Update node-exporter from v0.15.2 to v0.17.0

* node-exporter renamed multiple metrics that are reflected
in changes to Prometheus rules and Grafana dashboard expressions

addons/prometheus/exporters/node-exporter/daemonset.yaml

@@ -28,21 +28,24 @@ spec:
       hostPID: true
       containers:
       - name: node-exporter
-        image: quay.io/prometheus/node-exporter:v0.15.2
+        image: quay.io/prometheus/node-exporter:v0.17.0
         args:
-          - "--path.procfs=/host/proc"
-          - "--path.sysfs=/host/sys"
+          - --path.procfs=/host/proc
+          - --path.sysfs=/host/sys
+          - --path.rootfs=/host/root
+          - --collector.filesystem.ignored-mount-points=^/(dev|proc|sys|var/lib/docker/.+)($|/)
+          - --collector.filesystem.ignored-fs-types=^(autofs|binfmt_misc|cgroup|configfs|debugfs|devpts|devtmpfs|fusectl|hugetlbfs|mqueue|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|sysfs|tracefs)$
         ports:
           - name: metrics
             containerPort: 9100
             hostPort: 9100
         resources:
           requests:
-            memory: 30Mi
             cpu: 100m
-          limits:
             memory: 50Mi
+          limits:
             cpu: 200m
+            memory: 100Mi
         volumeMounts:
           - name: proc
             mountPath: /host/proc
@@ -50,6 +53,9 @@ spec:
           - name: sys
             mountPath: /host/sys
             readOnly: true
+          - name: root
+            mountPath: /host/root
+            readOnly: true
       tolerations:
         - effect: NoSchedule
           operator: Exists
@@ -60,3 +66,6 @@ spec:
         - name: sys
           hostPath:
             path: /sys
+        - name: root
+          hostPath:
+            path: /

addons/prometheus/rules.yaml

@@ -456,22 +456,22 @@ data:
     - name: node.rules
       rules:
       - record: instance:node_cpu:rate:sum
-        expr: sum(rate(node_cpu{mode!="idle",mode!="iowait",mode!~"^(?:guest.*)$"}[3m]))
+        expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!~"^(?:guest.*)$"}[3m]))
           BY (instance)
       - record: instance:node_filesystem_usage:sum
-        expr: sum((node_filesystem_size{mountpoint="/"} - node_filesystem_free{mountpoint="/"}))
+        expr: sum((node_filesystem_size_bytes{mountpoint="/"} - node_filesystem_free_bytes{mountpoint="/"}))
           BY (instance)
       - record: instance:node_network_receive_bytes:rate:sum
-        expr: sum(rate(node_network_receive_bytes[3m])) BY (instance)
+        expr: sum(rate(node_network_receive_bytes_total[3m])) BY (instance)
       - record: instance:node_network_transmit_bytes:rate:sum
-        expr: sum(rate(node_network_transmit_bytes[3m])) BY (instance)
+        expr: sum(rate(node_network_transmit_bytes_total[3m])) BY (instance)
       - record: instance:node_cpu:ratio
-        expr: sum(rate(node_cpu{mode!="idle"}[5m])) WITHOUT (cpu, mode) / ON(instance)
-          GROUP_LEFT() count(sum(node_cpu) BY (instance, cpu)) BY (instance)
+        expr: sum(rate(node_cpu_seconds_total{mode!="idle"}[5m])) WITHOUT (cpu, mode) / ON(instance)
+          GROUP_LEFT() count(sum(node_cpu_seconds_total) BY (instance, cpu)) BY (instance)
       - record: cluster:node_cpu:sum_rate5m
-        expr: sum(rate(node_cpu{mode!="idle"}[5m]))
+        expr: sum(rate(node_cpu_seconds_total{mode!="idle"}[5m]))
       - record: cluster:node_cpu:ratio
-        expr: cluster:node_cpu:rate5m / count(sum(node_cpu) BY (instance, cpu))
+        expr: cluster:node_cpu:sum_rate5m / count(sum(node_cpu_seconds_total) BY (instance, cpu))
       - alert: NodeExporterDown
         expr: absent(up{job="node-exporter"} == 1)
         for: 10m
@@ -481,7 +481,7 @@ data:
           description: Prometheus could not scrape a node-exporter for more than 10m,
             or node-exporters have disappeared from discovery
       - alert: NodeDiskRunningFull
-        expr: predict_linear(node_filesystem_free[6h], 3600 * 24) < 0
+        expr: predict_linear(node_filesystem_free_bytes[6h], 3600 * 24) < 0
         for: 30m
         labels:
           severity: warning
@@ -489,7 +489,7 @@ data:
           description: device {{$labels.device}} on node {{$labels.instance}} is running
             full within the next 24 hours (mounted at {{$labels.mountpoint}})
       - alert: NodeDiskRunningFull
-        expr: predict_linear(node_filesystem_free[30m], 3600 * 2) < 0
+        expr: predict_linear(node_filesystem_free_bytes[30m], 3600 * 2) < 0
         for: 10m
         labels:
           severity: critical