Merge pull request #178 from Cray-HPE/CASMMON-440-bug

CASMMON-440-VMscrape services and update resourecs
Cray-HPE · Sep 23, 2024 · d38a2aa · d38a2aa
2 parents 4f68b9d + c5218ec
commit d38a2aa
Show file tree

Hide file tree

Showing 3 changed files with 28 additions and 26 deletions.
diff --git a/kubernetes/cray-sysmgmt-health/Chart.yaml b/kubernetes/cray-sysmgmt-health/Chart.yaml
@@ -23,7 +23,7 @@
 #
 apiVersion: v2
 name: cray-sysmgmt-health
-version: 1.0.11
+version: 1.0.12
 description: An extension of the official prometheus-operator helm chart for monitoring
 keywords:
 - sysmgmt-health

diff --git a/kubernetes/cray-sysmgmt-health/dashboards_json/fluentbit/fluentbit.json b/kubernetes/cray-sysmgmt-health/dashboards_json/fluentbit/fluentbit.json
@@ -554,7 +554,25 @@
   "schemaVersion": 39,
   "tags": [],
   "templating": {
-    "list": []
+    "list": [
+      {
+        "current": {
+          "selected": false,
+          "text": "victorismetrics",
+          "value": "P1EB0681B67ED710F"
+        },
+        "hide": 2,
+        "includeAll": false,
+        "multi": false,
+        "name": "DS_PROMETHEUS",
+        "options": [],
+        "query": "prometheus",
+        "refresh": 1,
+        "regex": "",
+        "skipUrlSync": false,
+        "type": "datasource"
+      }
+    ]
   },
   "time": {
     "from": "now-15m",
@@ -589,6 +607,6 @@
   "timezone": "",
   "title": "FluentBit",
   "uid": "bNn5LUtiz",
-  "version": 2,
+  "version": 1,
   "weekStart": ""
 }
diff --git a/kubernetes/cray-sysmgmt-health/values.yaml b/kubernetes/cray-sysmgmt-health/values.yaml
@@ -260,8 +260,8 @@ victoria-metrics-k8s-stack:
           memory: 6Gi
         requests:
           cpu: '2'
-          memory: 2Gi
-      scrapeInterval: 25s
+          memory: 4Gi
+      scrapeInterval: 30s
       externalLabels:
         cluster: cluster-name
       shardCount: 2
@@ -361,11 +361,11 @@ victoria-metrics-k8s-stack:
                 storage: 50Gi
       resources:
         requests:
-          cpu: 3
-          memory: 3Gi
-        limits:
           cpu: 2
           memory: 2Gi
+        limits:
+          cpu: 4
+          memory: 4Gi
       # Configure external hostname for Istio ingress
       # Setup with Ansible
       # externalAuthority: alertmanager-shs.local
@@ -1089,22 +1089,6 @@ servicemonitors:
       metricsRelabelings: {}
       relabelings: {}
 
-  externaldnsEtcdExporter:
-    enabled: true
-    servicename: externaldns
-    cluster: etcd
-    serviceMonitor:
-      namespace: sysmgmt-health
-      port: http-client
-      matchNamespace:
-      - services
-      matchLabels:
-        etcd_cluster: cray-externaldns-etcd
-      interval: 30s
-      scheme: http
-      metricsRelabelings: {}
-      relabelings: {}
-
   fasEtcdExporter:
     enabled: true
     servicename: fas
@@ -1127,11 +1111,11 @@ servicemonitors:
     cluster: etcd
     serviceMonitor:
       namespace: sysmgmt-health
-      port: http-client
+      port: client
       matchNamespace:
       - services
       matchLabels:
-        etcd_cluster: cray-hbtd-etcd
+        app.kubernetes.io/name: cray-hbtd-bitnami-etcd
       interval: 30s
       scheme: http
       metricsRelabelings: {}