add cluster:node_cpu:ratio_rate5m

Azure · Aug 3, 2022 · 29c7ad9 · 29c7ad9
1 parent da75fe8
commit 29c7ad9
Show file tree

Hide file tree

Showing 3 changed files with 11 additions and 12 deletions.
diff --git a/GeneratedMonitoringArtifacts/Default/DefaultRecordingRulesRuleGroups.json b/GeneratedMonitoringArtifacts/Default/DefaultRecordingRulesRuleGroups.json
@@ -185,6 +185,10 @@
                     {
                         "record": ":node_memory_MemAvailable_bytes:sum",
                         "expression": "sum(  node_memory_MemAvailable_bytes{job=\"node\"} or  (    node_memory_Buffers_bytes{job=\"node\"} +    node_memory_Cached_bytes{job=\"node\"} +    node_memory_MemFree_bytes{job=\"node\"} +    node_memory_Slab_bytes{job=\"node\"}  )) by (cluster)"
+                    },
+                    {
+                        "record": "cluster:node_cpu:ratio_rate5m",
+                        "expression": "sum(rate(node_cpu_seconds_total{job=\"node\",mode!=\"idle\",mode!=\"iowait\",mode!=\"steal\"}[5m])) by (cluster) /count(sum(node_cpu_seconds_total{job=\"node\"}) by (cluster, instance, cpu)) by (cluster)"
                     }
                 ]
 

diff --git a/GeneratedMonitoringArtifacts/DefaultRecordingRulesList.txt b/GeneratedMonitoringArtifacts/DefaultRecordingRulesList.txt
@@ -1,10 +1,14 @@
+# Below are the default Recording Rules for Linux
+# One of these has 4 actuall RR's (for different workload types)
+# So count is below = 3 - currently 30
 namespace_workload_pod:kube_pod_owner:relabel
 node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate
 namespace_cpu:kube_pod_container_resource_requests:sum
 namespace_cpu:kube_pod_container_resource_limits:sum
 :node_memory_MemAvailable_bytes:sum
 namespace_memory:kube_pod_container_resource_requests:sum
 namespace_memory:kube_pod_container_resource_limits:sum
+cluster:node_cpu:ratio_rate5m
 cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests
 cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits
 cluster:namespace:pod_memory:active:kube_pod_container_resource_requests
@@ -23,13 +27,4 @@ instance_device:node_disk_io_time_weighted_seconds:rate5m
 node_namespace_pod_container:container_memory_working_set_bytes
 node_namespace_pod_container:container_memory_rss
 node_namespace_pod_container:container_memory_cache
-node_namespace_pod_container:container_memory_swap
-node:windows_node_cpu_utilisation:avg3m
-node:windows_node_memory_utilisation: 
-node:windows_node_memory_totalCached_bytes:sum 
-node:windows_node_memory_swap_io_pages:irate 
-node:windows_node_disk_utilisation:avg_irate 
-node:windows_node_net_utilisation:sum_irate 
-node:windows_node_net_saturation:sum_irate 
-node:windows_node_filesystem_usage: . 
-namespace_pod_container:windows_container_cpu_usage_seconds_total:sum_rate 
+node_namespace_pod_container:container_memory_swap
diff --git a/mixins/kubernetes/rules/node.libsonnet b/mixins/kubernetes/rules/node.libsonnet
@@ -56,8 +56,8 @@
             // This rule gives cpu utilization per cluster
             record: 'cluster:node_cpu:ratio_rate5m',
             expr: |||
-              sum(rate(node_cpu_seconds_total{%(nodeExporterSelector)s,mode!="idle",mode!="iowait",mode!="steal"}[5m])) /
-              count(sum(node_cpu_seconds_total{%(nodeExporterSelector)s}) by (%(clusterLabel)s, instance, cpu))
+              sum(rate(node_cpu_seconds_total{%(nodeExporterSelector)s,mode!="idle",mode!="iowait",mode!="steal"}[5m])) by (%(clusterLabel)s) /
+              count(sum(node_cpu_seconds_total{%(nodeExporterSelector)s}) by (%(clusterLabel)s, instance, cpu)) by (%(clusterLabel)s)
             ||| % $._config,
           },
         ],