Clément Désiles
be73f3adfa
Provision Grafana Unified Alerting as code: ntfy webhook contact point (?template=grafana), notification policy tree, and cumulative disk tiers for HDD temperature (48-60C, <20C) plus ZFS/filesystem capacity. Lower the smartctl exporter interval to 30m for alert responsiveness.
707 lines
24 KiB
YAML
707 lines
24 KiB
YAML
apiVersion: 1
|
|
|
|
# Managed by Ansible (roles/grafana). Disk alert rules: HDD temperature and
|
|
# capacity (ZFS pools + local filesystems).
|
|
#
|
|
# Temperature metric: smartctl_device_temperature{temperature_type="current"} (job="smartctl").
|
|
# Capacity metrics: zfs_pool_capacity_percent and
|
|
# node_filesystem_avail_bytes/node_filesystem_size_bytes (job="node").
|
|
# node_filesystem_* is filtered to real local filesystems (ext4/xfs/btrfs);
|
|
# ZFS datasets are excluded because they report pool-wide free space, not
|
|
# per-dataset, and are covered by zfs_pool_capacity_percent instead.
|
|
#
|
|
# Tiers are cumulative thresholds (>= N), not non-overlapping bands:
|
|
# rising -> each newly crossed threshold fires; lower tiers keep firing
|
|
# falling -> each crossed-down threshold resolves (ack); lower tiers keep firing
|
|
# So a rise pages once per tier crossed and a fall acks once per tier, with the
|
|
# final ack when leaving the lowest tier. Below the lowest threshold = no series
|
|
# = NoData, mapped to OK on purpose.
|
|
groups:
|
|
- orgId: 1
|
|
name: disk-temperature
|
|
folder: Disks
|
|
interval: 1m
|
|
rules:
|
|
- uid: disk_temp_ge_48
|
|
title: "Disk temperature ≥48°C"
|
|
condition: C
|
|
data:
|
|
- refId: A
|
|
relativeTimeRange: { from: 3600, to: 0 }
|
|
datasourceUid: prometheus
|
|
model:
|
|
editorMode: code
|
|
expr: >-
|
|
smartctl_device_temperature{job="smartctl", temperature_type="current"} >= 48
|
|
instant: false
|
|
intervalMs: 1000
|
|
legendFormat: "{{device}}"
|
|
maxDataPoints: 43200
|
|
range: true
|
|
refId: A
|
|
- refId: B
|
|
datasourceUid: __expr__
|
|
model:
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: A
|
|
reducer: last
|
|
refId: B
|
|
type: reduce
|
|
settings: { mode: dropNN }
|
|
- refId: C
|
|
datasourceUid: __expr__
|
|
model:
|
|
conditions:
|
|
- evaluator: { params: [0], type: gt }
|
|
operator: { type: and }
|
|
query: { params: [C] }
|
|
reducer: { type: last }
|
|
type: query
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: B
|
|
refId: C
|
|
type: threshold
|
|
for: 10m
|
|
noDataState: OK
|
|
execErrState: Error
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Disk {{ $labels.device }} at {{ $values.B }}°C ({{ $labels.instance }})"
|
|
description: "S.M.A.R.T. temperature is at or above 48°C. Ideal is 20-45°C."
|
|
|
|
- uid: disk_temp_ge_50
|
|
title: "Disk temperature ≥50°C"
|
|
condition: C
|
|
data:
|
|
- refId: A
|
|
relativeTimeRange: { from: 3600, to: 0 }
|
|
datasourceUid: prometheus
|
|
model:
|
|
editorMode: code
|
|
expr: >-
|
|
smartctl_device_temperature{job="smartctl", temperature_type="current"} >= 50
|
|
instant: false
|
|
intervalMs: 1000
|
|
legendFormat: "{{device}}"
|
|
maxDataPoints: 43200
|
|
range: true
|
|
refId: A
|
|
- refId: B
|
|
datasourceUid: __expr__
|
|
model:
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: A
|
|
reducer: last
|
|
refId: B
|
|
type: reduce
|
|
settings: { mode: dropNN }
|
|
- refId: C
|
|
datasourceUid: __expr__
|
|
model:
|
|
conditions:
|
|
- evaluator: { params: [0], type: gt }
|
|
operator: { type: and }
|
|
query: { params: [C] }
|
|
reducer: { type: last }
|
|
type: query
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: B
|
|
refId: C
|
|
type: threshold
|
|
for: 10m
|
|
noDataState: OK
|
|
execErrState: Error
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Disk {{ $labels.device }} at {{ $values.B }}°C ({{ $labels.instance }})"
|
|
description: "S.M.A.R.T. temperature is at or above 50°C."
|
|
|
|
- uid: disk_temp_ge_52
|
|
title: "Disk temperature ≥52°C"
|
|
condition: C
|
|
data:
|
|
- refId: A
|
|
relativeTimeRange: { from: 3600, to: 0 }
|
|
datasourceUid: prometheus
|
|
model:
|
|
editorMode: code
|
|
expr: >-
|
|
smartctl_device_temperature{job="smartctl", temperature_type="current"} >= 52
|
|
instant: false
|
|
intervalMs: 1000
|
|
legendFormat: "{{device}}"
|
|
maxDataPoints: 43200
|
|
range: true
|
|
refId: A
|
|
- refId: B
|
|
datasourceUid: __expr__
|
|
model:
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: A
|
|
reducer: last
|
|
refId: B
|
|
type: reduce
|
|
settings: { mode: dropNN }
|
|
- refId: C
|
|
datasourceUid: __expr__
|
|
model:
|
|
conditions:
|
|
- evaluator: { params: [0], type: gt }
|
|
operator: { type: and }
|
|
query: { params: [C] }
|
|
reducer: { type: last }
|
|
type: query
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: B
|
|
refId: C
|
|
type: threshold
|
|
for: 10m
|
|
noDataState: OK
|
|
execErrState: Error
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Disk {{ $labels.device }} at {{ $values.B }}°C ({{ $labels.instance }})"
|
|
description: "S.M.A.R.T. temperature is at or above 52°C."
|
|
|
|
- uid: disk_temp_ge_54
|
|
title: "Disk temperature ≥54°C"
|
|
condition: C
|
|
data:
|
|
- refId: A
|
|
relativeTimeRange: { from: 3600, to: 0 }
|
|
datasourceUid: prometheus
|
|
model:
|
|
editorMode: code
|
|
expr: >-
|
|
smartctl_device_temperature{job="smartctl", temperature_type="current"} >= 54
|
|
instant: false
|
|
intervalMs: 1000
|
|
legendFormat: "{{device}}"
|
|
maxDataPoints: 43200
|
|
range: true
|
|
refId: A
|
|
- refId: B
|
|
datasourceUid: __expr__
|
|
model:
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: A
|
|
reducer: last
|
|
refId: B
|
|
type: reduce
|
|
settings: { mode: dropNN }
|
|
- refId: C
|
|
datasourceUid: __expr__
|
|
model:
|
|
conditions:
|
|
- evaluator: { params: [0], type: gt }
|
|
operator: { type: and }
|
|
query: { params: [C] }
|
|
reducer: { type: last }
|
|
type: query
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: B
|
|
refId: C
|
|
type: threshold
|
|
for: 10m
|
|
noDataState: OK
|
|
execErrState: Error
|
|
labels:
|
|
severity: high
|
|
annotations:
|
|
summary: "Disk {{ $labels.device }} at {{ $values.B }}°C ({{ $labels.instance }})"
|
|
description: "S.M.A.R.T. temperature is at or above 54°C. Check airflow/fan."
|
|
|
|
- uid: disk_temp_ge_56
|
|
title: "Disk temperature ≥56°C"
|
|
condition: C
|
|
data:
|
|
- refId: A
|
|
relativeTimeRange: { from: 3600, to: 0 }
|
|
datasourceUid: prometheus
|
|
model:
|
|
editorMode: code
|
|
expr: >-
|
|
smartctl_device_temperature{job="smartctl", temperature_type="current"} >= 56
|
|
instant: false
|
|
intervalMs: 1000
|
|
legendFormat: "{{device}}"
|
|
maxDataPoints: 43200
|
|
range: true
|
|
refId: A
|
|
- refId: B
|
|
datasourceUid: __expr__
|
|
model:
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: A
|
|
reducer: last
|
|
refId: B
|
|
type: reduce
|
|
settings: { mode: dropNN }
|
|
- refId: C
|
|
datasourceUid: __expr__
|
|
model:
|
|
conditions:
|
|
- evaluator: { params: [0], type: gt }
|
|
operator: { type: and }
|
|
query: { params: [C] }
|
|
reducer: { type: last }
|
|
type: query
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: B
|
|
refId: C
|
|
type: threshold
|
|
for: 10m
|
|
noDataState: OK
|
|
execErrState: Error
|
|
labels:
|
|
severity: high
|
|
annotations:
|
|
summary: "Disk {{ $labels.device }} at {{ $values.B }}°C ({{ $labels.instance }})"
|
|
description: "S.M.A.R.T. temperature is at or above 56°C. Check airflow/fan."
|
|
|
|
- uid: disk_temp_ge_58
|
|
title: "Disk temperature ≥58°C"
|
|
condition: C
|
|
data:
|
|
- refId: A
|
|
relativeTimeRange: { from: 3600, to: 0 }
|
|
datasourceUid: prometheus
|
|
model:
|
|
editorMode: code
|
|
expr: >-
|
|
smartctl_device_temperature{job="smartctl", temperature_type="current"} >= 58
|
|
instant: false
|
|
intervalMs: 1000
|
|
legendFormat: "{{device}}"
|
|
maxDataPoints: 43200
|
|
range: true
|
|
refId: A
|
|
- refId: B
|
|
datasourceUid: __expr__
|
|
model:
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: A
|
|
reducer: last
|
|
refId: B
|
|
type: reduce
|
|
settings: { mode: dropNN }
|
|
- refId: C
|
|
datasourceUid: __expr__
|
|
model:
|
|
conditions:
|
|
- evaluator: { params: [0], type: gt }
|
|
operator: { type: and }
|
|
query: { params: [C] }
|
|
reducer: { type: last }
|
|
type: query
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: B
|
|
refId: C
|
|
type: threshold
|
|
for: 10m
|
|
noDataState: OK
|
|
execErrState: Error
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "Disk {{ $labels.device }} at {{ $values.B }}°C ({{ $labels.instance }})"
|
|
description: "S.M.A.R.T. temperature is at or above 58°C, close to the failure limit."
|
|
|
|
- uid: disk_temp_ge_60
|
|
title: "Disk temperature ≥60°C"
|
|
condition: C
|
|
data:
|
|
- refId: A
|
|
relativeTimeRange: { from: 3600, to: 0 }
|
|
datasourceUid: prometheus
|
|
model:
|
|
editorMode: code
|
|
expr: >-
|
|
smartctl_device_temperature{job="smartctl", temperature_type="current"} >= 60
|
|
instant: false
|
|
intervalMs: 1000
|
|
legendFormat: "{{device}}"
|
|
maxDataPoints: 43200
|
|
range: true
|
|
refId: A
|
|
- refId: B
|
|
datasourceUid: __expr__
|
|
model:
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: A
|
|
reducer: last
|
|
refId: B
|
|
type: reduce
|
|
settings: { mode: dropNN }
|
|
- refId: C
|
|
datasourceUid: __expr__
|
|
model:
|
|
conditions:
|
|
- evaluator: { params: [0], type: gt }
|
|
operator: { type: and }
|
|
query: { params: [C] }
|
|
reducer: { type: last }
|
|
type: query
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: B
|
|
refId: C
|
|
type: threshold
|
|
for: 5m
|
|
noDataState: OK
|
|
execErrState: Error
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "Disk {{ $labels.device }} at {{ $values.B }}°C ({{ $labels.instance }})"
|
|
description: "S.M.A.R.T. temperature is at or above the 60°C failure limit."
|
|
|
|
- uid: disk_temp_lt_20
|
|
title: "Disk temperature <20°C"
|
|
condition: C
|
|
data:
|
|
- refId: A
|
|
relativeTimeRange: { from: 3600, to: 0 }
|
|
datasourceUid: prometheus
|
|
model:
|
|
editorMode: code
|
|
expr: >-
|
|
smartctl_device_temperature{job="smartctl", temperature_type="current"} < 20
|
|
instant: false
|
|
intervalMs: 1000
|
|
legendFormat: "{{device}}"
|
|
maxDataPoints: 43200
|
|
range: true
|
|
refId: A
|
|
- refId: B
|
|
datasourceUid: __expr__
|
|
model:
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: A
|
|
reducer: last
|
|
refId: B
|
|
type: reduce
|
|
settings: { mode: dropNN }
|
|
- refId: C
|
|
datasourceUid: __expr__
|
|
model:
|
|
conditions:
|
|
- evaluator: { params: [0], type: gt }
|
|
operator: { type: and }
|
|
query: { params: [C] }
|
|
reducer: { type: last }
|
|
type: query
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: B
|
|
refId: C
|
|
type: threshold
|
|
for: 10m
|
|
noDataState: OK
|
|
execErrState: Error
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Disk {{ $labels.device }} at {{ $values.B }}°C ({{ $labels.instance }})"
|
|
description: "S.M.A.R.T. temperature is below the 20°C ideal minimum (sensor/fan/offline disk?)."
|
|
|
|
# --- Capacity: ZFS pools (data disk) ---
|
|
# zfs_pool_capacity_percent is emitted hourly by the zfs role's
|
|
# zfs-metrics.timer via node_exporter's textfile collector. Cumulative
|
|
# thresholds; below threshold = no series = NoData, mapped to OK.
|
|
- uid: zfs_pool_capacity_ge_80
|
|
title: "ZFS pool ≥80% full"
|
|
condition: C
|
|
data:
|
|
- refId: A
|
|
relativeTimeRange: { from: 3600, to: 0 }
|
|
datasourceUid: prometheus
|
|
model:
|
|
editorMode: code
|
|
expr: >-
|
|
zfs_pool_capacity_percent{job="node"} >= 80
|
|
instant: false
|
|
intervalMs: 1000
|
|
legendFormat: "{{pool}}"
|
|
maxDataPoints: 43200
|
|
range: true
|
|
refId: A
|
|
- refId: B
|
|
datasourceUid: __expr__
|
|
model:
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: A
|
|
reducer: last
|
|
refId: B
|
|
type: reduce
|
|
settings: { mode: dropNN }
|
|
- refId: C
|
|
datasourceUid: __expr__
|
|
model:
|
|
conditions:
|
|
- evaluator: { params: [0], type: gt }
|
|
operator: { type: and }
|
|
query: { params: [C] }
|
|
reducer: { type: last }
|
|
type: query
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: B
|
|
refId: C
|
|
type: threshold
|
|
for: 6h
|
|
noDataState: OK
|
|
execErrState: Error
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "ZFS pool {{ $labels.pool }} at {{ $values.B }}% ({{ $labels.instance }})"
|
|
description: "ZFS pool is at or above 80% capacity. ZFS performance degrades above 80%."
|
|
|
|
- uid: zfs_pool_capacity_ge_90
|
|
title: "ZFS pool ≥90% full"
|
|
condition: C
|
|
data:
|
|
- refId: A
|
|
relativeTimeRange: { from: 3600, to: 0 }
|
|
datasourceUid: prometheus
|
|
model:
|
|
editorMode: code
|
|
expr: >-
|
|
zfs_pool_capacity_percent{job="node"} >= 90
|
|
instant: false
|
|
intervalMs: 1000
|
|
legendFormat: "{{pool}}"
|
|
maxDataPoints: 43200
|
|
range: true
|
|
refId: A
|
|
- refId: B
|
|
datasourceUid: __expr__
|
|
model:
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: A
|
|
reducer: last
|
|
refId: B
|
|
type: reduce
|
|
settings: { mode: dropNN }
|
|
- refId: C
|
|
datasourceUid: __expr__
|
|
model:
|
|
conditions:
|
|
- evaluator: { params: [0], type: gt }
|
|
operator: { type: and }
|
|
query: { params: [C] }
|
|
reducer: { type: last }
|
|
type: query
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: B
|
|
refId: C
|
|
type: threshold
|
|
for: 1h
|
|
noDataState: OK
|
|
execErrState: Error
|
|
labels:
|
|
severity: high
|
|
annotations:
|
|
summary: "ZFS pool {{ $labels.pool }} at {{ $values.B }}% ({{ $labels.instance }})"
|
|
description: "ZFS pool is at or above 90% capacity. Free space is getting low."
|
|
|
|
- uid: zfs_pool_capacity_ge_95
|
|
title: "ZFS pool ≥95% full"
|
|
condition: C
|
|
data:
|
|
- refId: A
|
|
relativeTimeRange: { from: 3600, to: 0 }
|
|
datasourceUid: prometheus
|
|
model:
|
|
editorMode: code
|
|
expr: >-
|
|
zfs_pool_capacity_percent{job="node"} >= 95
|
|
instant: false
|
|
intervalMs: 1000
|
|
legendFormat: "{{pool}}"
|
|
maxDataPoints: 43200
|
|
range: true
|
|
refId: A
|
|
- refId: B
|
|
datasourceUid: __expr__
|
|
model:
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: A
|
|
reducer: last
|
|
refId: B
|
|
type: reduce
|
|
settings: { mode: dropNN }
|
|
- refId: C
|
|
datasourceUid: __expr__
|
|
model:
|
|
conditions:
|
|
- evaluator: { params: [0], type: gt }
|
|
operator: { type: and }
|
|
query: { params: [C] }
|
|
reducer: { type: last }
|
|
type: query
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: B
|
|
refId: C
|
|
type: threshold
|
|
for: 15m
|
|
noDataState: OK
|
|
execErrState: Error
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "ZFS pool {{ $labels.pool }} at {{ $values.B }}% ({{ $labels.instance }})"
|
|
description: "ZFS pool is at or above 95% capacity. Writes may fail soon."
|
|
|
|
# --- Capacity: local filesystems (system disk, db disk) ---
|
|
# node_exporter's filesystem collector. fstype filter excludes ZFS
|
|
# (pool-wide free space is not per-dataset) and virtual filesystems.
|
|
# Cumulative thresholds; below threshold = no series = NoData, OK.
|
|
- uid: fs_capacity_ge_80
|
|
title: "Filesystem ≥80% full"
|
|
condition: C
|
|
data:
|
|
- refId: A
|
|
relativeTimeRange: { from: 3600, to: 0 }
|
|
datasourceUid: prometheus
|
|
model:
|
|
editorMode: code
|
|
expr: >-
|
|
100 * (1 - node_filesystem_avail_bytes{job="node", fstype=~"ext4|xfs|btrfs"}
|
|
/ node_filesystem_size_bytes{job="node", fstype=~"ext4|xfs|btrfs"}) >= 80
|
|
instant: false
|
|
intervalMs: 1000
|
|
legendFormat: "{{mountpoint}}"
|
|
maxDataPoints: 43200
|
|
range: true
|
|
refId: A
|
|
- refId: B
|
|
datasourceUid: __expr__
|
|
model:
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: A
|
|
reducer: last
|
|
refId: B
|
|
type: reduce
|
|
settings: { mode: dropNN }
|
|
- refId: C
|
|
datasourceUid: __expr__
|
|
model:
|
|
conditions:
|
|
- evaluator: { params: [0], type: gt }
|
|
operator: { type: and }
|
|
query: { params: [C] }
|
|
reducer: { type: last }
|
|
type: query
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: B
|
|
refId: C
|
|
type: threshold
|
|
for: 6h
|
|
noDataState: OK
|
|
execErrState: Error
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Filesystem {{ $labels.mountpoint }} at {{ $values.B }}% ({{ $labels.instance }})"
|
|
description: "Filesystem is at or above 80% capacity."
|
|
|
|
- uid: fs_capacity_ge_90
|
|
title: "Filesystem ≥90% full"
|
|
condition: C
|
|
data:
|
|
- refId: A
|
|
relativeTimeRange: { from: 3600, to: 0 }
|
|
datasourceUid: prometheus
|
|
model:
|
|
editorMode: code
|
|
expr: >-
|
|
100 * (1 - node_filesystem_avail_bytes{job="node", fstype=~"ext4|xfs|btrfs"}
|
|
/ node_filesystem_size_bytes{job="node", fstype=~"ext4|xfs|btrfs"}) >= 90
|
|
instant: false
|
|
intervalMs: 1000
|
|
legendFormat: "{{mountpoint}}"
|
|
maxDataPoints: 43200
|
|
range: true
|
|
refId: A
|
|
- refId: B
|
|
datasourceUid: __expr__
|
|
model:
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: A
|
|
reducer: last
|
|
refId: B
|
|
type: reduce
|
|
settings: { mode: dropNN }
|
|
- refId: C
|
|
datasourceUid: __expr__
|
|
model:
|
|
conditions:
|
|
- evaluator: { params: [0], type: gt }
|
|
operator: { type: and }
|
|
query: { params: [C] }
|
|
reducer: { type: last }
|
|
type: query
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: B
|
|
refId: C
|
|
type: threshold
|
|
for: 1h
|
|
noDataState: OK
|
|
execErrState: Error
|
|
labels:
|
|
severity: high
|
|
annotations:
|
|
summary: "Filesystem {{ $labels.mountpoint }} at {{ $values.B }}% ({{ $labels.instance }})"
|
|
description: "Filesystem is at or above 90% capacity. Free space is getting low."
|
|
|
|
- uid: fs_capacity_ge_95
|
|
title: "Filesystem ≥95% full"
|
|
condition: C
|
|
data:
|
|
- refId: A
|
|
relativeTimeRange: { from: 3600, to: 0 }
|
|
datasourceUid: prometheus
|
|
model:
|
|
editorMode: code
|
|
expr: >-
|
|
100 * (1 - node_filesystem_avail_bytes{job="node", fstype=~"ext4|xfs|btrfs"}
|
|
/ node_filesystem_size_bytes{job="node", fstype=~"ext4|xfs|btrfs"}) >= 95
|
|
instant: false
|
|
intervalMs: 1000
|
|
legendFormat: "{{mountpoint}}"
|
|
maxDataPoints: 43200
|
|
range: true
|
|
refId: A
|
|
- refId: B
|
|
datasourceUid: __expr__
|
|
model:
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: A
|
|
reducer: last
|
|
refId: B
|
|
type: reduce
|
|
settings: { mode: dropNN }
|
|
- refId: C
|
|
datasourceUid: __expr__
|
|
model:
|
|
conditions:
|
|
- evaluator: { params: [0], type: gt }
|
|
operator: { type: and }
|
|
query: { params: [C] }
|
|
reducer: { type: last }
|
|
type: query
|
|
datasource: { type: __expr__, uid: __expr__ }
|
|
expression: B
|
|
refId: C
|
|
type: threshold
|
|
for: 15m
|
|
noDataState: OK
|
|
execErrState: Error
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "Filesystem {{ $labels.mountpoint }} at {{ $values.B }}% ({{ $labels.instance }})"
|
|
description: "Filesystem is at or above 95% capacity. Writes may fail soon."
|