root@cby:~# mkdir /prometheus/dist/
root@cby:~# vim /prometheus/dist/123.yml
root@cby:~# cat /prometheus/dist/123.yml
groups:
- name: generals.rules
rules:
- alert: PrometheusJobMissing
expr: absent(up{job="prometheus"})
for: 0m
labels:
severity: warning
annotations:
summary: Prometheus job missing (instance {{ $labels.instance }})
description: "A Prometheus job has disappeared\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusTargetMissing
expr: up == 0
for: 0m
labels:
severity: critical
annotations:
summary: Prometheus target missing (instance {{ $labels.instance }})
description: "A Prometheus target has disappeared. An exporter might be crashed.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusAllTargetsMissing
expr: sum by (job) (up) == 0
for: 0m
labels:
severity: critical
annotations:
summary: Prometheus all targets missing (instance {{ $labels.instance }})
description: "A Prometheus job does not have living target anymore.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusTargetMissingWithWarmupTime
expr: sum by (instance, job) ((up == 0) * on (instance) group_right(job) (node_time_seconds - node_boot_time_seconds > 600))
for: 0m
labels:
severity: critical
annotations:
summary: Prometheus target missing with warmup time (instance {{ $labels.instance }})
description: "Allow a job time to start up (10 minutes) before alerting that it's down.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusConfigurationReloadFailure
expr: prometheus_config_last_reload_successful != 1
for: 0m
labels:
severity: warning
annotations:
summary: Prometheus configuration reload failure (instance {{ $labels.instance }})
description: "Prometheus configuration reload error\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusTooManyRestarts
expr: changes(process_start_time_seconds{job=~"prometheus|pushgateway|alertmanager"}[15m]) > 2
for: 0m
labels:
severity: warning
annotations:
summary: Prometheus too many restarts (instance {{ $labels.instance }})
description: "Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusAlertmanagerJobMissing
expr: absent(up{job="alertmanager"})
for: 0m
labels:
severity: warning
annotations:
summary: Prometheus AlertManager job missing (instance {{ $labels.instance }})
description: "A Prometheus AlertManager job has disappeared\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusAlertmanagerConfigurationReloadFailure
expr: alertmanager_config_last_reload_successful != 1
for: 0m
labels:
severity: warning
annotations:
summary: Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }})
description: "AlertManager configuration reload error\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusAlertmanagerConfigNotSynced
expr: count(count_values("config_hash", alertmanager_config_hash)) > 1
for: 0m
labels:
severity: warning
annotations:
summary: Prometheus AlertManager config not synced (instance {{ $labels.instance }})
description: "Configurations of AlertManager cluster instances are out of sync\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusAlertmanagerE2eDeadManSwitch
expr: vector(1)
for: 0m
labels:
severity: critical
annotations:
summary: Prometheus AlertManager E2E dead man switch (instance {{ $labels.instance }})
description: "Prometheus DeadManSwitch is an always-firing alert. It's used as an end-to-end test of Prometheus through the Alertmanager.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusNotConnectedToAlertmanager
expr: prometheus_notifications_alertmanagers_discovered < 1
for: 0m
labels:
severity: critical
annotations:
summary: Prometheus not connected to alertmanager (instance {{ $labels.instance }})
description: "Prometheus cannot connect the alertmanager\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusRuleEvaluationFailures
expr: increase(prometheus_rule_evaluation_failures_total[3m]) > 0
for: 0m
labels:
severity: critical
annotations:
summary: Prometheus rule evaluation failures (instance {{ $labels.instance }})
description: "Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusTemplateTextExpansionFailures
expr: increase(prometheus_template_text_expansion_failures_total[3m]) > 0
for: 0m
labels:
severity: critical
annotations:
summary: Prometheus template text expansion failures (instance {{ $labels.instance }})
description: "Prometheus encountered {{ $value }} template text expansion failures\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusRuleEvaluationSlow
expr: prometheus_rule_group_last_duration_seconds > prometheus_rule_group_interval_seconds
for: 5m
labels:
severity: warning
annotations:
summary: Prometheus rule evaluation slow (instance {{ $labels.instance }})
description: "Prometheus rule evaluation took more time than the scheduled interval. It indicates a slower storage backend access or too complex query.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusNotificationsBacklog
expr: min_over_time(prometheus_notifications_queue_length[10m]) > 0
for: 0m
labels:
severity: warning
annotations:
summary: Prometheus notifications backlog (instance {{ $labels.instance }})
description: "The Prometheus notification queue has not been empty for 10 minutes\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusAlertmanagerNotificationFailing
expr: rate(alertmanager_notifications_failed_total[1m]) > 0
for: 0m
labels:
severity: critical
annotations:
summary: Prometheus AlertManager notification failing (instance {{ $labels.instance }})
description: "Alertmanager is failing sending notifications\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusTargetEmpty
expr: prometheus_sd_discovered_targets == 0
for: 0m
labels:
severity: critical
annotations:
summary: Prometheus target empty (instance {{ $labels.instance }})
description: "Prometheus has no target in service discovery\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusTargetScrapingSlow
expr: prometheus_target_interval_length_seconds{quantile="0.9"} / on (interval, instance, job) prometheus_target_interval_length_seconds{quantile="0.5"} > 1.05
for: 5m
labels:
severity: warning
annotations:
summary: Prometheus target scraping slow (instance {{ $labels.instance }})
description: "Prometheus is scraping exporters slowly since it exceeded the requested interval time. Your Prometheus server is under-provisioned.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusLargeScrape
expr: increase(prometheus_target_scrapes_exceeded_sample_limit_total[10m]) > 10
for: 5m
labels:
severity: warning
annotations:
summary: Prometheus large scrape (instance {{ $labels.instance }})
description: "Prometheus has many scrapes that exceed the sample limit\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusTargetScrapeDuplicate
expr: increase(prometheus_target_scrapes_sample_duplicate_timestamp_total[5m]) > 0
for: 0m
labels:
severity: warning
annotations:
summary: Prometheus target scrape duplicate (instance {{ $labels.instance }})
description: "Prometheus has many samples rejected due to duplicate timestamps but different values\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusTsdbCheckpointCreationFailures
expr: increase(prometheus_tsdb_checkpoint_creations_failed_total[1m]) > 0
for: 0m
labels:
severity: critical
annotations:
summary: Prometheus TSDB checkpoint creation failures (instance {{ $labels.instance }})
description: "Prometheus encountered {{ $value }} checkpoint creation failures\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusTsdbCheckpointDeletionFailures
expr: increase(prometheus_tsdb_checkpoint_deletions_failed_total[1m]) > 0
for: 0m
labels:
severity: critical
annotations:
summary: Prometheus TSDB checkpoint deletion failures (instance {{ $labels.instance }})
description: "Prometheus encountered {{ $value }} checkpoint deletion failures\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusTsdbCompactionsFailed
expr: increase(prometheus_tsdb_compactions_failed_total[1m]) > 0
for: 0m
labels:
severity: critical
annotations:
summary: Prometheus TSDB compactions failed (instance {{ $labels.instance }})
description: "Prometheus encountered {{ $value }} TSDB compactions failures\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusTsdbHeadTruncationsFailed
expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) > 0
for: 0m
labels:
severity: critical
annotations:
summary: Prometheus TSDB head truncations failed (instance {{ $labels.instance }})
description: "Prometheus encountered {{ $value }} TSDB head truncation failures\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusTsdbReloadFailures
expr: increase(prometheus_tsdb_reloads_failures_total[1m]) > 0
for: 0m
labels:
severity: critical
annotations:
summary: Prometheus TSDB reload failures (instance {{ $labels.instance }})
description: "Prometheus encountered {{ $value }} TSDB reload failures\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusTsdbWalCorruptions
expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) > 0
for: 0m
labels:
severity: critical
annotations:
summary: Prometheus TSDB WAL corruptions (instance {{ $labels.instance }})
description: "Prometheus encountered {{ $value }} TSDB WAL corruptions\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusTsdbWalTruncationsFailed
expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) > 0
for: 0m
labels:
severity: critical
annotations:
summary: Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }})
description: "Prometheus encountered {{ $value }} TSDB WAL truncation failures\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PrometheusTimeserieCardinality
expr: label_replace(count by(__name__) ({__name__=~".+"}), "name", "$1", "__name__", "(.+)") > 10000
for: 0m
labels:
severity: warning
annotations:
summary: Prometheus timeserie cardinality (instance {{ $labels.instance }})
description: "The \"{{ $labels.name }}\" timeserie cardinality is getting very high: {{ $value }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostOutOfMemory
expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10
for: 2m
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: 2m
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 }}"
- alert: HostUnusualNetworkThroughputIn
expr: sum by (instance) (rate(node_network_receive_bytes_total[2m])) / 1024 / 1024 > 100
for: 5m
labels:
severity: warning
annotations:
summary: Host unusual network throughput in (instance {{ $labels.instance }})
description: "Host network interfaces are probably receiving too much data (> 100 MB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostUnusualNetworkThroughputOut
expr: sum by (instance) (rate(node_network_transmit_bytes_total[2m])) / 1024 / 1024 > 100
for: 5m
labels:
severity: warning
annotations:
summary: Host unusual network throughput out (instance {{ $labels.instance }})
description: "Host network interfaces are probably sending too much data (> 100 MB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostUnusualDiskReadRate
expr: sum by (instance) (rate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50
for: 5m
labels:
severity: warning
annotations:
summary: Host unusual disk read rate (instance {{ $labels.instance }})
description: "Disk is probably reading too much data (> 50 MB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostUnusualDiskWriteRate
expr: sum by (instance) (rate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50
for: 2m
labels:
severity: warning
annotations:
summary: Host unusual disk write rate (instance {{ $labels.instance }})
description: "Disk is probably writing too much data (> 50 MB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Please add ignored mountpoints in node_exporter parameters like
# "--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|run)($|/)".
# Same rule using "node_filesystem_free_bytes" will fire when disk fills for non-root users.
- alert: HostOutOfDiskSpace
expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0
for: 2m
labels:
severity: warning
annotations:
summary: Host out of disk space (instance {{ $labels.instance }})
description: "Disk is almost full (< 10% left)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Please add ignored mountpoints in node_exporter parameters like
# "--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|run)($|/)".
# Same rule using "node_filesystem_free_bytes" will fire when disk fills for non-root users.
- alert: HostDiskWillFillIn24Hours
expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) predict_linear(node_filesystem_avail_bytes{fstype!~"tmpfs"}[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly == 0
for: 2m
labels:
severity: warning
annotations:
summary: Host disk will fill in 24 hours (instance {{ $labels.instance }})
description: "Filesystem is predicted to run out of space within the next 24 hours at current write rate\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostOutOfInodes
expr: node_filesystem_files_free / node_filesystem_files * 100 < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0
for: 2m
labels:
severity: warning
annotations:
summary: Host out of inodes (instance {{ $labels.instance }})
description: "Disk is almost running out of available inodes (< 10% left)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostInodesWillFillIn24Hours
expr: node_filesystem_files_free / node_filesystem_files * 100 < 10 and predict_linear(node_filesystem_files_free[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly == 0
for: 2m
labels:
severity: warning
annotations:
summary: Host inodes will fill in 24 hours (instance {{ $labels.instance }})
description: "Filesystem is predicted to run out of inodes within the next 24 hours at current write rate\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostUnusualDiskReadLatency
expr: rate(node_disk_read_time_seconds_total[1m]) / rate(node_disk_reads_completed_total[1m]) > 0.1 and rate(node_disk_reads_completed_total[1m]) > 0
for: 2m
labels:
severity: warning
annotations:
summary: Host unusual disk read latency (instance {{ $labels.instance }})
description: "Disk latency is growing (read operations > 100ms)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostUnusualDiskWriteLatency
expr: rate(node_disk_write_time_seconds_total[1m]) / rate(node_disk_writes_completed_total[1m]) > 0.1 and rate(node_disk_writes_completed_total[1m]) > 0
for: 2m
labels:
severity: warning
annotations:
summary: Host unusual disk write latency (instance {{ $labels.instance }})
description: "Disk latency is growing (write operations > 100ms)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostHighCpuLoad
expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[2m])) * 100) > 80
for: 0m
labels:
severity: warning
annotations:
summary: Host high CPU load (instance {{ $labels.instance }})
description: "CPU load is > 80%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostCpuStealNoisyNeighbor
expr: avg by(instance) (rate(node_cpu_seconds_total{mode="steal"}[5m])) * 100 > 10
for: 0m
labels:
severity: warning
annotations:
summary: Host CPU steal noisy neighbor (instance {{ $labels.instance }})
description: "CPU steal is > 10%. A noisy neighbor is killing VM performances or a spot instance may be out of credit.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostCpuHighIowait
expr: avg by (instance) (rate(node_cpu_seconds_total{mode="iowait"}[5m])) * 100 > 5
for: 0m
labels:
severity: warning
annotations:
summary: Host CPU high iowait (instance {{ $labels.instance }})
description: "CPU iowait > 5%. A high iowait means that you are disk or network bound.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# 1000 context switches is an arbitrary number.
# Alert threshold depends on nature of application.
# Please read: https://github.com/samber/awesome-prometheus-alerts/issues/58
- alert: HostContextSwitching
expr: (rate(node_context_switches_total[5m])) / (count without(cpu, mode) (node_cpu_seconds_total{mode="idle"})) > 1000
for: 0m
labels:
severity: warning
annotations:
summary: Host context switching (instance {{ $labels.instance }})
description: "Context switching is growing on node (> 1000 / s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostSwapIsFillingUp
expr: (1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes)) * 100 > 80
for: 2m
labels:
severity: warning
annotations:
summary: Host swap is filling up (instance {{ $labels.instance }})
description: "Swap is filling up (>80%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostSystemdServiceCrashed
expr: node_systemd_unit_state{state="failed"} == 1
for: 0m
labels:
severity: warning
annotations:
summary: Host systemd service crashed (instance {{ $labels.instance }})
description: "systemd service crashed\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostPhysicalComponentTooHot
expr: node_hwmon_temp_celsius > 75
for: 5m
labels:
severity: warning
annotations:
summary: Host physical component too hot (instance {{ $labels.instance }})
description: "Physical hardware component too hot\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostNodeOvertemperatureAlarm
expr: node_hwmon_temp_crit_alarm_celsius == 1
for: 0m
labels:
severity: critical
annotations:
summary: Host node overtemperature alarm (instance {{ $labels.instance }})
description: "Physical node temperature alarm triggered\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostRaidArrayGotInactive
expr: node_md_state{state="inactive"} > 0
for: 0m
labels:
severity: critical
annotations:
summary: Host RAID array got inactive (instance {{ $labels.instance }})
description: "RAID array {{ $labels.device }} is in degraded state due to one or more disks failures. Number of spare drives is insufficient to fix issue automatically.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostRaidDiskFailure
expr: node_md_disks{state="failed"} > 0
for: 2m
labels:
severity: warning
annotations:
summary: Host RAID disk failure (instance {{ $labels.instance }})
description: "At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostKernelVersionDeviations
expr: count(sum(label_replace(node_uname_info, "kernel", "$1", "release", "([0-9]+.[0-9]+.[0-9]+).*")) by (kernel)) > 1
for: 6h
labels:
severity: warning
annotations:
summary: Host kernel version deviations (instance {{ $labels.instance }})
description: "Different kernel versions are running\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostOomKillDetected
expr: increase(node_vmstat_oom_kill[1m]) > 0
for: 0m
labels:
severity: warning
annotations:
summary: Host OOM kill detected (instance {{ $labels.instance }})
description: "OOM kill detected\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostEdacCorrectableErrorsDetected
expr: increase(node_edac_correctable_errors_total[1m]) > 0
for: 0m
labels:
severity: info
annotations:
summary: Host EDAC Correctable Errors detected (instance {{ $labels.instance }})
description: "Host {{ $labels.instance }} has had {{ printf \"%.0f\" $value }} correctable memory errors reported by EDAC in the last 5 minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostEdacUncorrectableErrorsDetected
expr: node_edac_uncorrectable_errors_total > 0
for: 0m
labels:
severity: warning
annotations:
summary: Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }})
description: "Host {{ $labels.instance }} has had {{ printf \"%.0f\" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostNetworkReceiveErrors
expr: rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01
for: 2m
labels:
severity: warning
annotations:
summary: Host Network Receive Errors (instance {{ $labels.instance }})
description: "Host {{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf \"%.0f\" $value }} receive errors in the last two minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostNetworkTransmitErrors
expr: rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01
for: 2m
labels:
severity: warning
annotations:
summary: Host Network Transmit Errors (instance {{ $labels.instance }})
description: "Host {{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf \"%.0f\" $value }} transmit errors in the last two minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostNetworkInterfaceSaturated
expr: (rate(node_network_receive_bytes_total{device!~"^tap.*|^vnet.*|^veth.*|^tun.*"}[1m]) + rate(node_network_transmit_bytes_total{device!~"^tap.*|^vnet.*|^veth.*|^tun.*"}[1m])) / node_network_speed_bytes{device!~"^tap.*|^vnet.*|^veth.*|^tun.*"} > 0.8 < 10000
for: 1m
labels:
severity: warning
annotations:
summary: Host Network Interface Saturated (instance {{ $labels.instance }})
description: "The network interface \"{{ $labels.device }}\" on \"{{ $labels.instance }}\" is getting overloaded.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostNetworkBondDegraded
expr: (node_bonding_active - node_bonding_slaves) != 0
for: 2m
labels:
severity: warning
annotations:
summary: Host Network Bond Degraded (instance {{ $labels.instance }})
description: "Bond \"{{ $labels.device }}\" degraded on \"{{ $labels.instance }}\".\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostConntrackLimit
expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit > 0.8
for: 5m
labels:
severity: warning
annotations:
summary: Host conntrack limit (instance {{ $labels.instance }})
description: "The number of conntrack is approaching limit\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostClockSkew
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: 2m
labels:
severity: warning
annotations:
summary: Host clock skew (instance {{ $labels.instance }})
description: "Clock skew detected. Clock is out of sync. Ensure NTP is configured correctly on this host.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostClockNotSynchronising
expr: min_over_time(node_timex_sync_status[1m]) == 0 and node_timex_maxerror_seconds >= 16
for: 2m
labels:
severity: warning
annotations:
summary: Host clock not synchronising (instance {{ $labels.instance }})
description: "Clock not synchronising. Ensure NTP is configured on this host.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostRequiresReboot
expr: node_reboot_required > 0
for: 4h
labels:
severity: info
annotations:
summary: Host requires reboot (instance {{ $labels.instance }})
description: "{{ $labels.instance }} requires a reboot.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- 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_status_replicas_ready / kube_statefulset_status_replicas_current) != 1
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: KubernetesPodNotHealthy
expr: min_over_time(sum by (namespace, pod) (kube_pod_status_phase{phase=~"Pending|Unknown|Failed"})[15m:1m]) > 0
for: 0m
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 }}"
root@cby:~#