diff --git a/jsonnetfile.lock.json b/jsonnetfile.lock.json index 851982e6f9b1dbee99419c00564528c24dad3565..fa530d0dfccea1e27f0d09d454558149a678c65d 100644 --- a/jsonnetfile.lock.json +++ b/jsonnetfile.lock.json @@ -8,7 +8,7 @@ "subdir": "jsonnet/kube-prometheus" } }, - "version": "81b9c9f9f6886ba1fbd61b05cdf0cc4f4d95eba8" + "version": "e85d2f3b64c65f81aec7093dda880376a6719fe1" }, { "name": "ksonnet", @@ -18,7 +18,7 @@ "subdir": "" } }, - "version": "d03da231d6c8bd74437b74a1e9e8b966f13dffa2" + "version": "0d2f82676817bbf9e4acf6495b2090205f323b9f" }, { "name": "kubernetes-mixin", @@ -28,7 +28,7 @@ "subdir": "" } }, - "version": "ae58a33e85b191a8760a8d1bd8d3cda2fd046d05" + "version": "af494738e1709998696ffbce9296063a20c80692" }, { "name": "grafonnet", @@ -38,7 +38,7 @@ "subdir": "grafonnet" } }, - "version": "a6896d19aedc46ecf80dd64967191b9fd6f75f45" + "version": "bcd95ffa00fc4a58d34832f88f4b366effeb63ad" }, { "name": "grafana-builder", @@ -48,7 +48,7 @@ "subdir": "grafana-builder" } }, - "version": "a73d6c3e7f5804fc7a16f592b42a62384605046c" + "version": "de367fc28346fbf5a9afdef887ea20d9ffb7e927" }, { "name": "grafana", @@ -58,7 +58,7 @@ "subdir": "grafana" } }, - "version": "b6db6bdbdc8d7f2f8834a8044897ea6322a0f6ad" + "version": "c27d2792764867cdaf6484f067cc875cb8aef2f6" }, { "name": "prometheus-operator", @@ -78,7 +78,7 @@ "subdir": "Documentation/etcd-mixin" } }, - "version": "919b93b742c76b12a83bdf8885fa75f11db6bcac" + "version": "d6280f9ea54849e5364545ca34bdac0a58317569" } ] } diff --git a/manifests/prometheus-rules.yaml b/manifests/prometheus-rules.yaml index 33359312200f015f886eb40b023c401bb9d65d36..92b131c9286e291dc8484d6b2f654fbe79f8ba43 100644 --- a/manifests/prometheus-rules.yaml +++ b/manifests/prometheus-rules.yaml @@ -13,40 +13,26 @@ spec: - expr: | sum(rate(container_cpu_usage_seconds_total{job="kubelet", image!="", container_name!=""}[5m])) by (namespace) record: namespace:container_cpu_usage_seconds_total:sum_rate - - expr: | - sum by (namespace, pod_name, container_name) ( - rate(container_cpu_usage_seconds_total{job="kubelet", image!="", container_name!=""}[5m]) - ) - record: namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate - expr: | sum(container_memory_usage_bytes{job="kubelet", image!="", container_name!=""}) by (namespace) record: namespace:container_memory_usage_bytes:sum - expr: | - sum by (namespace, label_name) ( - sum(rate(container_cpu_usage_seconds_total{job="kubelet", image!="", container_name!=""}[5m])) by (namespace, pod_name) - * on (namespace, pod_name) group_left(label_name) - label_replace(kube_pod_labels{job="kube-state-metrics"}, "pod_name", "$1", "pod", "(.*)") - ) - record: namespace_name:container_cpu_usage_seconds_total:sum_rate - - expr: | - sum by (namespace, label_name) ( - sum(container_memory_usage_bytes{job="kubelet",image!="", container_name!=""}) by (pod_name, namespace) - * on (namespace, pod_name) group_left(label_name) - label_replace(kube_pod_labels{job="kube-state-metrics"}, "pod_name", "$1", "pod", "(.*)") + sum by (namespace, pod_name, container_name) ( + rate(container_cpu_usage_seconds_total{job="kubelet", image!="", container_name!=""}[5m]) ) - record: namespace_name:container_memory_usage_bytes:sum + record: namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate - expr: | - sum by (namespace, label_name) ( - sum(kube_pod_container_resource_requests_memory_bytes{job="kube-state-metrics"} * on (endpoint, instance, job, namespace, pod, service) group_left(phase) (kube_pod_status_phase{phase=~"^(Pending|Running)$"} == 1)) by (namespace, pod) - * on (namespace, pod) group_left(label_name) - label_replace(kube_pod_labels{job="kube-state-metrics"}, "pod_name", "$1", "pod", "(.*)") + sum by(namespace) ( + kube_pod_container_resource_requests_memory_bytes{job="kube-state-metrics"} + * on (endpoint, instance, job, namespace, pod, service) + group_left(phase) (kube_pod_status_phase{phase=~"^(Pending|Running)$"} == 1) ) record: namespace_name:kube_pod_container_resource_requests_memory_bytes:sum - expr: | - sum by (namespace, label_name) ( - sum(kube_pod_container_resource_requests_cpu_cores{job="kube-state-metrics"} * on (endpoint, instance, job, namespace, pod, service) group_left(phase) (kube_pod_status_phase{phase=~"^(Pending|Running)$"} == 1)) by (namespace, pod) - * on (namespace, pod) group_left(label_name) - label_replace(kube_pod_labels{job="kube-state-metrics"}, "pod_name", "$1", "pod", "(.*)") + sum by (namespace) ( + kube_pod_container_resource_requests_cpu_cores{job="kube-state-metrics"} + * on (endpoint, instance, job, namespace, pod, service) + group_left(phase) (kube_pod_status_phase{phase=~"^(Pending|Running)$"} == 1) ) record: namespace_name:kube_pod_container_resource_requests_cpu_cores:sum - expr: |