diff --git a/jsonnetfile.lock.json b/jsonnetfile.lock.json index 2ac75e690a3051cacc181b4bcb4d50b6959013b1..a7b3dab868aa677349994f31da1ca5c6bbc56f14 100644 --- a/jsonnetfile.lock.json +++ b/jsonnetfile.lock.json @@ -8,7 +8,7 @@ "subdir": "contrib/kube-prometheus/jsonnet/kube-prometheus" } }, - "version": "f6c5c4311b8c8ad699cfa718a6e1226780b8b3a5" + "version": "c22d20f7fc8eb359d4f99bc440175dee0d31c3cf" }, { "name": "ksonnet", @@ -28,7 +28,7 @@ "subdir": "" } }, - "version": "fee96cc51d22f196c982c6152cc8aee2585f65c0" + "version": "ab3d27befcdb31ec286790b8e0ca49bf1deecce5" }, { "name": "grafonnet", diff --git a/manifests/prometheus-rules.yaml b/manifests/prometheus-rules.yaml index 1809db6b106ab2aa5cbeb7a77d974d81881fa27d..7958b926fcffdf81bf2c4a953af6124d508c6852 100644 --- a/manifests/prometheus-rules.yaml +++ b/manifests/prometheus-rules.yaml @@ -781,10 +781,10 @@ spec: annotations: message: Based on recent sampling, the persistent volume claimed by {{ $labels.persistentvolumeclaim }} in namespace {{ $labels.namespace }} is expected to fill up within four - days. + days. Currently {{ $value }} bytes are available. runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumefullinfourdays expr: | - predict_linear(kubelet_volume_stats_available_bytes{job="kubelet"}[1h], 4 * 24 * 3600) < 0 + kubelet_volume_stats_available_bytes{job="kubelet"} and predict_linear(kubelet_volume_stats_available_bytes{job="kubelet"}[6h], 4 * 24 * 3600) < 0 for: 5m labels: severity: critical @@ -954,21 +954,19 @@ spec: rules: - alert: NodeDiskRunningFull annotations: - description: device {{$labels.device}} on node {{$labels.instance}} is running - full within the next 24 hours (mounted at {{$labels.mountpoint}}) - summary: Node disk is running full within 24 hours + message: Device {{ $labels.device }} of node-exporter {{ $labels.namespace + }}/{{ $labels.pod }} is running full within the next 24 hours. expr: | - predict_linear(node_filesystem_free{job="node-exporter",mountpoint!~"^/etc/(?:resolv.conf|hosts|hostname)$"}[6h], 3600 * 24) < 0 and on(instance) up{job="node-exporter"} + (node:node_filesystem_usage: > 0.85) and (predict_linear(node:node_filesystem_avail:[6h], 3600 * 24) < 0) for: 30m labels: severity: warning - alert: NodeDiskRunningFull annotations: - description: device {{$labels.device}} on node {{$labels.instance}} is running - full within the next 2 hours (mounted at {{$labels.mountpoint}}) - summary: Node disk is running full within 2 hours + message: Device {{ $labels.device }} of node-exporter {{ $labels.namespace + }}/{{ $labels.pod }} is running full within the next 2 hours. expr: | - predict_linear(node_filesystem_free{job="node-exporter",mountpoint!~"^/etc/(?:resolv.conf|hosts|hostname)$"}[30m], 3600 * 2) < 0 and on(instance) up{job="node-exporter"} + (node:node_filesystem_usage: > 0.85) and (predict_linear(node:node_filesystem_avail:[30m], 3600 * 2) < 0) for: 10m labels: severity: critical