From 40cddb67b40a245d3416816a5fe330b152203d87 Mon Sep 17 00:00:00 2001 From: June <june@jsts.xyz> Date: Thu, 6 Feb 2025 19:17:21 +0100 Subject: [PATCH] grafana: account for long backup jobs in Prom. hyperv. disk rw rate al. --- .../grafana/docker_compose/prometheus_alerts.rules.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/resources/chaosknoten/grafana/docker_compose/prometheus_alerts.rules.yaml b/resources/chaosknoten/grafana/docker_compose/prometheus_alerts.rules.yaml index 3d9d7a1..5cc54e9 100644 --- a/resources/chaosknoten/grafana/docker_compose/prometheus_alerts.rules.yaml +++ b/resources/chaosknoten/grafana/docker_compose/prometheus_alerts.rules.yaml @@ -166,7 +166,7 @@ groups: # Longer intervals to account for disk intensive hypervisor tasks (backups, moving VMs, etc.). - alert: HypervisorHostUnusualDiskReadRate expr: (sum by (instance) (rate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50) * on(instance) group_left (nodename) node_uname_info{nodename="chaosknoten"} - for: 30m + for: 60m labels: severity: warning annotations: @@ -174,7 +174,7 @@ groups: description: "Disk is probably reading too much data (> 50 MB/s)\n VALUE = {{ $value }}" - alert: HypervisorHostUnusualDiskWriteRate expr: (sum by (instance) (rate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50) * on(instance) group_left (nodename) node_uname_info{nodename="chaosknoten"} - for: 20m + for: 60m labels: severity: warning annotations: