Minor changes in nopo11y-stack (#3)

* Updated SLO dashboard * Removed not required metrics from the alerts * Updated chart version to 1.1.1 * Updated nopo11y health check values
znsio · May 17, 2024 · f20d4c9 · f20d4c9
1 parent f823951
commit f20d4c9
Show file tree

Hide file tree

Showing 4 changed files with 11 additions and 26 deletions.
diff --git a/charts/nopo11y-stack/Chart.yaml b/charts/nopo11y-stack/Chart.yaml
@@ -40,4 +40,4 @@ dependencies:
 description: A Helm chart for observability stack
 name: nopo11y-stack
 type: application
-version: 1.1.0
+version: 1.1.1
diff --git a/charts/nopo11y-stack/dashboards/slo-details.json b/charts/nopo11y-stack/dashboards/slo-details.json
@@ -388,7 +388,7 @@
               "lastNotNull"
             ],
             "fields": "",
-            "values": false
+            "values": true
           },
           "text": {},
           "textMode": "name"
@@ -587,7 +587,7 @@
               "lastNotNull"
             ],
             "fields": "",
-            "values": false
+            "values": true
           },
           "text": {},
           "textMode": "name"
@@ -658,7 +658,7 @@
               "lastNotNull"
             ],
             "fields": "",
-            "values": false
+            "values": true
           },
           "text": {},
           "textMode": "value_and_name"
@@ -729,7 +729,7 @@
               "lastNotNull"
             ],
             "fields": "",
-            "values": false
+            "values": true
           },
           "text": {},
           "textMode": "value_and_name"
@@ -800,7 +800,7 @@
               "lastNotNull"
             ],
             "fields": "",
-            "values": false
+            "values": true
           },
           "text": {},
           "textMode": "value_and_name"
@@ -1096,7 +1096,7 @@
               "lastNotNull"
             ],
             "fields": "",
-            "values": false
+            "values": true
           },
           "text": {},
           "textMode": "value_and_name"
@@ -1181,7 +1181,7 @@
               "lastNotNull"
             ],
             "fields": "",
-            "values": false
+            "values": true
           },
           "text": {},
           "textMode": "value_and_name"

diff --git a/charts/nopo11y-stack/templates/alerts.yaml b/charts/nopo11y-stack/templates/alerts.yaml
@@ -12,14 +12,10 @@ spec:
     - alert: HighCpuUtilization
       expr: |
         sum(
-                node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate
-              * on(pod)
-                group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel
+              rate(container_cpu_usage_seconds_total{container!=""}[5m])
             ) by (pod)
             /sum(
                 kube_pod_container_resource_limits{resource="cpu"}
-              * on(namespace,pod)
-                group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel
             ) by (pod) * 100 > 75
       for: 5m
       annotations:
@@ -30,14 +26,10 @@ spec:
     - alert: HighCpuUtilization
       expr: |
         sum(
-                node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate
-              * on(pod)
-                group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel
+                rate(container_cpu_usage_seconds_total{container!=""}[5m])
             ) by (pod)
             /sum(
                 kube_pod_container_resource_limits{resource="cpu"}
-              * on(namespace,pod)
-                group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel
             ) by (pod) * 100 > 90
       for: 5m
       annotations:
@@ -49,13 +41,9 @@ spec:
       expr: |
         sum(
                 container_memory_working_set_bytes{container!="", image!=""}
-              * on(pod)
-                group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel
             ) by (pod)
             /sum(
                 kube_pod_container_resource_limits{job="kube-state-metrics", resource="memory"}
-              * on(namespace,pod)
-                group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel
             ) by (pod) * 100 > 75
       for: 5m
       annotations:
@@ -66,13 +54,9 @@ spec:
     - alert: HighMemoryUtilization
       expr: sum(
                 container_memory_working_set_bytes{container!="", image!=""}
-              * on(pod)
-                group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel
             ) by (pod)
             /sum(
                 kube_pod_container_resource_limits{job="kube-state-metrics", resource="memory"}
-              * on(namespace,pod)
-                group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel
             ) by (pod) * 100 > 90
       annotations:
         description: Memory utilization of pod {{ "{{" }} $labels.pod {{ "}}" }} is went above 90%.

diff --git a/charts/nopo11y-stack/values.yaml b/charts/nopo11y-stack/values.yaml
@@ -16028,6 +16028,7 @@ nopo11y_health_check:
      memory: 100Mi
   ## You can provide the below environment variables to the health check
   ## NAMESPACE - default is default namespace
+  ## HEALTHY_PODS_PERCENTAGE - default is 30%
   ## HEALTHY_POD_CPU_UTILIZATION_THRESHOLD - default is 80%
   ## HEALTHY_POD_MEMORY_UTILIZATION_THRESHOLD - default is 80%
   ## HEALTHY_PVC_FREE_SPACE - default is 200mb