Browse Source

docs/node-mixin: add alerts about failing RAID array

Signed-off-by: paulfantom <pawel@krupa.net.pl>
pull/1821/head
paulfantom 4 years ago committed by Johannes 'fish' Ziemke
parent
commit
e4ec8e04c5
  1. 27
      docs/node-mixin/alerts/alerts.libsonnet

27
docs/node-mixin/alerts/alerts.libsonnet

@ -248,6 +248,33 @@
message: 'Clock on {{ $labels.instance }} is not synchronising. Ensure NTP is configured on this host.', message: 'Clock on {{ $labels.instance }} is not synchronising. Ensure NTP is configured on this host.',
}, },
}, },
{
alert: 'NodeRAIDDegraded',
expr: |||
'node_md_disks_required - ignoring (state) (node_md_disks{state="active"}) > 0'
||| % $._config,
'for': '15m',
labels: {
severity: 'critical',
},
annotations: {
summary: 'RAID Array is degraded',
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.',
},
},
{
alert: 'NodeRAIDDiskFailure',
expr: |||
node_md_disks{state="fail"} > 0
||| % $._config,
labels: {
severity: 'warning',
},
annotations: {
summary: 'Failed device in RAID array',
description: 'At least one device in RAID array on {{ $labels.instance }} failed. Array '{{ $labels.device }}' needs attention and possibly a disk swap.',
},
},
], ],
}, },
], ],

Loading…
Cancel
Save