Added Fault Dashboards and Bump sub-chart version

charts/aci-monitoring-stack/Chart.lock

@@ -0,0 +1,15 @@
+dependencies:
+- name: prometheus
+  repository: https://prometheus-community.github.io/helm-charts
+  version: 25.27.0
+- name: loki
+  repository: https://grafana.github.io/helm-charts
+  version: 6.12.0
+- name: promtail
+  repository: https://grafana.github.io/helm-charts
+  version: 6.16.6
+- name: grafana
+  repository: https://grafana.github.io/helm-charts
+  version: 8.5.1
+digest: sha256:2b6c353c5b8e85d90ea29616103c716b26e8367a4b50a9fd69602f4e0ffba962
+generated: "2024-09-19T16:37:22.820798857+10:00"

charts/aci-monitoring-stack/Chart.yaml

@@ -23,18 +23,18 @@ version: 0.1.2
 appVersion: "v0.8.0"
 dependencies:
 - name: prometheus
-  version: "25.24.1"
+  version: "25.27.0"
   repository: "https://prometheus-community.github.io/helm-charts"
   condition: prometheus.enabled
 - name: loki
-  version: "6.7.3"
+  version: "6.12.0"
   repository: "https://grafana.github.io/helm-charts"
   condition: loki.enabled
 - name: "promtail"
   condition: promtail.enabled
   repository: "https://grafana.github.io/helm-charts"
-  version: "6.16.4"
+  version: "6.16.6"
 - name: "grafana"
   condition: grafana.enabled
   repository: "https://grafana.github.io/helm-charts"
-  version: "8.3.6"
+  version: "8.5.1"

charts/aci-monitoring-stack/config.d/system.yaml

@@ -74,6 +74,36 @@ class_queries:
         # This is used as a workaround so I can set the nodeid == fabric to detect fabric wide metrics
         regex: "^uni/(?P<nodeid>.*)/compcat-default"
 
+  fault_insts:
+    class_name: faultInst
+    query_parameter: '?order-by=faultInst.dn&query-target-filter=and(not(wcard(faultInst.dn,"__ui_")))'
+    metrics:
+      - name: faults
+        value_name: faultInst.attributes.lastTransition
+        # Use the time the profile was applied
+        value_regex_transformation: "(?P<lastTransition>.*)"
+        value_calculation: "lastTransition"
+        help: Returns the faults last transition time
+    labels:
+      - property_name: faultInst.attributes.ack
+        regex: "(?P<ack>.*)"
+      - property_name: faultInst.attributes.dn
+        regex: "(?P<dn>.*)"
+      - property_name: faultInst.attributes.cause
+        regex: "(?P<cause>.*)"
+      - property_name: faultInst.attributes.created
+        regex: "(?P<created>.*)"
+      - property_name: faultInst.attributes.descr
+        regex: "(?P<descr>.*)"
+      - property_name: faultInst.attributes.code
+        regex: "(?P<code>.*)"
+      - property_name: faultInst.attributes.severity
+        regex: "(?P<severity>.*)"
+      - property_name: faultInst.attributes.domain
+        regex: "(?P<domain>.*)"
+      - property_name: faultInst.attributes.type
+        regex: "(?P<type>.*)"
+
 
 compound_queries:
   object_count:

charts/aci-monitoring-stack/templates/prometheus/configmap-config.yaml

@@ -29,7 +29,7 @@ data:
             # DO NOT INSERT SPACES and use \ for next line or aci-exporter will not be able to parse the queries
           queries:
             - "health,fabric_node_info,max_capacity,max_global_pctags,\
-              vlans,static_binding_info,node_count,object_count,\
+              vlans,static_binding_info,node_count,object_count,fault_insts,\
               ps_power_usage,apic_hw_sensors,controller_topsystem"
         scheme: http
         http_sd_configs: