feat: new scrapes

This commit is contained in:
nyyu 2023-03-05 08:58:53 +01:00
parent 97cf13cb09
commit ec65c7876d
3 changed files with 412 additions and 3 deletions

View File

@ -0,0 +1,311 @@
groups:
- name: KubestateExporter
rules:
- alert: KubernetesNodeReady
expr: 'kube_node_status_condition{condition="Ready",status="true"} == 0'
for: 10m
labels:
severity: critical
annotations:
summary: Kubernetes Node ready (instance {{ $labels.instance }})
description: "Node {{ $labels.node }} has been unready for a long time\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesMemoryPressure
expr: 'kube_node_status_condition{condition="MemoryPressure",status="true"} == 1'
for: 2m
labels:
severity: critical
annotations:
summary: Kubernetes memory pressure (instance {{ $labels.instance }})
description: "{{ $labels.node }} has MemoryPressure condition\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesDiskPressure
expr: 'kube_node_status_condition{condition="DiskPressure",status="true"} == 1'
for: 2m
labels:
severity: critical
annotations:
summary: Kubernetes disk pressure (instance {{ $labels.instance }})
description: "{{ $labels.node }} has DiskPressure condition\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesNetworkUnavailable
expr: 'kube_node_status_condition{condition="NetworkUnavailable",status="true"} == 1'
for: 2m
labels:
severity: critical
annotations:
summary: Kubernetes network unavailable (instance {{ $labels.instance }})
description: "{{ $labels.node }} has NetworkUnavailable condition\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesOutOfCapacity
expr: 'sum by (node) ((kube_pod_status_phase{phase="Running"} == 1) + on(uid) group_left(node) (0 * kube_pod_info{pod_template_hash=""})) / sum by (node) (kube_node_status_allocatable{resource="pods"}) * 100 > 90'
for: 2m
labels:
severity: warning
annotations:
summary: Kubernetes out of capacity (instance {{ $labels.instance }})
description: "{{ $labels.node }} is out of capacity\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesContainerOomKiller
expr: '(kube_pod_container_status_restarts_total - kube_pod_container_status_restarts_total offset 10m >= 1) and ignoring (reason) min_over_time(kube_pod_container_status_last_terminated_reason{reason="OOMKilled"}[10m]) == 1'
for: 0m
labels:
severity: warning
annotations:
summary: Kubernetes container oom killer (instance {{ $labels.instance }})
description: "Container {{ $labels.container }} in pod {{ $labels.namespace }}/{{ $labels.pod }} has been OOMKilled {{ $value }} times in the last 10 minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesJobFailed
expr: 'kube_job_status_failed > 0'
for: 0m
labels:
severity: warning
annotations:
summary: Kubernetes Job failed (instance {{ $labels.instance }})
description: "Job {{ $labels.namespace }}/{{ $labels.exported_job }} failed to complete\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesCronjobSuspended
expr: 'kube_cronjob_spec_suspend != 0'
for: 0m
labels:
severity: warning
annotations:
summary: Kubernetes CronJob suspended (instance {{ $labels.instance }})
description: "CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is suspended\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesPersistentvolumeclaimPending
expr: 'kube_persistentvolumeclaim_status_phase{phase="Pending"} == 1'
for: 2m
labels:
severity: warning
annotations:
summary: Kubernetes PersistentVolumeClaim pending (instance {{ $labels.instance }})
description: "PersistentVolumeClaim {{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is pending\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesVolumeOutOfDiskSpace
expr: 'kubelet_volume_stats_available_bytes / kubelet_volume_stats_capacity_bytes * 100 < 10'
for: 2m
labels:
severity: warning
annotations:
summary: Kubernetes Volume out of disk space (instance {{ $labels.instance }})
description: "Volume is almost full (< 10% left)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesVolumeFullInFourDays
expr: 'predict_linear(kubelet_volume_stats_available_bytes[6h], 4 * 24 * 3600) < 0'
for: 0m
labels:
severity: critical
annotations:
summary: Kubernetes Volume full in four days (instance {{ $labels.instance }})
description: "{{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is expected to fill up within four days. Currently {{ $value | humanize }}% is available.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesPersistentvolumeError
expr: 'kube_persistentvolume_status_phase{phase=~"Failed|Pending", job="kube-state-metrics"} > 0'
for: 0m
labels:
severity: critical
annotations:
summary: Kubernetes PersistentVolume error (instance {{ $labels.instance }})
description: "Persistent volume is in bad state\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesStatefulsetDown
expr: 'kube_statefulset_replicas != kube_statefulset_status_replicas_ready > 0'
for: 1m
labels:
severity: critical
annotations:
summary: Kubernetes StatefulSet down (instance {{ $labels.instance }})
description: "A StatefulSet went down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesHpaScalingAbility
expr: 'kube_horizontalpodautoscaler_status_condition{status="false", condition="AbleToScale"} == 1'
for: 2m
labels:
severity: warning
annotations:
summary: Kubernetes HPA scaling ability (instance {{ $labels.instance }})
description: "Pod is unable to scale\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesHpaMetricAvailability
expr: 'kube_horizontalpodautoscaler_status_condition{status="false", condition="ScalingActive"} == 1'
for: 0m
labels:
severity: warning
annotations:
summary: Kubernetes HPA metric availability (instance {{ $labels.instance }})
description: "HPA is not able to collect metrics\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesHpaScaleCapability
expr: 'kube_horizontalpodautoscaler_status_desired_replicas >= kube_horizontalpodautoscaler_spec_max_replicas'
for: 2m
labels:
severity: info
annotations:
summary: Kubernetes HPA scale capability (instance {{ $labels.instance }})
description: "The maximum number of desired Pods has been hit\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesHpaUnderutilized
expr: 'max(quantile_over_time(0.5, kube_horizontalpodautoscaler_status_desired_replicas[1d]) == kube_horizontalpodautoscaler_spec_min_replicas) by (horizontalpodautoscaler) > 3'
for: 0m
labels:
severity: info
annotations:
summary: Kubernetes HPA underutilized (instance {{ $labels.instance }})
description: "HPA is constantly at minimum replicas for 50% of the time. Potential cost saving here.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesPodNotHealthy
expr: 'sum by (namespace, pod) (kube_pod_status_phase{phase=~"Pending|Unknown|Failed"}) > 0'
for: 15m
labels:
severity: critical
annotations:
summary: Kubernetes Pod not healthy (instance {{ $labels.instance }})
description: "Pod has been in a non-ready state for longer than 15 minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesPodCrashLooping
expr: 'increase(kube_pod_container_status_restarts_total[1m]) > 3'
for: 2m
labels:
severity: warning
annotations:
summary: Kubernetes pod crash looping (instance {{ $labels.instance }})
description: "Pod {{ $labels.pod }} is crash looping\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesReplicassetMismatch
expr: 'kube_replicaset_spec_replicas != kube_replicaset_status_ready_replicas'
for: 10m
labels:
severity: warning
annotations:
summary: Kubernetes ReplicasSet mismatch (instance {{ $labels.instance }})
description: "Deployment Replicas mismatch\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesDeploymentReplicasMismatch
expr: 'kube_deployment_spec_replicas != kube_deployment_status_replicas_available'
for: 10m
labels:
severity: warning
annotations:
summary: Kubernetes Deployment replicas mismatch (instance {{ $labels.instance }})
description: "Deployment Replicas mismatch\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesStatefulsetReplicasMismatch
expr: 'kube_statefulset_status_replicas_ready != kube_statefulset_status_replicas'
for: 10m
labels:
severity: warning
annotations:
summary: Kubernetes StatefulSet replicas mismatch (instance {{ $labels.instance }})
description: "A StatefulSet does not match the expected number of replicas.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesDeploymentGenerationMismatch
expr: 'kube_deployment_status_observed_generation != kube_deployment_metadata_generation'
for: 10m
labels:
severity: critical
annotations:
summary: Kubernetes Deployment generation mismatch (instance {{ $labels.instance }})
description: "A Deployment has failed but has not been rolled back.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesStatefulsetGenerationMismatch
expr: 'kube_statefulset_status_observed_generation != kube_statefulset_metadata_generation'
for: 10m
labels:
severity: critical
annotations:
summary: Kubernetes StatefulSet generation mismatch (instance {{ $labels.instance }})
description: "A StatefulSet has failed but has not been rolled back.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesStatefulsetUpdateNotRolledOut
expr: 'max without (revision) (kube_statefulset_status_current_revision unless kube_statefulset_status_update_revision) * (kube_statefulset_replicas != kube_statefulset_status_replicas_updated)'
for: 10m
labels:
severity: warning
annotations:
summary: Kubernetes StatefulSet update not rolled out (instance {{ $labels.instance }})
description: "StatefulSet update has not been rolled out.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesDaemonsetRolloutStuck
expr: 'kube_daemonset_status_number_ready / kube_daemonset_status_desired_number_scheduled * 100 < 100 or kube_daemonset_status_desired_number_scheduled - kube_daemonset_status_current_number_scheduled > 0'
for: 10m
labels:
severity: warning
annotations:
summary: Kubernetes DaemonSet rollout stuck (instance {{ $labels.instance }})
description: "Some Pods of DaemonSet are not scheduled or not ready\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesDaemonsetMisscheduled
expr: 'kube_daemonset_status_number_misscheduled > 0'
for: 1m
labels:
severity: critical
annotations:
summary: Kubernetes DaemonSet misscheduled (instance {{ $labels.instance }})
description: "Some DaemonSet Pods are running where they are not supposed to run\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesCronjobTooLong
expr: 'time() - kube_cronjob_next_schedule_time > 3600'
for: 0m
labels:
severity: warning
annotations:
summary: Kubernetes CronJob too long (instance {{ $labels.instance }})
description: "CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is taking more than 1h to complete.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesJobSlowCompletion
expr: 'kube_job_spec_completions - kube_job_status_succeeded > 0'
for: 12h
labels:
severity: critical
annotations:
summary: Kubernetes job slow completion (instance {{ $labels.instance }})
description: "Kubernetes Job {{ $labels.namespace }}/{{ $labels.job_name }} did not complete in time.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesApiServerErrors
expr: 'sum(rate(apiserver_request_total{job="apiserver",code=~"^(?:5..)$"}[1m])) / sum(rate(apiserver_request_total{job="apiserver"}[1m])) * 100 > 3'
for: 2m
labels:
severity: critical
annotations:
summary: Kubernetes API server errors (instance {{ $labels.instance }})
description: "Kubernetes API server is experiencing high error rate\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesApiClientErrors
expr: '(sum(rate(rest_client_requests_total{code=~"(4|5).."}[1m])) by (instance, job) / sum(rate(rest_client_requests_total[1m])) by (instance, job)) * 100 > 1'
for: 2m
labels:
severity: critical
annotations:
summary: Kubernetes API client errors (instance {{ $labels.instance }})
description: "Kubernetes API client is experiencing high error rate\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesClientCertificateExpiresNextWeek
expr: 'apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 7*24*60*60'
for: 0m
labels:
severity: warning
annotations:
summary: Kubernetes client certificate expires next week (instance {{ $labels.instance }})
description: "A client certificate used to authenticate to the apiserver is expiring next week.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesClientCertificateExpiresSoon
expr: 'apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 24*60*60'
for: 0m
labels:
severity: critical
annotations:
summary: Kubernetes client certificate expires soon (instance {{ $labels.instance }})
description: "A client certificate used to authenticate to the apiserver is expiring in less than 24.0 hours.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesApiServerLatency
expr: 'histogram_quantile(0.99, sum(rate(apiserver_request_latencies_bucket{subresource!="log",verb!~"^(?:CONNECT|WATCHLIST|WATCH|PROXY)$"} [10m])) WITHOUT (instance, resource)) / 1e+06 > 1'
for: 2m
labels:
severity: warning
annotations:
summary: Kubernetes API server latency (instance {{ $labels.instance }})
description: "Kubernetes API server has a 99th percentile latency of {{ $value }} seconds for {{ $labels.verb }} {{ $labels.resource }}.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"

View File

@ -0,0 +1,86 @@
groups:
- name: MysqldExporter
rules:
- alert: MysqlDown
expr: 'mysql_up == 0'
for: 0m
labels:
severity: critical
annotations:
summary: MySQL down (instance {{ $labels.instance }})
description: "MySQL instance is down on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: MysqlTooManyConnections(>80%)
expr: 'max_over_time(mysql_global_status_threads_connected[1m]) / mysql_global_variables_max_connections * 100 > 80'
for: 2m
labels:
severity: warning
annotations:
summary: MySQL too many connections (> 80%) (instance {{ $labels.instance }})
description: "More than 80% of MySQL connections are in use on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: MysqlHighThreadsRunning
expr: 'max_over_time(mysql_global_status_threads_running[1m]) / mysql_global_variables_max_connections * 100 > 60'
for: 2m
labels:
severity: warning
annotations:
summary: MySQL high threads running (instance {{ $labels.instance }})
description: "More than 60% of MySQL connections are in running state on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: MysqlSlaveIoThreadNotRunning
expr: '( mysql_slave_status_slave_io_running and ON (instance) mysql_slave_status_master_server_id > 0 ) == 0'
for: 0m
labels:
severity: critical
annotations:
summary: MySQL Slave IO thread not running (instance {{ $labels.instance }})
description: "MySQL Slave IO thread not running on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: MysqlSlaveSqlThreadNotRunning
expr: '( mysql_slave_status_slave_sql_running and ON (instance) mysql_slave_status_master_server_id > 0) == 0'
for: 0m
labels:
severity: critical
annotations:
summary: MySQL Slave SQL thread not running (instance {{ $labels.instance }})
description: "MySQL Slave SQL thread not running on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: MysqlSlaveReplicationLag
expr: '( (mysql_slave_status_seconds_behind_master - mysql_slave_status_sql_delay) and ON (instance) mysql_slave_status_master_server_id > 0 ) > 30'
for: 1m
labels:
severity: critical
annotations:
summary: MySQL Slave replication lag (instance {{ $labels.instance }})
description: "MySQL replication lag on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: MysqlSlowQueries
expr: 'increase(mysql_global_status_slow_queries[1m]) > 0'
for: 2m
labels:
severity: warning
annotations:
summary: MySQL slow queries (instance {{ $labels.instance }})
description: "MySQL server mysql has some new slow query.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: MysqlInnodbLogWaits
expr: 'rate(mysql_global_status_innodb_log_waits[15m]) > 10'
for: 0m
labels:
severity: warning
annotations:
summary: MySQL InnoDB log waits (instance {{ $labels.instance }})
description: "MySQL innodb log writes stalling\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: MysqlRestarted
expr: 'mysql_global_status_uptime < 60'
for: 0m
labels:
severity: info
annotations:
summary: MySQL restarted (instance {{ $labels.instance }})
description: "MySQL has just been restarted, less than one minute ago on {{ $labels.instance }}.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"

View File

@ -29,9 +29,9 @@ scrape_configs:
static_configs:
- targets: ["cadvisor:8080"]
- job_name: "smartctl"
static_configs:
- targets: ["nyyu.dev:9633"]
# - job_name: "smartctl"
# static_configs:
# - targets: ["nyyu.dev:9633"]
- job_name: "node_nyyu"
scheme: https
@ -43,6 +43,18 @@ scrape_configs:
static_configs:
- targets: ["alpine:9100"]
- job_name: "mariadb"
static_configs:
- targets: ["192.168.0.4:9104"]
- job_name: "kube"
static_configs:
- targets: ["192.168.0.4:9122"]
- job_name: "freebox"
static_configs:
- targets: ["192.168.0.4:9091"]
# - job_name: "smokeping"
# static_configs:
# - targets: ["smokeping:9374"]