From 45a711f92189751644398240a08ecf41c79b7ba2 Mon Sep 17 00:00:00 2001 From: samber Date: Sun, 25 Feb 2024 00:32:13 +0000 Subject: [PATCH] Publish --- dist/rules/host-and-hardware/node-exporter.yml | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/dist/rules/host-and-hardware/node-exporter.yml b/dist/rules/host-and-hardware/node-exporter.yml index e5fa55c..32a3d71 100644 --- a/dist/rules/host-and-hardware/node-exporter.yml +++ b/dist/rules/host-and-hardware/node-exporter.yml @@ -211,13 +211,13 @@ groups: summary: Host node overtemperature alarm (instance {{ $labels.instance }}) description: "Physical node temperature alarm triggered\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - - alert: HostSoftwareRaidIsNotActive - expr: '(node_md_disks_required - on(device, instance) node_md_disks{state="active"}) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + - alert: HostSoftwareRaidInsufficientDrives + expr: '((node_md_disks_required - on(device, instance) node_md_disks{state="active"}) > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' for: 0m labels: severity: critical annotations: - summary: Host Software RAID is not active (instance {{ $labels.instance }}) + summary: Host Software RAID insufficient drives (instance {{ $labels.instance }}) description: "MD RAID array {{ $labels.device }} on {{ $labels.instance }} has insufficient drives remaining.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostSoftwareRaidDiskFailure @@ -230,7 +230,7 @@ groups: description: "MD RAID array {{ $labels.device }} on {{ $labels.instance }} needs attention.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostKernelVersionDeviations - expr: 'changes(node_uname_info[1h]) == 0' + expr: 'changes(node_uname_info[1h]) > 0' for: 6h labels: severity: info