try to fix prometheus deployment 6 (final) (for now)

This commit is contained in:
Aaron Riedel 2023-06-20 13:15:28 +02:00
parent c706f9b61e
commit e63707d16c
Signed by: aaron
GPG key ID: 643004654D40D577
3 changed files with 38 additions and 149 deletions

1
.gitignore vendored Normal file
View file

@ -0,0 +1 @@
**/secret.yaml

View file

@ -4,9 +4,11 @@ kind: PrometheusRule
metadata:
name: prometheus-core-deployment-rules
namespace: prometheus
labels:
monitor: core-deployment
spec:
groups:
- name: memory_high
- name: hardware
rules:
- alert: MemoryHigh
expr: round((((node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes) * 100), 0.1) > 80
@ -16,9 +18,7 @@ spec:
annotations:
summary: "Memory over 80%"
description: "Memory on node {{ $labels.node }} is over 80% for more than 5 minutes. Plox fix. Memory usage: {{ $value }}%"
- name: diskspace_low_worker
rules:
- alert: DiskspaceLow
- alert: DiskspaceLowWorker
expr: round(node_filesystem_avail_bytes{mountpoint="/", node=~"worker.*"} / 1073742000, 0.1) < 50
for: 1m
labels:
@ -26,9 +26,7 @@ spec:
annotations:
summary: "Free disk space below 10 GB"
description: "Disk space on server {{ $labels.node }} is under 10 GB. Plox fix. Free Space: {{ $value }} GB on partition {{ $labels.device }}"
- name: diskspace_low_master
rules:
- alert: DiskspaceLow
- alert: DiskspaceLowMaster
expr: round(node_filesystem_avail_bytes{mountpoint="/", node=~"master.*"} / 1073742000, 0.1) < 10
for: 1m
labels:
@ -36,7 +34,62 @@ spec:
annotations:
summary: "Free disk space below 2 GB"
description: "Disk space on server {{ $labels.node }} is under 2 GB. Plox fix. Free Space: {{ $value }} GB on partition {{ $labels.device }}"
- name: KubernetesUnhealthyPod
- alert: HostMemoryUnderMemoryPressure
expr: rate(node_vmstat_pgmajfault[1m]) > 1000
for: 2m
labels:
severity: warning
annotations:
summary: Host memory under memory pressure {{ $labels.node }}
description: "The node is under heavy memory pressure. High rate of major page faults\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostUnusualDiskReadRate
expr: sum by (instance) (rate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 200
for: 5m
labels:
severity: warning
annotations:
summary: Host unusual disk read rate {{ $labels.node }}
description: "Disk is probably reading too much data (> 200 MB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostUnusualDiskWriteRate
expr: sum by (instance) (rate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 200
for: 3m
labels:
severity: warning
annotations:
summary: Host unusual disk write rate {{ $labels.node }}
description: "Disk is probably writing too much data (> 200 MB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostCpuStealNoisyNeighbor
expr: avg by(instance) (rate(node_cpu_seconds_total{mode="steal"}[5m])) * 100 > 10
for: 1m
labels:
severity: warning
annotations:
summary: Host CPU steal noisy neighbor {{ $labels.node }}
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: HostPhysicalComponentTooHot
expr: node_hwmon_temp_celsius > 85
for: 5m
labels:
severity: warning
annotations:
summary: Host physical component too hot {{ $labels.node }}
description: "Physical hardware component too hot\n Sensor = {{ $labels.sensor }}\n Temp = {{ $value }}"
- alert: SMARTbad
expr: smartmon_device_smart_healthy < 1
for: 0m
labels:
severity: critical
annotations:
summary: SMART check bad of drive {{ $labels.exported_disk }} in server {{ $labels.node }}
description: "SMART check returned bad health of {{ $labels.exported_disk }} in server {{ $labels.node }}. VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: "SMARTcheck too old"
expr: (time() - smartmon_smartctl_run) > 10800
labels:
severity: warning
annotations:
summary: "SMARTcheck not running"
description: 'The last SMARTcheck on server {{ $labels.node }} was more than 3h ago. Plox fix.'
- name: kubernetes
rules:
- alert: KubernetesUnhealthyPod
expr: kube_pod_container_status_waiting_reason == 1
@ -46,142 +99,3 @@ spec:
annotations:
summary: "The Pod {{ $labels.pod }} is {{ $labels.reason }}"
description: "The Pod {{ $labels.pod }} is in the state {{ $labels.reason }} for more than 5m. The Pod is in namespace {{ $labels.namespace }} and on node {{ $labels.node }}."
- name: PrometheusTargetMissing
rules:
- alert: PrometheusTargetMissing
expr: up == 0
for: 3m
labels:
severity: critical
annotations:
summary: Prometheus target missing (instance {{ $labels.instance }})
description: "A Prometheus target has disappeared. {{if ne $labels.job \"\"}}\n Job: {{ $labels.job }}{{end}}{{if ne $labels.app \"\"}}\n App: {{ $labels.app }}{{end}}{{if ne $labels.pod \"\"}}\n Pod: {{ $labels.pod }}{{end}}{{if ne $labels.node \"\"}}\n Node: {{ $labels.node }}{{end}}{{if ne $labels.namespace \"\"}}\n Namespace: {{ $labels.namespace }}{{end}}"
- name: PrometheusConfigurationReloadFailure
rules:
- alert: PrometheusConfigurationReloadFailure
expr: prometheus_config_last_reload_successful != 1
for: 3m
labels:
severity: critical
annotations:
summary: Prometheus configuration reload failure (instance {{ $labels.instance }})
description: "Prometheus configuration reload error\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- name: PrometheusAlertmanagerConfigurationReloadFailure
rules:
- alert: PrometheusAlertmanagerConfigurationReloadFailure
expr: alertmanager_config_last_reload_successful != 1
for: 3m
labels:
severity: critical
annotations:
summary: Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }})
description: "AlertManager configuration reload error\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- name: PrometheusAlertmanagerConfigNotSynced
rules:
- alert: PrometheusAlertmanagerConfigNotSynced
expr: count(count_values("config_hash", alertmanager_config_hash)) > 1
for: 3m
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 }}"
- name: PrometheusTargetEmpty
rules:
- alert: PrometheusTargetEmpty
expr: prometheus_sd_discovered_targets == 0
for: 3m
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 }}"
- name: PrometheusTargetScrapingSlow
rules:
- alert: PrometheusTargetScrapingSlow
expr: prometheus_target_interval_length_seconds{quantile="0.9"} > 120
for: 5m
labels:
severity: warning
annotations:
summary: Prometheus target scraping (instance {{ $labels.instance }})
description: "Prometheus is scraping exporters ly\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- name: PrometheusLargeScrape
rules:
- 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 }}"
- name: HostMemoryUnderMemoryPressure
rules:
- alert: HostMemoryUnderMemoryPressure
expr: rate(node_vmstat_pgmajfault[1m]) > 1000
for: 2m
labels:
severity: warning
annotations:
summary: Host memory under memory pressure {{ $labels.node }}
description: "The node is under heavy memory pressure. High rate of major page faults\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- name: HostUnusualDiskReadRate
rules:
- alert: HostUnusualDiskReadRate
expr: sum by (instance) (rate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 200
for: 5m
labels:
severity: warning
annotations:
summary: Host unusual disk read rate {{ $labels.node }}
description: "Disk is probably reading too much data (> 200 MB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- name: HostUnusualDiskWriteRate
rules:
- alert: HostUnusualDiskWriteRate
expr: sum by (instance) (rate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 200
for: 3m
labels:
severity: warning
annotations:
summary: Host unusual disk write rate {{ $labels.node }}
description: "Disk is probably writing too much data (> 200 MB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- name: HostCpuStealNoisyNeighbor
rules:
- alert: HostCpuStealNoisyNeighbor
expr: avg by(instance) (rate(node_cpu_seconds_total{mode="steal"}[5m])) * 100 > 10
for: 1m
labels:
severity: warning
annotations:
summary: Host CPU steal noisy neighbor {{ $labels.node }}
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 }}"
- name: HostPhysicalComponentTooHot
rules:
- alert: HostPhysicalComponentTooHot
expr: node_hwmon_temp_celsius > 85
for: 5m
labels:
severity: warning
annotations:
summary: Host physical component too hot {{ $labels.node }}
description: "Physical hardware component too hot\n Sensor = {{ $labels.sensor }}\n Temp = {{ $value }}"
- name: SMARTbad
rules:
- alert: SMARTbad
expr: smartmon_device_smart_healthy < 1
for: 0m
labels:
severity: critical
annotations:
summary: SMART check bad of drive {{ $labels.exported_disk }} in server {{ $labels.node }}
description: "SMART check returned bad health of {{ $labels.exported_disk }} in server {{ $labels.node }}. VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- name: SMARTcheck_old
rules:
- alert: "SMARTcheck too old"
expr: (time() - smartmon_smartctl_run) > 10800
labels:
severity: warning
annotations:
summary: "SMARTcheck not running"
description: 'The last SMARTcheck on server {{ $labels.node }} was more than 3h ago. Plox fix.'

View file

@ -1,53 +1,14 @@
alertmanager:
alertmanagerSpec:
image:
registry: registry-1.docker.io
repository: aaronriedel/alertmanager
tag: latest
replicas: 2
config:
global:
resolve_timeout: 5m
templates:
- '/etc/alertmanager/config/*.tmpl'
route:
group_by: ['alertname']
group_wait: 30s
group_interval: 30s
repeat_interval: 24h
receiver: 'tg1'
routes:
- matchers:
- severity=warning
receiver: 'tg1'
- matchers:
- severity=critical
receiver: 'tg1'
receivers:
- name: tg1
telegram_configs:
- bot_token_file: '/etc/alertmanager/telegram-token/api_key'
chat_id: -995270884
api_url: "https://api.telegram.org"
send_resolved: true
parse_mode: "HTML"
message: '{{ template "telegram.aaron" .}}'
inhibit_rules:
- source_matchers:
- severity = critical
target_matchers:
- severity = warning
equal: ['alertname', 'server', 'instance']
templateFiles:
telegram.tmpl: |-
{{ define "telegram.aaron" }}
{{ range .Alerts }}
{{ if eq .Status "firing"}}🔥 <b>{{ .Labels.alertname }}</b> 🔥{{ else }}✅ <b>{{ .Labels.alertname }}</b> ✅{{ end }}
<b> {{ .Annotations.summary }} </b>
{{ .Annotations.description }}
{{ end }}
{{ end }}
storage:
volumeClaimTemplate:
spec:
accessModes: ["ReadWriteOnce"]
resources:
requests:
storage: 5Gi
useExistingSecret: true
ingress:
paths:
- /
@ -105,5 +66,18 @@ prometheus:
nginx.org/basic-auth-secret: prometheus-basic-auth-secret
prometheusSpec:
replicas: 2
storageSpec:
volumeClaimTemplate:
spec:
accessModes: ["ReadWriteOnce"]
resources:
requests:
storage: 10Gi
ruleNamespaceSelector: {}
ruleSelectorNilUsesHelmValues: false
serviceMonitorSelectorNilUsesHelmValues: false
podMonitorSelectorNilUsesHelmValues: false
probeSelectorNilUsesHelmValues: false
scrapeConfigSelectorNilUsesHelmValues: false
servicePerReplica:
enabled: true