|
|
@@ -0,0 +1,301 @@ |
|
|
groups: |
|
|
- name: node_exporter_alerts |
|
|
rules: |
|
|
- alert: Node down |
|
|
expr: up{job="goethe_monitoring"} == 0 |
|
|
for: 2m |
|
|
labels: |
|
|
severity: warning |
|
|
annotations: |
|
|
title: Node {{ $labels.instance }} is down |
|
|
description: Failed to scrape {{ $labels.job }} on {{ $labels.instance }} for more than 2 minutes. Node seems down. |
|
|
|
|
|
|
|
|
- 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 }} |
|
|
|
|
|
- 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 }} |
|
|
|
|
|
- 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 }} |
|
|
|
|
|
- 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 }} |
|
|
|
|
|
- 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 }} |
|
|
|
|
|
- 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 = {{ $value }} |
|
|
|
|
|
# Please add ignored mountpoints in node_exporter parameters like |
|
|
# "--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|run)($|/)". |
|
|
# 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 = {{ $value }} |
|
|
|
|
|
# Please add ignored mountpoints in node_exporter parameters like |
|
|
# "--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|run)($|/)". |
|
|
# 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 }} |
|
|
|
|
|
- alert: HostOutOfInodes |
|
|
expr: node_filesystem_files_free{mountpoint ="/rootfs"} / node_filesystem_files{mountpoint="/rootfs"} * 100 < 10 and ON (instance, device, mountpoint) node_filesystem_readonly{mountpoint="/rootfs"} == 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 }} |
|
|
|
|
|
- alert: HostInodesWillFillIn24Hours |
|
|
expr: node_filesystem_files_free{mountpoint ="/rootfs"} / node_filesystem_files{mountpoint="/rootfs"} * 100 < 10 and predict_linear(node_filesystem_files_free{mountpoint="/rootfs"}[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly{mountpoint="/rootfs"} == 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 }} |
|
|
|
|
|
- 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 }} |
|
|
|
|
|
- alert: HostUnusualDiskWriteLatency |
|
|
expr: rate(node_disk_write_time_seconds_totali{device!~"mmcblk.+"}[1m]) / rate(node_disk_writes_completed_total{device!~"mmcblk.+"}[1m]) > 0.1 and rate(node_disk_writes_completed_total{device!~"mmcblk.+"}[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 }} |
|
|
|
|
|
- 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 }} |
|
|
|
|
|
- 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 }} |
|
|
|
|
|
# 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 }} |
|
|
|
|
|
- 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 }} |
|
|
|
|
|
- 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 }} |
|
|
|
|
|
- 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 }} |
|
|
|
|
|
- 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 }} |
|
|
|
|
|
- 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 }} |
|
|
|
|
|
- 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 }} |
|
|
|
|
|
- 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 }} |
|
|
|
|
|
- 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 }} |
|
|
|
|
|
- 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: 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 |
|
|
for: 0m |
|
|
labels: |
|
|
severity: warning |
|
|
annotations: |
|
|
summary: Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }}) |
|
|
description: 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 |
|
|
for: 2m |
|
|
labels: |
|
|
severity: warning |
|
|
annotations: |
|
|
summary: Host Network Receive Errors (instance {{ $labels.instance }}:{{ $labels.device }}) |
|
|
description: Instance interface has encountered {{ printf "%.0f" $value }} receive errors in the last five minutes.\n VALUE = {{ $value }} |
|
|
|
|
|
- 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 }}:{{ $labels.device }}) |
|
|
description: Instance has encountered {{ printf "%.0f" $value }} transmit errors in the last five minutes.\n VALUE = {{ $value }} |
|
|
|
|
|
- alert: HostNetworkInterfaceSaturated |
|
|
expr: (rate(node_network_receive_bytes_total{device!~"^tap.*"}[1m]) + rate(node_network_transmit_bytes_total{device!~"^tap.*"}[1m])) / node_network_speed_bytes{device!~"^tap.*"} > 0.8 |
|
|
for: 1m |
|
|
labels: |
|
|
severity: warning |
|
|
annotations: |
|
|
summary: Host Network Interface Saturated (instance {{ $labels.instance }}:{{ $labels.interface }}) |
|
|
description: The network interface is getting overloaded.\n VALUE = {{ $value }} |
|
|
|
|
|
- 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 approching 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) |
|
|
for: 2m |
|
|
labels: |
|
|
severity: warning |
|
|
annotations: |
|
|
summary: Host clock skew (instance {{ $labels.instance }}) |
|
|
description: Clock skew detected. Clock is out of sync.\n VALUE = {{ $value }} |
|
|
|
|
|
- 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.\n VALUE = {{ $value }} |
|
|
|
krisek revised this gist