mirror of
https://github.com/monitoring-mixins/website.git
synced 2024-12-14 11:37:31 +00:00
235 lines
8.8 KiB
YAML
235 lines
8.8 KiB
YAML
groups:
|
|
- name: node-exporter
|
|
rules:
|
|
- alert: NodeFilesystemSpaceFillingUp
|
|
annotations:
|
|
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has
|
|
only {{ printf "%.2f" $value }}% available space left and is filling up.
|
|
summary: Filesystem is predicted to run out of space within the next 24 hours.
|
|
expr: |
|
|
(
|
|
node_filesystem_avail_bytes{job="node",fstype!=""} / node_filesystem_size_bytes{job="node",fstype!=""} * 100 < 40
|
|
and
|
|
predict_linear(node_filesystem_avail_bytes{job="node",fstype!=""}[6h], 24*60*60) < 0
|
|
and
|
|
node_filesystem_readonly{job="node",fstype!=""} == 0
|
|
)
|
|
for: 1h
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeFilesystemSpaceFillingUp
|
|
annotations:
|
|
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has
|
|
only {{ printf "%.2f" $value }}% available space left and is filling up fast.
|
|
summary: Filesystem is predicted to run out of space within the next 4 hours.
|
|
expr: |
|
|
(
|
|
node_filesystem_avail_bytes{job="node",fstype!=""} / node_filesystem_size_bytes{job="node",fstype!=""} * 100 < 20
|
|
and
|
|
predict_linear(node_filesystem_avail_bytes{job="node",fstype!=""}[6h], 4*60*60) < 0
|
|
and
|
|
node_filesystem_readonly{job="node",fstype!=""} == 0
|
|
)
|
|
for: 1h
|
|
labels:
|
|
severity: critical
|
|
- alert: NodeFilesystemAlmostOutOfSpace
|
|
annotations:
|
|
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has
|
|
only {{ printf "%.2f" $value }}% available space left.
|
|
summary: Filesystem has less than 5% space left.
|
|
expr: |
|
|
(
|
|
node_filesystem_avail_bytes{job="node",fstype!=""} / node_filesystem_size_bytes{job="node",fstype!=""} * 100 < 5
|
|
and
|
|
node_filesystem_readonly{job="node",fstype!=""} == 0
|
|
)
|
|
for: 1h
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeFilesystemAlmostOutOfSpace
|
|
annotations:
|
|
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has
|
|
only {{ printf "%.2f" $value }}% available space left.
|
|
summary: Filesystem has less than 3% space left.
|
|
expr: |
|
|
(
|
|
node_filesystem_avail_bytes{job="node",fstype!=""} / node_filesystem_size_bytes{job="node",fstype!=""} * 100 < 3
|
|
and
|
|
node_filesystem_readonly{job="node",fstype!=""} == 0
|
|
)
|
|
for: 1h
|
|
labels:
|
|
severity: critical
|
|
- alert: NodeFilesystemFilesFillingUp
|
|
annotations:
|
|
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has
|
|
only {{ printf "%.2f" $value }}% available inodes left and is filling up.
|
|
summary: Filesystem is predicted to run out of inodes within the next 24 hours.
|
|
expr: |
|
|
(
|
|
node_filesystem_files_free{job="node",fstype!=""} / node_filesystem_files{job="node",fstype!=""} * 100 < 40
|
|
and
|
|
predict_linear(node_filesystem_files_free{job="node",fstype!=""}[6h], 24*60*60) < 0
|
|
and
|
|
node_filesystem_readonly{job="node",fstype!=""} == 0
|
|
)
|
|
for: 1h
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeFilesystemFilesFillingUp
|
|
annotations:
|
|
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has
|
|
only {{ printf "%.2f" $value }}% available inodes left and is filling up fast.
|
|
summary: Filesystem is predicted to run out of inodes within the next 4 hours.
|
|
expr: |
|
|
(
|
|
node_filesystem_files_free{job="node",fstype!=""} / node_filesystem_files{job="node",fstype!=""} * 100 < 20
|
|
and
|
|
predict_linear(node_filesystem_files_free{job="node",fstype!=""}[6h], 4*60*60) < 0
|
|
and
|
|
node_filesystem_readonly{job="node",fstype!=""} == 0
|
|
)
|
|
for: 1h
|
|
labels:
|
|
severity: critical
|
|
- alert: NodeFilesystemAlmostOutOfFiles
|
|
annotations:
|
|
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has
|
|
only {{ printf "%.2f" $value }}% available inodes left.
|
|
summary: Filesystem has less than 5% inodes left.
|
|
expr: |
|
|
(
|
|
node_filesystem_files_free{job="node",fstype!=""} / node_filesystem_files{job="node",fstype!=""} * 100 < 5
|
|
and
|
|
node_filesystem_readonly{job="node",fstype!=""} == 0
|
|
)
|
|
for: 1h
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeFilesystemAlmostOutOfFiles
|
|
annotations:
|
|
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has
|
|
only {{ printf "%.2f" $value }}% available inodes left.
|
|
summary: Filesystem has less than 3% inodes left.
|
|
expr: |
|
|
(
|
|
node_filesystem_files_free{job="node",fstype!=""} / node_filesystem_files{job="node",fstype!=""} * 100 < 3
|
|
and
|
|
node_filesystem_readonly{job="node",fstype!=""} == 0
|
|
)
|
|
for: 1h
|
|
labels:
|
|
severity: critical
|
|
- alert: NodeNetworkReceiveErrs
|
|
annotations:
|
|
description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered
|
|
{{ printf "%.0f" $value }} receive errors in the last two minutes.'
|
|
summary: Network interface is reporting many receive errors.
|
|
expr: |
|
|
rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01
|
|
for: 1h
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeNetworkTransmitErrs
|
|
annotations:
|
|
description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered
|
|
{{ printf "%.0f" $value }} transmit errors in the last two minutes.'
|
|
summary: Network interface is reporting many transmit errors.
|
|
expr: |
|
|
rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01
|
|
for: 1h
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeHighNumberConntrackEntriesUsed
|
|
annotations:
|
|
description: '{{ $value | humanizePercentage }} of conntrack entries are used.'
|
|
summary: Number of conntrack are getting close to the limit.
|
|
expr: |
|
|
(node_nf_conntrack_entries / node_nf_conntrack_entries_limit) > 0.75
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeTextFileCollectorScrapeError
|
|
annotations:
|
|
description: Node Exporter text file collector failed to scrape.
|
|
summary: Node Exporter text file collector failed to scrape.
|
|
expr: |
|
|
node_textfile_scrape_error{job="node"} == 1
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeClockSkewDetected
|
|
annotations:
|
|
description: Clock on {{ $labels.instance }} is out of sync by more than 300s.
|
|
Ensure NTP is configured correctly on this host.
|
|
summary: Clock skew detected.
|
|
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: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeClockNotSynchronising
|
|
annotations:
|
|
description: Clock on {{ $labels.instance }} is not synchronising. Ensure NTP
|
|
is configured on this host.
|
|
summary: Clock not synchronising.
|
|
expr: |
|
|
min_over_time(node_timex_sync_status[5m]) == 0
|
|
and
|
|
node_timex_maxerror_seconds >= 16
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeRAIDDegraded
|
|
annotations:
|
|
description: RAID array '{{ $labels.device }}' on {{ $labels.instance }} is
|
|
in degraded state due to one or more disks failures. Number of spare drives
|
|
is insufficient to fix issue automatically.
|
|
summary: RAID Array is degraded
|
|
expr: |
|
|
node_md_disks_required - ignoring (state) (node_md_disks{state="active"}) > 0
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
- alert: NodeRAIDDiskFailure
|
|
annotations:
|
|
description: At least one device in RAID array on {{ $labels.instance }} failed.
|
|
Array '{{ $labels.device }}' needs attention and possibly a disk swap.
|
|
summary: Failed device in RAID array
|
|
expr: |
|
|
node_md_disks{state="failed"} > 0
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeFileDescriptorLimit
|
|
annotations:
|
|
description: File descriptors limit at {{ $labels.instance }} is currently at
|
|
{{ printf "%.2f" $value }}%.
|
|
summary: Kernel is predicted to exhaust file descriptors limit soon.
|
|
expr: |
|
|
(
|
|
node_filefd_allocated{job="node-exporter"} * 100 / node_filefd_maximum{job="node-exporter"} > 70
|
|
)
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeFileDescriptorLimit
|
|
annotations:
|
|
description: File descriptors limit at {{ $labels.instance }} is currently at
|
|
{{ printf "%.2f" $value }}%.
|
|
summary: Kernel is predicted to exhaust file descriptors limit soon.
|
|
expr: |
|
|
(
|
|
node_filefd_allocated{job="node-exporter"} * 100 / node_filefd_maximum{job="node-exporter"} > 90
|
|
)
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|