enable hwmon for sensor collection for bare metal clusters

Enable the hwmon data collection so that hardware telemetry like CPU
temperature and fan speeds are available for bare metal clusters.

Signed-off-by: Doug Hellmann <[email protected]>

Author: dhellmann

CHANGELOG.md

@@ -7,6 +7,7 @@
   - Adjusted NodeClockNotSynchronising, NodeNetworkReceiveErrs, and NodeNetworkTransmitErrs alerts.
 - [#962](https://github.com/openshift/cluster-monitoring-operator/pull/962) Enable namespace by pod and pod total networking Grafana dashboards.
 - [#959](https://github.com/openshift/cluster-monitoring-operator/pull/959) Remove memory limits from prometheus-config-reloader in user workload monitoring
+- [#971](https://github.com/openshift/cluster-monitoring-operator/pull/971) Enable `hwmon` in node-exporter for hardware sensor data collection
 
 ## 4.6
 

assets/node-exporter/daemonset.yaml

@@ -23,7 +23,6 @@ spec:
         - --path.sysfs=/host/sys
         - --path.rootfs=/host/root
         - --no-collector.wifi
-        - --no-collector.hwmon
         - --collector.filesystem.ignored-mount-points=^/(dev|proc|sys|var/lib/docker/.+|var/lib/kubelet/pods/.+)($|/)
         - --collector.mountstats
         - --collector.cpu.info

jsonnet/node-exporter.jsonnet

@@ -123,7 +123,10 @@ local tlsVolumeName = 'node-exporter-tls';
                       }
                     else
                       c {
-                        args+: ['--collector.mountstats', '--collector.cpu.info', '--collector.textfile.directory=' + textfileDir],
+		        // Remove the flag to disable hwmon that is set upstream so we
+			// gather that data (especially for bare metal clusters), and
+			// add flags to collect data not included by default.
+                        args: [a for a in c.args if a != '--no-collector.hwmon'] + ['--collector.mountstats', '--collector.cpu.info', '--collector.textfile.directory=' + textfileDir],
                         terminationMessagePolicy: 'FallbackToLogsOnError',
                         volumeMounts+: [
                           containerVolumeMount.new(textfileVolumeName, textfileDir, true),

manifests/0000_50_cluster-monitoring-operator_02-role.yaml

@@ -19,8 +19,8 @@
 # 	assets/prometheus-k8s/cluster-role.yaml
 # 	assets/prometheus-k8s/role-config.yaml
 # 	assets/prometheus-k8s/role-specific-namespaces.yaml
-# 	assets/prometheus-operator-user-workload/cluster-role.yaml
 # 	assets/prometheus-operator/cluster-role.yaml
+# 	assets/prometheus-operator-user-workload/cluster-role.yaml
 # 	assets/prometheus-user-workload/cluster-role.yaml
 # 	assets/prometheus-user-workload/role-config.yaml
 # 	assets/prometheus-user-workload/role-specific-namespaces.yaml
@@ -419,20 +419,6 @@ rules:
   verbs:
   - list
   - watch
-- apiGroups:
-  - apiextensions.k8s.io
-  resourceNames:
-  - alertmanagers.monitoring.coreos.com
-  - podmonitors.monitoring.coreos.com
-  - prometheuses.monitoring.coreos.com
-  - prometheusrules.monitoring.coreos.com
-  - servicemonitors.monitoring.coreos.com
-  - thanosrulers.monitoring.coreos.com
-  resources:
-  - customresourcedefinitions
-  verbs:
-  - get
-  - update
 - apiGroups:
   - ''
   resources:
@@ -448,12 +434,6 @@ rules:
   - get
   - list
   - watch
-- apiGroups:
-  - apiextensions.k8s.io
-  resources:
-  - customresourcedefinitions
-  verbs:
-  - create
 - apiGroups:
   - apps
   resources:
@@ -478,6 +458,26 @@ rules:
   - delete
   - get
   - update
+- apiGroups:
+  - apiextensions.k8s.io
+  resourceNames:
+  - alertmanagers.monitoring.coreos.com
+  - podmonitors.monitoring.coreos.com
+  - prometheuses.monitoring.coreos.com
+  - prometheusrules.monitoring.coreos.com
+  - servicemonitors.monitoring.coreos.com
+  - thanosrulers.monitoring.coreos.com
+  resources:
+  - customresourcedefinitions
+  verbs:
+  - get
+  - update
+- apiGroups:
+  - apiextensions.k8s.io
+  resources:
+  - customresourcedefinitions
+  verbs:
+  - create
 - apiGroups:
   - monitoring.coreos.com
   resources: