[kube-prometheus-stack] fix: use correct job name for dashboards to w…

…ork, make deployment more intuitively (#3672) * fix: use correct job name for dashboards to work, make deployment more intuitively Signed-off-by: Markus Lippert <[email protected]> * merge main Signed-off-by: Markus Lippert <[email protected]> * bump version Signed-off-by: Markus Lippert <[email protected]> --------- Signed-off-by: Markus Lippert <[email protected]>
prometheus-community · Sep 22, 2023 · 9c8e405 · 9c8e405
1 parent fe84f27
commit 9c8e405
Show file tree

Hide file tree

Showing 4 changed files with 56 additions and 36 deletions.
diff --git a/charts/kube-prometheus-stack/Chart.yaml b/charts/kube-prometheus-stack/Chart.yaml
@@ -21,7 +21,7 @@ name: kube-prometheus-stack
 sources:
   - https://github.com/prometheus-community/helm-charts
   - https://github.com/prometheus-operator/kube-prometheus
-version: 51.1.0
+version: 51.1.1
 appVersion: v0.68.0
 kubeVersion: ">=1.19.0-0"
 home: https://github.com/prometheus-operator/kube-prometheus

diff --git a/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/windows.node.rules.yaml b/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/windows.node.rules.yaml
@@ -26,41 +26,41 @@ spec:
     rules:
     - expr: |-
         count (
-          windows_system_system_up_time{job="{{ .Values.windowsMonitoring.job }}"}
+          windows_system_system_up_time{job="windows-exporter"}
         )
       record: node:windows_node:sum
     - expr: |-
         count by (instance) (sum by (instance, core) (
-          windows_cpu_time_total{job="{{ .Values.windowsMonitoring.job }}"}
+          windows_cpu_time_total{job="windows-exporter"}
         ))
       record: node:windows_node_num_cpu:sum
-    - expr: 1 - avg(rate(windows_cpu_time_total{job="{{ .Values.windowsMonitoring.job }}",mode="idle"}[1m]))
+    - expr: 1 - avg(rate(windows_cpu_time_total{job="windows-exporter",mode="idle"}[1m]))
       record: :windows_node_cpu_utilisation:avg1m
     - expr: |-
         1 - avg by (instance) (
-          rate(windows_cpu_time_total{job="{{ .Values.windowsMonitoring.job }}",mode="idle"}[1m])
+          rate(windows_cpu_time_total{job="windows-exporter",mode="idle"}[1m])
         )
       record: node:windows_node_cpu_utilisation:avg1m
     - expr: |-
         1 -
-        sum(windows_memory_available_bytes{job="{{ .Values.windowsMonitoring.job }}"})
+        sum(windows_memory_available_bytes{job="windows-exporter"})
         /
-        sum(windows_os_visible_memory_bytes{job="{{ .Values.windowsMonitoring.job }}"})
+        sum(windows_os_visible_memory_bytes{job="windows-exporter"})
       record: ':windows_node_memory_utilisation:'
-    - expr: sum(windows_memory_available_bytes{job="{{ .Values.windowsMonitoring.job }}"} + windows_memory_cache_bytes{job="{{ .Values.windowsMonitoring.job }}"})
+    - expr: sum(windows_memory_available_bytes{job="windows-exporter"} + windows_memory_cache_bytes{job="windows-exporter"})
       record: :windows_node_memory_MemFreeCached_bytes:sum
-    - expr: (windows_memory_cache_bytes{job="{{ .Values.windowsMonitoring.job }}"} + windows_memory_modified_page_list_bytes{job="{{ .Values.windowsMonitoring.job }}"} + windows_memory_standby_cache_core_bytes{job="{{ .Values.windowsMonitoring.job }}"} + windows_memory_standby_cache_normal_priority_bytes{job="{{ .Values.windowsMonitoring.job }}"} + windows_memory_standby_cache_reserve_bytes{job="{{ .Values.windowsMonitoring.job }}"})
+    - expr: (windows_memory_cache_bytes{job="windows-exporter"} + windows_memory_modified_page_list_bytes{job="windows-exporter"} + windows_memory_standby_cache_core_bytes{job="windows-exporter"} + windows_memory_standby_cache_normal_priority_bytes{job="windows-exporter"} + windows_memory_standby_cache_reserve_bytes{job="windows-exporter"})
       record: node:windows_node_memory_totalCached_bytes:sum
-    - expr: sum(windows_os_visible_memory_bytes{job="{{ .Values.windowsMonitoring.job }}"})
+    - expr: sum(windows_os_visible_memory_bytes{job="windows-exporter"})
       record: :windows_node_memory_MemTotal_bytes:sum
     - expr: |-
         sum by (instance) (
-          (windows_memory_available_bytes{job="{{ .Values.windowsMonitoring.job }}"})
+          (windows_memory_available_bytes{job="windows-exporter"})
         )
       record: node:windows_node_memory_bytes_available:sum
     - expr: |-
         sum by (instance) (
-          windows_os_visible_memory_bytes{job="{{ .Values.windowsMonitoring.job }}"}
+          windows_os_visible_memory_bytes{job="windows-exporter"}
         )
       record: node:windows_node_memory_bytes_total:sum
     - expr: |-
@@ -70,43 +70,43 @@ spec:
       record: node:windows_node_memory_utilisation:ratio
     - expr: 1 - (node:windows_node_memory_bytes_available:sum / node:windows_node_memory_bytes_total:sum)
       record: 'node:windows_node_memory_utilisation:'
-    - expr: irate(windows_memory_swap_page_operations_total{job="{{ .Values.windowsMonitoring.job }}"}[5m])
+    - expr: irate(windows_memory_swap_page_operations_total{job="windows-exporter"}[5m])
       record: node:windows_node_memory_swap_io_pages:irate
     - expr: |-
-        avg(irate(windows_logical_disk_read_seconds_total{job="{{ .Values.windowsMonitoring.job }}"}[1m]) +
-            irate(windows_logical_disk_write_seconds_total{job="{{ .Values.windowsMonitoring.job }}"}[1m])
+        avg(irate(windows_logical_disk_read_seconds_total{job="windows-exporter"}[1m]) +
+            irate(windows_logical_disk_write_seconds_total{job="windows-exporter"}[1m])
           )
       record: :windows_node_disk_utilisation:avg_irate
     - expr: |-
         avg by (instance) (
-          (irate(windows_logical_disk_read_seconds_total{job="{{ .Values.windowsMonitoring.job }}"}[1m]) +
-           irate(windows_logical_disk_write_seconds_total{job="{{ .Values.windowsMonitoring.job }}"}[1m]))
+          (irate(windows_logical_disk_read_seconds_total{job="windows-exporter"}[1m]) +
+           irate(windows_logical_disk_write_seconds_total{job="windows-exporter"}[1m]))
         )
       record: node:windows_node_disk_utilisation:avg_irate
     - expr: |-
         max by (instance,volume)(
-          (windows_logical_disk_size_bytes{job="{{ .Values.windowsMonitoring.job }}"}
-        - windows_logical_disk_free_bytes{job="{{ .Values.windowsMonitoring.job }}"})
-        / windows_logical_disk_size_bytes{job="{{ .Values.windowsMonitoring.job }}"}
+          (windows_logical_disk_size_bytes{job="windows-exporter"}
+        - windows_logical_disk_free_bytes{job="windows-exporter"})
+        / windows_logical_disk_size_bytes{job="windows-exporter"}
         )
       record: 'node:windows_node_filesystem_usage:'
-    - expr: max by (instance, volume) (windows_logical_disk_free_bytes{job="{{ .Values.windowsMonitoring.job }}"} / windows_logical_disk_size_bytes{job="{{ .Values.windowsMonitoring.job }}"})
+    - expr: max by (instance, volume) (windows_logical_disk_free_bytes{job="windows-exporter"} / windows_logical_disk_size_bytes{job="windows-exporter"})
       record: 'node:windows_node_filesystem_avail:'
-    - expr: sum(irate(windows_net_bytes_total{job="{{ .Values.windowsMonitoring.job }}"}[1m]))
+    - expr: sum(irate(windows_net_bytes_total{job="windows-exporter"}[1m]))
       record: :windows_node_net_utilisation:sum_irate
     - expr: |-
         sum by (instance) (
-          (irate(windows_net_bytes_total{job="{{ .Values.windowsMonitoring.job }}"}[1m]))
+          (irate(windows_net_bytes_total{job="windows-exporter"}[1m]))
         )
       record: node:windows_node_net_utilisation:sum_irate
     - expr: |-
-        sum(irate(windows_net_packets_received_discarded_total{job="{{ .Values.windowsMonitoring.job }}"}[1m])) +
-        sum(irate(windows_net_packets_outbound_discarded_total{job="{{ .Values.windowsMonitoring.job }}"}[1m]))
+        sum(irate(windows_net_packets_received_discarded_total{job="windows-exporter"}[1m])) +
+        sum(irate(windows_net_packets_outbound_discarded_total{job="windows-exporter"}[1m]))
       record: :windows_node_net_saturation:sum_irate
     - expr: |-
         sum by (instance) (
-          (irate(windows_net_packets_received_discarded_total{job="{{ .Values.windowsMonitoring.job }}"}[1m]) +
-          irate(windows_net_packets_outbound_discarded_total{job="{{ .Values.windowsMonitoring.job }}"}[1m]))
+          (irate(windows_net_packets_received_discarded_total{job="windows-exporter"}[1m]) +
+          irate(windows_net_packets_outbound_discarded_total{job="windows-exporter"}[1m]))
         )
       record: node:windows_node_net_saturation:sum_irate
 {{- end }}
diff --git a/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/windows.pod.rules.yaml b/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/windows.pod.rules.yaml
@@ -24,17 +24,17 @@ spec:
   groups:
   - name: windows.pod.rules
     rules:
-    - expr: windows_container_available{job="{{ .Values.windowsMonitoring.job }}"} * on(container_id) group_left(container, pod, namespace) max(kube_pod_container_info{job="kube-state-metrics"}) by(container, container_id, pod, namespace)
+    - expr: windows_container_available{job="windows-exporter"} * on(container_id) group_left(container, pod, namespace) max(kube_pod_container_info{job="kube-state-metrics"}) by(container, container_id, pod, namespace)
       record: windows_pod_container_available
-    - expr: windows_container_cpu_usage_seconds_total{job="{{ .Values.windowsMonitoring.job }}"} * on(container_id) group_left(container, pod, namespace) max(kube_pod_container_info{job="kube-state-metrics"}) by(container, container_id, pod, namespace)
+    - expr: windows_container_cpu_usage_seconds_total{job="windows-exporter"} * on(container_id) group_left(container, pod, namespace) max(kube_pod_container_info{job="kube-state-metrics"}) by(container, container_id, pod, namespace)
       record: windows_container_total_runtime
-    - expr: windows_container_memory_usage_commit_bytes{job="{{ .Values.windowsMonitoring.job }}"} * on(container_id) group_left(container, pod, namespace) max(kube_pod_container_info{job="kube-state-metrics"}) by(container, container_id, pod, namespace)
+    - expr: windows_container_memory_usage_commit_bytes{job="windows-exporter"} * on(container_id) group_left(container, pod, namespace) max(kube_pod_container_info{job="kube-state-metrics"}) by(container, container_id, pod, namespace)
       record: windows_container_memory_usage
-    - expr: windows_container_memory_usage_private_working_set_bytes{job="{{ .Values.windowsMonitoring.job }}"} * on(container_id) group_left(container, pod, namespace) max(kube_pod_container_info{job="kube-state-metrics"}) by(container, container_id, pod, namespace)
+    - expr: windows_container_memory_usage_private_working_set_bytes{job="windows-exporter"} * on(container_id) group_left(container, pod, namespace) max(kube_pod_container_info{job="kube-state-metrics"}) by(container, container_id, pod, namespace)
       record: windows_container_private_working_set_usage
-    - expr: windows_container_network_receive_bytes_total{job="{{ .Values.windowsMonitoring.job }}"} * on(container_id) group_left(container, pod, namespace) max(kube_pod_container_info{job="kube-state-metrics"}) by(container, container_id, pod, namespace)
+    - expr: windows_container_network_receive_bytes_total{job="windows-exporter"} * on(container_id) group_left(container, pod, namespace) max(kube_pod_container_info{job="kube-state-metrics"}) by(container, container_id, pod, namespace)
       record: windows_container_network_received_bytes_total
-    - expr: windows_container_network_transmit_bytes_total{job="{{ .Values.windowsMonitoring.job }}"} * on(container_id) group_left(container, pod, namespace) max(kube_pod_container_info{job="kube-state-metrics"}) by(container, container_id, pod, namespace)
+    - expr: windows_container_network_transmit_bytes_total{job="windows-exporter"} * on(container_id) group_left(container, pod, namespace) max(kube_pod_container_info{job="kube-state-metrics"}) by(container, container_id, pod, namespace)
       record: windows_container_network_transmitted_bytes_total
     - expr: |-
         max by (namespace, pod, container) (

diff --git a/charts/kube-prometheus-stack/values.yaml b/charts/kube-prometheus-stack/values.yaml
@@ -201,10 +201,30 @@ global:
   # - "image-pull-secret"
 
 windowsMonitoring:
-  ## Deploys the windows-exporter and Windows-specific dashboards and rules
+  ## Deploys the windows-exporter and Windows-specific dashboards and rules (job name must be 'windows-exporter')
   enabled: false
-  ## Job must match jobLabel in the PodMonitor/ServiceMonitor and is used for the rules
-  job: prometheus-windows-exporter
+
+## Configuration for prometheus-windows-exporter
+## ref: https://github.com/prometheus-community/helm-charts/tree/main/charts/prometheus-windows-exporter
+##
+prometheus-windows-exporter:
+  ## Enable ServiceMonitor and set Kubernetes label to use as a job label
+  ##
+  prometheus:
+    monitor:
+      enabled: true
+      jobLabel: jobLabel
+
+  ## Set job label to 'windows-exporter' as required by the default Prometheus rules and Grafana dashboards
+  ##
+  podLabels:
+    jobLabel: windows-exporter
+
+  ## Enable memory and container metrics as required by the default Prometheus rules and Grafana dashboards
+  ##
+  config: |-
+    collectors:
+      enabled: '[defaults],memory,container'
 
 ## Configuration for alertmanager
 ## ref: https://prometheus.io/docs/alerting/alertmanager/