fixed some incompatibilities with old metrics

Author: wtripp180901

ansible/roles/grafana-dashboards/files/openhpc-slurm.json

@@ -1950,15 +1950,15 @@
         "allValue": null,
         "current": {},
         "datasource": "${DS_PROMETHEUS}",
-        "definition": "label_values(node_cpu_seconds_total{job=~\"node-exporter\"}, cluster_env)",
+        "definition": "label_values(node_cpu_seconds_total{job=~\"node-exporter\"}, env)",
         "error": null,
         "hide": 0,
         "includeAll": true,
         "label": "Environment",
         "multi": true,
-        "name": "cluster_env",
+        "name": "env",
         "options": [],
-        "query": "label_values(node_cpu_seconds_total{job=~\"node-exporter\"}, cluster_env)",
+        "query": "label_values(node_cpu_seconds_total{job=~\"node-exporter\"}, env)",
         "refresh": 1,
         "regex": "",
         "skipUrlSync": false,
@@ -1994,15 +1994,15 @@
         "allValue": null,
         "current": {},
         "datasource": "${DS_PROMETHEUS}",
-        "definition": "label_values(node_cpu_seconds_total{job=~\"node-exporter\", cluster_env=~\"$cluster_env\", instance=~\"$host_filter\"}, instance)",
+        "definition": "label_values(node_cpu_seconds_total{job=~\"node-exporter\", env=~\"$env\", instance=~\"$host_filter\"}, instance)",
         "error": null,
         "hide": 0,
         "includeAll": true,
         "label": null,
         "multi": true,
         "name": "instance",
         "options": [],
-        "query": "label_values(node_cpu_seconds_total{job=~\"node-exporter\", cluster_env=~\"$cluster_env\", instance=~\"$host_filter\"}, instance)",
+        "query": "label_values(node_cpu_seconds_total{job=~\"node-exporter\", env=~\"$env\", instance=~\"$host_filter\"}, instance)",
         "refresh": 1,
         "regex": "",
         "skipUrlSync": false,

ansible/roles/kube_prometheus_stack/defaults/main/helm.yml

@@ -181,8 +181,9 @@ kube_prometheus_stack_release_defaults:
             targetLabel: instance
             replacement: $1
             action: replace
-        metricRelabelings:
-          - targetLabel: cluster_env
+          - targetLabel: env
+            sourceLabels: [env]
+            regex: ^$
             replacement: ungrouped
 
 kube_prometheus_stack_release_overrides: {}

docs/monitoring-and-logging.README.md

@@ -256,6 +256,7 @@ This appliance customises the default set of collectors to a minimal set, these
 - cpufreq
 - diskstats
 - filesystem
+- uname
 
 The list can be customised by adding or removing `--collector` flags to Node Exporter's command line arguments. The defaults can be found in:
 
@@ -265,7 +266,7 @@ The list can be customised by adding or removing `--collector` flags to Node Exp
 
 #### prometheus_node_exporter_targets
 
-Groups prometheus targets into per environment groups. The ansible variable, `cluster_env` is used to determine the grouping. The metrics for each target in the group are given the prometheus label, `cluster_env: $cluster_env`, where `$cluster_env` is the value of the `cluster_env` variable for that host.
+Groups prometheus targets into per environment groups. The ansible variable, `env` is used to determine the grouping. The metrics for each target in the group are given the prometheus label, `env: $env`, where `$env` is the value of the `env` variable for that host.
 
 ## slurm-stats
 

environments/common/inventory/group_vars/all/node_exporter.yml

@@ -10,3 +10,4 @@ node_exporter_args:
   - --collector.cpufreq
   - --collector.diskstats
   - --collector.filesystem
+  - --collector.uname