From 4c532bb8f3a2b8e40c263b6cc79cb99202874c20 Mon Sep 17 00:00:00 2001 From: Steve Wilkerson Date: Thu, 16 Aug 2018 16:35:44 -0500 Subject: [PATCH] Prometheus: Remove Kubernetes recording rules This removes the recording rules for Kubernetes, as these rules add signficant overhead to the total evaluation time for rules. Any recording rules should be handled as operator overrides and not set by default, in order to prevent undesired overhead time for rules that aren't currently used by the charts Change-Id: I183d32e62619b71b5020cd3733e4707d7c9ad11b --- prometheus/values.yaml | 76 ------------------------------------------ 1 file changed, 76 deletions(-) diff --git a/prometheus/values.yaml b/prometheus/values.yaml index 249255662..0c7566e1e 100644 --- a/prometheus/values.yaml +++ b/prometheus/values.yaml @@ -1220,82 +1220,6 @@ conf: groups: - name: kubernetes.rules rules: - - record: cluster_namespace_controller_pod_container:spec_memory_limit_bytes - expr: sum(label_replace(container_spec_memory_limit_bytes{container_name!=""}, "controller", "$1", "pod_name", "^(.*)-[a-z0-9]+")) BY (cluster, namespace, controller, pod_name, container_name) - - record: cluster_namespace_controller_pod_container:spec_cpu_shares - expr: sum(label_replace(container_spec_cpu_shares{container_name!=""}, "controller", "$1", "pod_name", "^(.*)-[a-z0-9]+")) BY (cluster, namespace, controller, pod_name, container_name) - - record: cluster_namespace_controller_pod_container:cpu_usage:rate - expr: sum(label_replace(irate(container_cpu_usage_seconds_total{container_name!=""}[5m]), "controller", "$1", "pod_name", "^(.*)-[a-z0-9]+")) BY (cluster, namespace, controller, pod_name, container_name) - - record: cluster_namespace_controller_pod_container:memory_usage:bytes - expr: sum(label_replace(container_memory_usage_bytes{container_name!=""}, "controller", "$1", "pod_name", "^(.*)-[a-z0-9]+")) BY (cluster, namespace, controller, pod_name, container_name) - - record: cluster_namespace_controller_pod_container:memory_working_set:bytes - expr: sum(label_replace(container_memory_working_set_bytes{container_name!=""}, "controller", "$1", "pod_name", "^(.*)-[a-z0-9]+")) BY (cluster, namespace, controller, pod_name, container_name) - - record: cluster_namespace_controller_pod_container:memory_rss:bytes - expr: sum(label_replace(container_memory_rss{container_name!=""}, "controller", "$1", "pod_name", "^(.*)-[a-z0-9]+")) BY (cluster, namespace, controller, pod_name, container_name) - - record: cluster_namespace_controller_pod_container:memory_cache:bytes - expr: sum(label_replace(container_memory_cache{container_name!=""}, "controller", "$1", "pod_name", "^(.*)-[a-z0-9]+")) BY (cluster, namespace, controller, pod_name, container_name) - - record: cluster_namespace_controller_pod_container:disk_usage:bytes - expr: sum(label_replace(container_disk_usage_bytes{container_name!=""}, "controller", "$1", "pod_name", "^(.*)-[a-z0-9]+")) BY (cluster, namespace, controller, pod_name, container_name) - - record: cluster_namespace_controller_pod_container:memory_pagefaults:rate - expr: sum(label_replace(irate(container_memory_failures_total{container_name!=""}[5m]), "controller", "$1", "pod_name", "^(.*)-[a-z0-9]+")) BY (cluster, namespace, controller, pod_name, container_name, scope, type) - - record: cluster_namespace_controller_pod_container:memory_oom:rate - expr: sum(label_replace(irate(container_memory_failcnt{container_name!=""}[5m]), "controller", "$1", "pod_name", "^(.*)-[a-z0-9]+")) BY (cluster, namespace, controller, pod_name, container_name, scope, type) - - record: cluster:memory_allocation:percent - expr: 100 * sum(container_spec_memory_limit_bytes{pod_name!=""}) BY (cluster) / sum(machine_memory_bytes) BY (cluster) - - record: cluster:memory_used:percent - expr: 100 * sum(container_memory_usage_bytes{pod_name!=""}) BY (cluster) / sum(machine_memory_bytes) BY (cluster) - - record: cluster:cpu_allocation:percent - expr: 100 * sum(container_spec_cpu_shares{pod_name!=""}) BY (cluster) / sum(container_spec_cpu_shares{id="/"} * ON(cluster, instance) machine_cpu_cores) BY (cluster) - - record: cluster:node_cpu_use:percent - expr: 100 * sum(rate(node_cpu{mode!="idle"}[5m])) BY (cluster) / sum(machine_cpu_cores) BY (cluster) - - record: cluster_resource_verb:apiserver_latency:quantile_seconds - expr: histogram_quantile(0.99, sum(apiserver_request_latencies_bucket) BY (le, cluster, job, resource, verb)) / 1e+06 - labels: - quantile: "0.99" - - record: cluster_resource_verb:apiserver_latency:quantile_seconds - expr: histogram_quantile(0.9, sum(apiserver_request_latencies_bucket) BY (le, cluster, job, resource, verb)) / 1e+06 - labels: - quantile: "0.9" - - record: cluster_resource_verb:apiserver_latency:quantile_seconds - expr: histogram_quantile(0.5, sum(apiserver_request_latencies_bucket) BY (le, cluster, job, resource, verb)) / 1e+06 - labels: - quantile: "0.5" - - record: cluster:scheduler_e2e_scheduling_latency:quantile_seconds - expr: histogram_quantile(0.99, sum(scheduler_e2e_scheduling_latency_microseconds_bucket) BY (le, cluster)) / 1e+06 - labels: - quantile: "0.99" - - record: cluster:scheduler_e2e_scheduling_latency:quantile_seconds - expr: histogram_quantile(0.9, sum(scheduler_e2e_scheduling_latency_microseconds_bucket) BY (le, cluster)) / 1e+06 - labels: - quantile: "0.9" - - record: cluster:scheduler_e2e_scheduling_latency:quantile_seconds - expr: histogram_quantile(0.5, sum(scheduler_e2e_scheduling_latency_microseconds_bucket) BY (le, cluster)) / 1e+06 - labels: - quantile: "0.5" - - record: cluster:scheduler_scheduling_algorithm_latency:quantile_seconds - expr: histogram_quantile(0.99, sum(scheduler_scheduling_algorithm_latency_microseconds_bucket) BY (le, cluster)) / 1e+06 - labels: - quantile: "0.99" - - record: cluster:scheduler_scheduling_algorithm_latency:quantile_seconds - expr: histogram_quantile(0.9, sum(scheduler_scheduling_algorithm_latency_microseconds_bucket) BY (le, cluster)) / 1e+06 - labels: - quantile: "0.9" - - record: cluster:scheduler_scheduling_algorithm_latency:quantile_seconds - expr: histogram_quantile(0.5, sum(scheduler_scheduling_algorithm_latency_microseconds_bucket) BY (le, cluster)) / 1e+06 - labels: - quantile: "0.5" - - record: cluster:scheduler_binding_latency:quantile_seconds - expr: histogram_quantile(0.99, sum(scheduler_binding_latency_microseconds_bucket) BY (le, cluster)) / 1e+06 - labels: - quantile: "0.99" - - record: cluster:scheduler_binding_latency:quantile_seconds - expr: histogram_quantile(0.9, sum(scheduler_binding_latency_microseconds_bucket) BY (le, cluster)) / 1e+06 - labels: - quantile: "0.9" - - record: cluster:scheduler_binding_latency:quantile_seconds - expr: histogram_quantile(0.5, sum(scheduler_binding_latency_microseconds_bucket) BY (le, cluster)) / 1e+06 - labels: - quantile: "0.5" - alert: kube_statefulset_replicas_unavailable expr: kube_statefulset_status_replicas < kube_statefulset_replicas for: 5m