready",status="true"} ==
0) / count(kube_node_status_condition{condition="Ready",status="true"})) > 0.2
for: 1m
labels:
severity: critical
annotations:
description: '{{ $value }} Kubernetes nodes (more than 10% are in the NotReady
state).'
summary: Many Kubernetes nodes are Not Ready
- alert: K8SKubeletDown
expr: count(up{job="kubernetes-nodes"} == 0) / count(up{job="kubernetes-nodes"}) > 0.03
for: 1h
labels:
severity: warning
annotations:
description: Prometheus failed to scrape {{ $value }}% of kubelets.
summary: Many Kubelets cannot be scraped
- alert: K8SKubeletDown
expr: absent(up{job="kubernetes-nodes"} == 1) or count(up{job="kubernetes-nodes"} == 0) / count(up{job="kubernetes-nodes"})
> 0.1
for: 1h
labels:
severity: critical
annotations:
description: Prometheus failed to scrape {{ $value }}% of kubelets, or all Kubelets
have disappeared from service discovery.
summary: Many Kubelets cannot be scraped
- alert: K8SKubeletTooManyPods
expr: kubelet_running_pod_count > 100
labels:
severity: warning
annotations:
description: Kubelet {{$labels.instance}} is running {{$value}} pods, close
to the limit of 110
summary: Kubelet is close to pod limit
- alert: K8SDaemonSetsNotScheduled
expr: kube_daemonset_status_desired_number_scheduled - kube_daemonset_status_current_number_scheduled
> 0
for: 10m
labels:
severity: warning
annotations:
description: A number of daemonsets are not scheduled.
summary: Daemonsets are not scheduled correctly
- alert: K8SDaemonSetsNotRunning
expr: kube_daemonset_status_desired_number_scheduled - kube_daemonset_status_number_ready
> 0
for: 10m
labels:
severity: warning
annotations:
description: A number of daemonsets are not ready.
summary: Daemonsets are not ready
- alert: K8SDaemonSetsMissScheduled
expr: kube_daemonset_status_number_misscheduled > 0
for: 10m
labels:
severity: warning
annotations:
description: A number of daemonsets are running where they are not supposed
to run.
summary: Daemonsets are not scheduled correctly
kubernetes.rules.yaml: |+
groups:
- name: ./kubernetes.rules
rules:
- record: cluster_namespace_controller_pod_container:spec_memory_limit_bytes
expr: sum(label_replace(container_spec_memory_limit_bytes{container_name!=""},
"controller", "$1", "pod_name", "^(.*)-[a-z0-9]+")) BY (cluster, namespace,
controller, pod_name, container_name)
- record: cluster_namespace_controller_pod_container:spec_cpu_shares
expr: sum(label_replace(container_spec_cpu_shares{container_name!=""}, "controller",
"$1", "pod_name", "^(.*)-[a-z0-9]+")) BY (cluster, namespace, controller, pod_name,
container_name)
- record: cluster_namespace_controller_pod_container:cpu_usage:rate
expr: sum(label_replace(irate(container_cpu_usage_seconds_total{container_name!=""}[5m]),
"controller", "$1", "pod_name", "^(.*)-[a-z0-9]+")) BY (cluster, namespace,
controller, pod_name, container_name)
- record: cluster_namespace_controller_pod_container:memory_usage:bytes
expr: sum(label_replace(container_memory_usage_bytes{container_name!=""}, "controller",
"$1", "pod_name", "^(.*)-[a-z0-9]+")) BY (cluster, namespace, controller, pod_name,
container_name)
- record: cluster_namespace_controller_pod_container:memory_working_set:bytes
expr: sum(label_replace(container_memory_working_set_bytes{container_name!=""},
"controller", "$1", "pod_name", "^(.*)-[a-z0-9]+")) BY (cluster, namespace,
controller, pod_name, container_name)
- record: cluster_namespace_controller_pod_container:memory_rss:bytes
expr: sum(label_replace(container_memory_rss{container_name!=""}, "controller",
"$1", "pod_name", "^(.*)-[a-z0-9]+")) BY (cluster, namespace, controller, pod_name,
container_name)
- record: cluster_namespace_controller_pod_container:memory_cache:bytes
expr: sum(label_replace(container_memory_cache{container_name!=""}, "controller",
"$1", "pod_name", "^(.*)-[a-z0-9]+")) BY (cluster, namespace, controller, pod_name,
container_name)
- record: cluster_namespace_controller_pod_container:disk_usage:bytes
expr: sum(label_replace(container_disk_usage_bytes{container_name!=""}, "controller",
"$1", "pod_name", "^(.*)-[a-z0-9]+")) BY (cluster, namespace, controller, pod_name,
container_name)
- record: cluster_namespace_controller_pod_container:memory_pagefaults:rate
expr: sum(label_replace(irate(container_memory_failures_total{container_name!=""}[5m]),
"controller", "$1", "pod_name", "^(.*)-[a-z0-9]+")) BY (cluster, namespace,
controller, pod_name, container_name, scope, type)
- record: cluster_namespace_controller_pod_container:memory_oom:rate
expr: sum(label_replace(irate(container_memory_failcnt{container_name!=""}[5m]),
"controller", "$1", "pod_name", "^(.*)-[a-z0-9]+")) BY (cluster, namespace,
controller, pod_name, container_name, scope, type)
- record: cluster:memory_allocation:percent
expr: 100 * sum(container_spec_memory_limit_bytes{pod_name!=""}) BY (cluster)
/ sum(machine_memory_bytes) BY (cluster)
- record: cluster:memory_used:percent
expr: 100 * sum(container_memory_usage_bytes{pod_name!=""}) BY (cluster) / sum(machine_memory_bytes)
BY (cluster)
- record: cluster:cpu_allocation:percent
expr: 100 * sum(container_spec_cpu_shares{pod_name!=""}) BY (cluster) / sum(container_spec_cpu_shares{id="/"}
* ON(cluster, instance) machine_cpu_cores) BY (cluster)
- record: cluster:node_cpu_use:percent
expr: 100 * sum(rate(node_cpu{mode!="idle"}[5m])) BY (cluster) / sum(machine_cpu_cores)
BY (cluster)
- record: cluster_resource_verb:apiserver_latency:quantile_seconds
expr: histogram_quantile(0.99, sum(apiserver_request_latencies_bucket) BY (le,
cluster, job, resource, verb)) / 1e+06
labels:
quantile: "0.99"
- record: cluster_resource_verb:apiserver_latency:quantile_seconds
expr: histogram_quantile(0.9, sum(apiserver_request_latencies_bucket) BY (le,
cluster, job, resource, verb)) / 1e+06
labels:
quantile: "0.9"
- record: cluster_resource_verb:apiserver_latency:quantile_seconds
expr: histogram_quantile(0.5, sum(apiserver_request_latencies_bucket) BY (le,
cluster, job, resource, verb)) / 1e+06
labels:
quantile: "0.5"
- record: cluster:scheduler_e2e_scheduling_latency:quantile_seconds
expr: histogram_quantile(0.99, sum(scheduler_e2e_scheduling_latency_microseconds_bucket)
BY (le, cluster)) / 1e+06
labels:
quantile: "0.99"
- record: cluster:scheduler_e2e_scheduling_latency:quantile_seconds
expr: histogram_quantile(0.9, sum(scheduler_e2e_scheduling_latency_microseconds_bucket)
BY (le, cluster)) / 1e+06
labels:
quantile: "0.9"
- record: cluster:scheduler_e2e_scheduling_latency:quantile_seconds
expr: histogram_quantile(0.5, sum(scheduler_e2e_scheduling_latency_microseconds_bucket)
BY (le, cluster)) / 1e+06
labels:
quantile: "0.5"
- record: cluster:scheduler_scheduling_algorithm_latency:quantile_seconds
expr: histogram_quantile(0.99, sum(scheduler_scheduling_algorithm_latency_microseconds_bucket)
BY (le, cluster)) / 1e+06
labels:
quantile: "0.99"
- record: cluster:scheduler_scheduling_algorithm_latency:quantile_seconds
expr: histogram_quantile(0.9, sum(scheduler_scheduling_algorithm_latency_microseconds_bucket)
BY (le, cluster)) / 1e+06
labels:
quantile: "0.9"
- record: cluster:scheduler_scheduling_algorithm_latency:quantile_seconds
expr: histogram_quantile(0.5, sum(scheduler_scheduling_algorithm_latency_microseconds_bucket)
BY (le, cluster)) / 1e+06
labels:
quantile: "0.5"
- record: cluster:scheduler_binding_latency:quantile_seconds
expr: histogram_quantile(0.99, sum(scheduler_binding_latency_microseconds_bucket)
BY (le, cluster)) / 1e+06
labels:
quantile: "0.99"
- record: cluster:scheduler_binding_latency:quantile_seconds
expr: histogram_quantile(0.9, sum(scheduler_binding_latency_microseconds_bucket)
BY (le, cluster)) / 1e+06
labels:
quantile: "0.9"
- record: cluster:scheduler_binding_latency:quantile_seconds
expr: histogram_quantile(0.5, sum(scheduler_binding_latency_microseconds_bucket)
BY (le, cluster)) / 1e+06
labels:
quantile: "0.5"
node.rules.yaml: |+
groups:
- name: ./node.rules
rules:
- alert: NodeExporterDown
expr: absent(up{kubernetes_name="node-exporter"} == 1)
for: 10m
labels:
severity: warning
annotations:
description: Prometheus could not scrape a node-exporter for more than 10m,
or node-exporters have disappeared from discovery.
summary: node-exporter cannot be scraped
- alert: K8SNodeOutOfDisk
expr: kube_node_status_condition{condition="OutOfDisk",status="true"} == 1
labels:
service: k8s
severity: critical
annotations:
description: '{{ $labels.node }} has run out of disk space.'
summary: Node ran out of disk space.
- alert: K8SNodeMemoryPressure
expr: kube_node_status_condition{condition="MemoryPressure",status="true"} ==
1
labels:
service: k8s
severity: warning
annotations:
description: '{{ $labels.node }} is under memory pressure.'
summary: Node is under memory pressure.
- alert: K8SNodeDiskPressure
expr: kube_node_status_condition{condition="DiskPressure",status="true"} == 1
labels:
service: k8s
severity: warning
annotations:
description: '{{ $labels.node }} is under disk pressure.'
summary: Node is under disk pressure.
prometheus.rules.yaml: |+
groups:
- name: ./prometheus.rules
rules:
- alert: FailedReload
expr: prometheus_config_last_reload_successful == 0
for: 10m
labels:
severity: warning
annotations:
description: Reloading Prometheus' configuration has failed for {{ $labels.namespace
}}/{{ $labels.pod}}.
summary: Prometheus configuration reload has failed