diff --git a/jsonnet/kube-prometheus/rules/node-rules.libsonnet b/jsonnet/kube-prometheus/rules/node-rules.libsonnet index acd05424ae2450bc52443d16421855352e7f7cbc..8cdee4798116642e10beabf8a72226c9ec88e5eb 100644 --- a/jsonnet/kube-prometheus/rules/node-rules.libsonnet +++ b/jsonnet/kube-prometheus/rules/node-rules.libsonnet @@ -5,7 +5,7 @@ name: 'kube-prometheus-node-recording.rules', rules: [ { - expr: 'sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait"}[3m])) BY (instance)', + expr: 'sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[3m])) BY (instance)', record: 'instance:node_cpu:rate:sum', }, { @@ -17,11 +17,11 @@ record: 'instance:node_network_transmit_bytes:rate:sum', }, { - expr: 'sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait"}[5m])) WITHOUT (cpu, mode) / ON(instance) GROUP_LEFT() count(sum(node_cpu_seconds_total) BY (instance, cpu)) BY (instance)', + expr: 'sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m])) WITHOUT (cpu, mode) / ON(instance) GROUP_LEFT() count(sum(node_cpu_seconds_total) BY (instance, cpu)) BY (instance)', record: 'instance:node_cpu:ratio', }, { - expr: 'sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait"}[5m]))', + expr: 'sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m]))', record: 'cluster:node_cpu:sum_rate5m', }, { diff --git a/manifests/prometheus-rules.yaml b/manifests/prometheus-rules.yaml index a46fe442fb21627b1c7358502f39e77e6096c351..43951b816c0dfdcc418f0c7aaf781ce615d579dd 100644 --- a/manifests/prometheus-rules.yaml +++ b/manifests/prometheus-rules.yaml @@ -762,15 +762,15 @@ spec: record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile - name: kube-prometheus-node-recording.rules rules: - - expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait"}[3m])) BY (instance) + - expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[3m])) BY (instance) record: instance:node_cpu:rate:sum - expr: sum(rate(node_network_receive_bytes_total[3m])) BY (instance) record: instance:node_network_receive_bytes:rate:sum - expr: sum(rate(node_network_transmit_bytes_total[3m])) BY (instance) record: instance:node_network_transmit_bytes:rate:sum - - expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait"}[5m])) WITHOUT (cpu, mode) / ON(instance) GROUP_LEFT() count(sum(node_cpu_seconds_total) BY (instance, cpu)) BY (instance) + - expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m])) WITHOUT (cpu, mode) / ON(instance) GROUP_LEFT() count(sum(node_cpu_seconds_total) BY (instance, cpu)) BY (instance) record: instance:node_cpu:ratio - - expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait"}[5m])) + - expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m])) record: cluster:node_cpu:sum_rate5m - expr: cluster:node_cpu_seconds_total:rate5m / count(sum(node_cpu_seconds_total) BY (instance, cpu)) record: cluster:node_cpu:ratio