prometheus, alertmanager: use Prometheus alerts with Alertmanager

For now introduce node-exporter/hosts alert rules, which got taken from
https://samber.github.io/awesome-prometheus-alerts/rules
However with the labels removed from the description, since they don't
render correctly (at least in Telegram) and don't seem to provide much
value, as we render the labels in the notification anyway.

Also only have Telegram as the notification channel for now, as it was
the easiest to set up.
This commit is contained in:
June 2024-10-02 03:36:30 +02:00
parent 803b19de0a
commit 30876f821c
Signed by: june
SSH key fingerprint: SHA256:o9EAq4Y9N9K0pBQeBTqhSDrND5E7oB+60ZNx0U1yPe0
6 changed files with 416 additions and 4 deletions

View file

@ -6,6 +6,12 @@ docker_compose__configuration_files:
content: "{{ lookup('ansible.builtin.file', 'files/chaosknoten/configs/grafana/docker_compose/grafana-datasource.yml') }}"
- name: prometheus.yml
content: "{{ lookup('ansible.builtin.file', 'files/chaosknoten/configs/grafana/docker_compose/prometheus.yml') }}"
- name: alertmanager.yaml
content: "{{ lookup('ansible.builtin.template', 'templates/chaosknoten/configs/grafana/docker_compose/alertmanager.yaml.j2') }}"
- name: prometheus_alerts.rules.yaml
content: "{{ lookup('ansible.builtin.file', 'files/chaosknoten/configs/grafana/docker_compose/prometheus_alerts.rules.yaml') }}"
- name: alertmanager_alert_templates.tmpl
content: "{{ lookup('ansible.builtin.file', 'files/chaosknoten/configs/grafana/docker_compose/alertmanager_alert_templates.tmpl') }}"
certbot__version_spec: ""
certbot__acme_account_email_address: le-admin@hamburg.ccc.de

View file

@ -0,0 +1,35 @@
{{/*
Links & Resources
- https://prometheus.io/blog/2016/03/03/custom-alertmanager-templates/
- https://prometheus.io/docs/alerting/latest/notifications/
- https://gist.github.com/jidckii/5ac5f8f20368b56de72af70222509b7b
*/}}
{{ define "alert-item.telegram.ccchh.internal" }}
<b>[{{ .Labels.alertname }}] {{ .Labels.nodename }}</b>
{{- if .Annotations.summary }}
<i>Summary</i>: {{ .Annotations.summary }}
{{- end }}
{{- if .Annotations.description }}
<i>Description</i>: {{ .Annotations.description }}
{{- end }}
<i>Labels</i>:
{{ range .Labels.SortedPairs -}}
• <i>{{ .Name }}</i>: <code>{{ .Value }}</code>
{{ end }}
{{- end }}
{{ define "alert-message.telegram.ccchh" }}
{{- if .Alerts.Firing }}
<u>🔥{{ len .Alerts.Firing }} Alert(/s) Firing 🔥</u>
{{ range .Alerts.Firing -}}
{{ template "alert-item.telegram.ccchh.internal" . }}
{{- end }}
{{- end }}
{{- if .Alerts.Resolved }}
<u>✅{{ len .Alerts.Resolved }} Alert(/s) Resolved ✅</u>
{{ range .Alerts.Resolved -}}
{{ template "alert-item.telegram.ccchh.internal" . }}
{{- end }}
{{- end }}
{{- end }}

View file

@ -2,13 +2,18 @@ global:
scrape_interval: 15s
scrape_timeout: 10s
evaluation_interval: 15s
alerting:
alertmanagers:
- static_configs:
- targets: []
scheme: http
- scheme: http
timeout: 10s
api_version: v1
static_configs:
- targets:
- "alertmanager:9093"
rule_files:
- "/etc/prometheus/rules/*.rules.yaml"
scrape_configs:
- job_name: prometheus
honor_timestamps: true

View file

@ -0,0 +1,313 @@
# Links & Resources:
# - https://samber.github.io/awesome-prometheus-alerts/rules
groups:
- name: node-exporter
rules:
- alert: HostOutOfMemory
expr: (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
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 }}"
- alert: HostMemoryUnderMemoryPressure
expr: (rate(node_vmstat_pgmajfault[1m]) > 1000) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
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 }}"
# You may want to increase the alert manager 'repeat_interval' for this type of alert to daily or weekly
- alert: HostMemoryIsUnderutilized
expr: (100 - (avg_over_time(node_memory_MemAvailable_bytes[30m]) / node_memory_MemTotal_bytes * 100) < 20) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 1w
labels:
severity: info
annotations:
summary: Host Memory is underutilized (instance {{ $labels.instance }})
description: "Node memory is < 20% for 1 week. Consider reducing memory space. (instance {{ $labels.instance }})\n VALUE = {{ $value }}"
- alert: HostUnusualNetworkThroughputIn
expr: (sum by (instance) (rate(node_network_receive_bytes_total[2m])) / 1024 / 1024 > 100) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
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 }}"
- alert: HostUnusualNetworkThroughputOut
expr: (sum by (instance) (rate(node_network_transmit_bytes_total[2m])) / 1024 / 1024 > 100) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
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 }}"
- alert: HostUnusualDiskReadRate
expr: (sum by (instance) (rate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
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 }}"
- alert: HostUnusualDiskWriteRate
expr: (sum by (instance) (rate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
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 = {{ $value }}"
# Please add ignored mountpoints in node_exporter parameters like
# "--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|run)($|/)".
# 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) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 2m
labels:
severity: warning
annotations:
summary: Host out of disk space (instance {{ $labels.instance }})
description: "Disk is almost full (< 10% left)\n VALUE = {{ $value }}"
# Please add ignored mountpoints in node_exporter parameters like
# "--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|run)($|/)".
# 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) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
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 }}"
- alert: HostOutOfInodes
expr: (node_filesystem_files_free{fstype!="msdosfs"} / node_filesystem_files{fstype!="msdosfs"} * 100 < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
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 }}"
- alert: HostInodesWillFillIn24Hours
expr: (node_filesystem_files_free{fstype!="msdosfs"} / node_filesystem_files{fstype!="msdosfs"} * 100 < 10 and predict_linear(node_filesystem_files_free{fstype!="msdosfs"}[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly{fstype!="msdosfs"} == 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
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 }}"
- alert: HostFilesystemDeviceError
expr: node_filesystem_device_error == 1
for: 2m
labels:
severity: critical
annotations:
summary: Host filesystem device error (instance {{ $labels.instance }})
description: "{{ $labels.instance }}: Device error with the {{ $labels.mountpoint }} filesystem\n VALUE = {{ $value }}"
- 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) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
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 }}"
- 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) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
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 }}"
- alert: HostHighCpuLoad
expr: (sum by (instance) (avg by (mode, instance) (rate(node_cpu_seconds_total{mode!="idle"}[2m]))) > 0.8) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 10m
labels:
severity: warning
annotations:
summary: Host high CPU load (instance {{ $labels.instance }})
description: "CPU load is > 80%\n VALUE = {{ $value }}"
# We might want to introduce that later, tho maybe excluding hosts with one core, if possible and only for VMs?
# # You may want to increase the alert manager 'repeat_interval' for this type of alert to daily or weekly
# - alert: HostCpuIsUnderutilized
# expr: (100 - (rate(node_cpu_seconds_total{mode="idle"}[30m]) * 100) < 20) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
# for: 1w
# labels:
# severity: info
# annotations:
# summary: Host CPU is underutilized (instance {{ $labels.instance }})
# description: "CPU load is < 20% for 1 week. Consider reducing the number of CPUs.\n VALUE = {{ $value }}"
- alert: HostCpuStealNoisyNeighbor
expr: (avg by(instance) (rate(node_cpu_seconds_total{mode="steal"}[5m])) * 100 > 10) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
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 }}"
- alert: HostCpuHighIowait
expr: (avg by (instance) (rate(node_cpu_seconds_total{mode="iowait"}[5m])) * 100 > 10) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 0m
labels:
severity: warning
annotations:
summary: Host CPU high iowait (instance {{ $labels.instance }})
description: "CPU iowait > 10%. A high iowait means that you are disk or network bound.\n VALUE = {{ $value }}"
- alert: HostUnusualDiskIo
expr: (rate(node_disk_io_time_seconds_total[1m]) > 0.5) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 5m
labels:
severity: warning
annotations:
summary: Host unusual disk IO (instance {{ $labels.instance }})
description: "Time spent in IO is too high on {{ $labels.instance }}. Check storage for issues.\n VALUE = {{ $value }}"
# # x2 context switches is an arbitrary number.
# # The alert threshold depends on the nature of the application.
# # Please read: https://github.com/samber/awesome-prometheus-alerts/issues/58
# - alert: HostContextSwitchingHigh
# expr: (rate(node_context_switches_total[15m])/count without(mode,cpu) (node_cpu_seconds_total{mode="idle"})) / (rate(node_context_switches_total[1d])/count without(mode,cpu) (node_cpu_seconds_total{mode="idle"})) > 2
# for: 0m
# labels:
# severity: warning
# annotations:
# summary: Host context switching high (instance {{ $labels.instance }})
# description: "Context switching is growing on the node (twice the daily average during the last 15m)\n VALUE = {{ $value }}"
- alert: HostSwapIsFillingUp
expr: ((1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes)) * 100 > 80) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 2m
labels:
severity: warning
annotations:
summary: Host swap is filling up (instance {{ $labels.instance }})
description: "Swap is filling up (>80%)\n VALUE = {{ $value }}"
- alert: HostSystemdServiceCrashed
expr: (node_systemd_unit_state{state="failed"} == 1) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 0m
labels:
severity: warning
annotations:
summary: Host systemd service crashed (instance {{ $labels.instance }})
description: "systemd service crashed\n VALUE = {{ $value }}"
- alert: HostPhysicalComponentTooHot
expr: ((node_hwmon_temp_celsius * ignoring(label) group_left(instance, job, node, sensor) node_hwmon_sensor_label{label!="tctl"} > 75)) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 5m
labels:
severity: warning
annotations:
summary: Host physical component too hot (instance {{ $labels.instance }})
description: "Physical hardware component too hot\n VALUE = {{ $value }}"
- alert: HostNodeOvertemperatureAlarm
expr: ((node_hwmon_temp_crit_alarm_celsius == 1) or (node_hwmon_temp_alarm == 1)) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 0m
labels:
severity: critical
annotations:
summary: Host node overtemperature alarm (instance {{ $labels.instance }})
description: "Physical node temperature alarm triggered\n VALUE = {{ $value }}"
- alert: HostRaidArrayGotInactive
expr: (node_md_state{state="inactive"} > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 0m
labels:
severity: critical
annotations:
summary: Host RAID array got inactive (instance {{ $labels.instance }})
description: "RAID array {{ $labels.device }} is in a degraded state due to one or more disk failures. The number of spare drives is insufficient to fix the issue automatically.\n VALUE = {{ $value }}"
- alert: HostRaidDiskFailure
expr: (node_md_disks{state="failed"} > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
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 }}"
- alert: HostKernelVersionDeviations
expr: (count(sum(label_replace(node_uname_info, "kernel", "$1", "release", "([0-9]+.[0-9]+.[0-9]+).*")) by (kernel)) > 1) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 6h
labels:
severity: warning
annotations:
summary: Host kernel version deviations (instance {{ $labels.instance }})
description: "Different kernel versions are running\n VALUE = {{ $value }}"
- alert: HostOomKillDetected
expr: (increase(node_vmstat_oom_kill[1m]) > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 0m
labels:
severity: warning
annotations:
summary: Host OOM kill detected (instance {{ $labels.instance }})
description: "OOM kill detected\n VALUE = {{ $value }}"
- alert: HostEdacCorrectableErrorsDetected
expr: (increase(node_edac_correctable_errors_total[1m]) > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
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 }}"
- alert: HostEdacUncorrectableErrorsDetected
expr: (node_edac_uncorrectable_errors_total > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
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 }}"
- alert: HostNetworkReceiveErrors
expr: (rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
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 }}"
- alert: HostNetworkTransmitErrors
expr: (rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
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 }}"
- alert: HostNetworkBondDegraded
expr: ((node_bonding_active - node_bonding_slaves) != 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
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 }}"
- alert: HostConntrackLimit
expr: (node_nf_conntrack_entries / node_nf_conntrack_entries_limit > 0.8) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 5m
labels:
severity: warning
annotations:
summary: Host conntrack limit (instance {{ $labels.instance }})
description: "The number of conntrack is approaching limit\n VALUE = {{ $value }}"
- 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)) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 10m
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 }}"
- alert: HostClockNotSynchronising
expr: (min_over_time(node_timex_sync_status[1m]) == 0 and node_timex_maxerror_seconds >= 16) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
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 }}"
- alert: HostRequiresReboot
expr: (node_reboot_required > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 4h
labels:
severity: info
annotations:
summary: Host requires reboot (instance {{ $labels.instance }})
description: "{{ $labels.instance }} requires a reboot.\n VALUE = {{ $value }}"

View file

@ -11,7 +11,20 @@ services:
restart: unless-stopped
volumes:
- ./configs/prometheus.yml:/etc/prometheus/prometheus.yml
- ./configs/prometheus_alerts.rules.yaml:/etc/prometheus/rules/alerts.rules.yaml
- prom_data:/prometheus
alertmanager:
image: prom/alertmanager
container_name: alertmanager
command:
- '--config.file=/etc/alertmanager/alertmanager.yaml'
ports:
- 9093:9093
restart: unless-stopped
volumes:
- ./configs/alertmanager.yaml:/etc/alertmanager/alertmanager.yaml
- ./configs/alertmanager_alert_templates.tmpl:/etc/alertmanager/templates/alert_templates.tmpl
grafana:
image: grafana/grafana

View file

@ -0,0 +1,40 @@
# Links & References:
# - https://prometheus.io/docs/alerting/latest/configuration/
# - https://github.com/prometheus/alertmanager/blob/48a99764a1fc9279fc828de83e7a03ae2219abc7/doc/examples/simple.yml
route:
group_by: ["alertname", "site", "type", "hypervisor"]
group_wait: 30s
group_interval: 5m
repeat_interval: 3h
receiver: ccchh-infrastructure-alerts
{# Disable these for now, but might be interesting in the future.
# Inhibition rules allow to mute a set of alerts given that another alert is
# firing.
# We use this to mute any warning-level notifications if the same alert is
# already critical.
inhibit_rules:
- source_matchers: [severity="critical"]
target_matchers: [severity="warning"]
# Apply inhibition if the alertname is the same.
# CAUTION:
# If all label names listed in `equal` are missing
# from both the source and target alerts,
# the inhibition rule will apply!
equal: [alertname, cluster, service] #}
templates:
- "/etc/alertmanager/templates/*.tmpl"
receivers:
- name: "ccchh-infrastructure-alerts"
telegram_configs:
- send_resolved: true
bot_token: {{ lookup("community.general.passwordstore", "noc/vm-secrets/chaosknoten/grafana/alertmanager_telegram_bot_token", create=false, missing="error") }}
chat_id: -1002434372415
parse_mode: HTML
message: {{ "'{{ template \"alert-message.telegram.ccchh\" . }}'" }}