June
f16f8697c2
Because of how Ansible local relative search paths work, the global "files" and "templates" directories need to be next to the playbooks. However its not intuitive to look into the "playbooks" directory to find the files and templates for a host. Therefore move them out of the "playbooks" directory into the root directory and add symlinks so everything still works. Similarly for local roles, they also need to be next to the playbooks. So for a nicer structure, move the "roles" directory out into the root directory as well and add a symlink so everything still works. Also see: https://docs.ansible.com/ansible/latest/playbook_guide/playbook_pathing.html#resolving-local-relative-paths https://docs.ansible.com/ansible/latest/playbook_guide/playbooks_reuse_roles.html#storing-and-finding-roles
583 lines
34 KiB
YAML
583 lines
34 KiB
YAML
# 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) < 10) * 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 < 10% 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 }}"
|
|
# Have different disk read and write rate alerts for VMs and physical machines.
|
|
- alert: VirtualHostUnusualDiskReadRate
|
|
expr: (sum by (instance) (rate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50) * on(instance) group_left (nodename) node_uname_info{ype="virtual_machine", nodename=~".+", nodename!="forgejo-actions-runner", nodename!="woodpecker"}
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Virtual host unusual disk read rate (instance {{ $labels.instance }})
|
|
description: "Disk is probably reading too much data (> 50 MB/s)\n VALUE = {{ $value }}"
|
|
- alert: VirtualHostUnusualDiskWriteRate
|
|
expr: (sum by (instance) (rate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50) * on(instance) group_left (nodename) node_uname_info{type="virtual_machine", nodename=~".+", nodename!="forgejo-actions-runner", nodename!="woodpecker"}
|
|
for: 2m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Virtual host unusual disk write rate (instance {{ $labels.instance }})
|
|
description: "Disk is probably writing too much data (> 50 MB/s)\n VALUE = {{ $value }}"
|
|
# Some VMs are expected to have high Read / Write rates z.B. CI servers
|
|
- alert: VirtualHostUnusualDiskReadRate
|
|
expr: (sum by (instance) (rate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50) * on(instance) group_left (nodename) node_uname_info{ype="virtual_machine", nodename="forgejo-actions-runner", nodename="woodpecker"}
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Virtual host unusual disk read rate for 10 min (instance {{ $labels.instance }})
|
|
description: "Disk is probably reading too much data (> 50 MB/s)\n VALUE = {{ $value }}"
|
|
- alert: VirtualHostUnusualDiskWriteRate
|
|
expr: (sum by (instance) (rate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50) * on(instance) group_left (nodename) node_uname_info{type="virtual_machine", nodename="forgejo-actions-runner", nodename="woodpecker"}
|
|
for: 4m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Virtual host unusual disk write rate for 4 min (instance {{ $labels.instance }})
|
|
description: "Disk is probably writing too much data (> 50 MB/s)\n VALUE = {{ $value }}"
|
|
- alert: PhysicalHostUnusualDiskReadRate
|
|
expr: (sum by (instance) (rate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 100) * on(instance) group_left (nodename) node_uname_info{type="physical_machine", nodename=~".+"}
|
|
for: 20m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Physical host unusual disk read rate (instance {{ $labels.instance }})
|
|
description: "Disk is probably reading too much data (> 100 MB/s)\n VALUE = {{ $value }}"
|
|
- alert: PhysicalHostUnusualDiskWriteRate
|
|
expr: (sum by (instance) (rate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 100) * on(instance) group_left (nodename) node_uname_info{type="physical_machine", nodename=~".+"}
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Physical host unusual disk write rate (instance {{ $labels.instance }})
|
|
description: "Disk is probably writing too much data (> 100 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 }}"
|
|
# Have different disk IO alerts for VMs and physical machines and for physical machines different ones for hard and other disks.
|
|
- alert: PhysicalHostUnusualHardDiskIo
|
|
expr: (rate(node_disk_io_time_seconds_total{device=~"s.+"}[1m]) > 0.75) * on(instance) group_left (nodename) node_uname_info{type="physical_machine", nodename=~".+"}
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Physical host unusual hard disk IO (instance {{ $labels.instance }})
|
|
description: "Time spent in IO is too high on {{ $labels.instance }}. Check storage for issues.\n VALUE = {{ $value }}"
|
|
- alert: PhysicalHostUnusualOtherDiskIo
|
|
expr: (rate(node_disk_io_time_seconds_total{device!~"s.+"}[1m]) > 0.5) * on(instance) group_left (nodename) node_uname_info{type="physical_machine", nodename=~".+"}
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Physical host unusual other (non-hard) disk IO (instance {{ $labels.instance }})
|
|
description: "Time spent in IO is too high on {{ $labels.instance }}. Check storage for issues.\n VALUE = {{ $value }}"
|
|
- alert: VirtualHostUnusualDiskIo
|
|
expr: (rate(node_disk_io_time_seconds_total[1m]) > 0.5) * on(instance) group_left (nodename) node_uname_info{type="virtual_machine", nodename=~".+"}
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Virtual 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 }}"
|
|
- name: prometheus
|
|
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 }}"
|
|
- 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 }}"
|
|
- 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 }}"
|
|
- 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 }}"
|
|
- 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 }}"
|
|
- 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 }}"
|
|
- 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 }}"
|
|
- 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 }}"
|
|
# For testing.
|
|
# - 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 }}"
|
|
- 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 }}"
|
|
- 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 }}"
|
|
- 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 }}"
|
|
- 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 }}"
|
|
- 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 }}"
|
|
- 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 }}"
|
|
- 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 }}"
|
|
- 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 }}"
|
|
- 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 }}"
|
|
- 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 }}"
|
|
- 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 }}"
|
|
- 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 }}"
|
|
- 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 }}"
|
|
- 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 }}"
|
|
- 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 }}"
|
|
- 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 }}"
|
|
- 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 }}"
|
|
- alert: PrometheusTimeseriesCardinality
|
|
expr: label_replace(count by(__name__) ({__name__=~".+"}), "name", "$1", "__name__", "(.+)") > 10000
|
|
for: 0m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Prometheus timeseries cardinality (instance {{ $labels.instance }})
|
|
description: "The \"{{ $labels.name }}\" timeseries cardinality is getting very high: {{ $value }}\n VALUE = {{ $value }}"
|