test: Add tests for KubeCPUOvercommit and KubeMemoryOvercommit

Author: skl

tests.yaml

@@ -1298,3 +1298,107 @@ tests:
         description: 'Cluster has overcommitted memory resource requests for Namespaces.'
         runbook_url: "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememoryquotaovercommit"
         summary: "Cluster has overcommitted memory resource requests."
+
+- name: KubeCPUOvercommit alert (single-node)
+- interval: 1m
+  input_series:
+  - series: 'namespace_cpu:kube_pod_container_resource_requests:sum{cluster="kubernetes", namespace="default"}'
+    values: '1x10'
+  - series: 'namespace_cpu:kube_pod_container_resource_requests:sum{cluster="kubernetes", namespace="kube-system"}'
+    values: '1x10'
+  - series: 'kube_node_status_allocatable{cluster="kubernetes", node="n1", resource="cpu", job="kube-state-metrics"}'
+    values: '1.9x10' # This value was seen on a 2x vCPU node
+  - series: 'kube_node_info{cluster="kubernetes", node="n1", job="kube-state-metrics"}'
+    values: '1x10'
+  alert_rule_test:
+  - eval_time: 9m
+    alertname: KubeCPUOvercommit
+  - eval_time: 10m
+    alertname: KubeCPUOvercommit
+    exp_alerts:
+    - exp_labels:
+        severity: warning
+      exp_annotations:
+        description: Cluster has overcommitted CPU resource requests for Pods by 0.385 CPU shares and cannot tolerate node failure.
+        runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuovercommit
+        summary: Cluster has overcommitted CPU resource requests.
+
+- name: KubeCPUOvercommit alert (multi-node)
+- interval: 1m
+  input_series:
+  - series: 'namespace_cpu:kube_pod_container_resource_requests:sum{cluster="kubernetes", namespace="default"}'
+    values: '2x10'
+  - series: 'namespace_cpu:kube_pod_container_resource_requests:sum{cluster="kubernetes", namespace="kube-system"}'
+    values: '2x10'
+  - series: 'kube_node_status_allocatable{cluster="kubernetes", node="n1", resource="cpu", job="kube-state-metrics"}'
+    values: '1.9x10' # This value was seen on a 2x vCPU node
+  - series: 'kube_node_status_allocatable{cluster="kubernetes", node="n2", resource="cpu", job="kube-state-metrics"}'
+    values: '1.9x10'
+  - series: 'kube_node_info{cluster="kubernetes", node="n1", job="kube-state-metrics"}'
+    values: '1x10'
+  - series: 'kube_node_info{cluster="kubernetes", node="n2", job="kube-state-metrics"}'
+    values: '1x10'
+  alert_rule_test:
+  - eval_time: 9m
+    alertname: KubeCPUOvercommit
+  - eval_time: 10m
+    alertname: KubeCPUOvercommit
+    exp_alerts:
+    - exp_labels:
+        severity: warning
+      exp_annotations:
+        description: Cluster has overcommitted CPU resource requests for Pods by 2.1 CPU shares and cannot tolerate node failure.
+        runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuovercommit
+        summary: Cluster has overcommitted CPU resource requests.
+
+- name: KubeMemoryOvercommit alert (single-node)
+- interval: 1m
+  input_series:
+  - series: 'namespace_memory:kube_pod_container_resource_requests:sum{cluster="kubernetes", namespace="default"}'
+    values: '1000000000x10' # 1 GB
+  - series: 'namespace_memory:kube_pod_container_resource_requests:sum{cluster="kubernetes", namespace="kube-system"}'
+    values: '1000000000x10'
+  - series: 'kube_node_status_allocatable{cluster="kubernetes", node="n1", resource="memory", job="kube-state-metrics"}'
+    values: '1000000000x10'
+  - series: 'kube_node_info{cluster="kubernetes", node="n1", job="kube-state-metrics"}'
+    values: '1x10'
+  alert_rule_test:
+  - eval_time: 9m
+    alertname: KubeMemoryOvercommit
+  - eval_time: 10m
+    alertname: KubeMemoryOvercommit
+    exp_alerts:
+    - exp_labels:
+        severity: warning
+      exp_annotations:
+        description: Cluster has overcommitted memory resource requests for Pods by 1.15G bytes and cannot tolerate node failure.
+        runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememoryovercommit
+        summary: Cluster has overcommitted memory resource requests.
+
+- name: KubeMemoryOvercommit alert (multi-node)
+- interval: 1m
+  input_series:
+  - series: 'namespace_memory:kube_pod_container_resource_requests:sum{cluster="kubernetes", namespace="default"}'
+    values: '2000000000x10' # 2 GB
+  - series: 'namespace_memory:kube_pod_container_resource_requests:sum{cluster="kubernetes", namespace="kube-system"}'
+    values: '2000000000x10'
+  - series: 'kube_node_status_allocatable{cluster="kubernetes", node="n1", resource="memory", job="kube-state-metrics"}'
+    values: '1000000000x10'
+  - series: 'kube_node_status_allocatable{cluster="kubernetes", node="n2", resource="memory", job="kube-state-metrics"}'
+    values: '1000000000x10'
+  - series: 'kube_node_info{cluster="kubernetes", node="n1", job="kube-state-metrics"}'
+    values: '1x10'
+  - series: 'kube_node_info{cluster="kubernetes", node="n2", job="kube-state-metrics"}'
+    values: '1x10'
+  alert_rule_test:
+  - eval_time: 9m
+    alertname: KubeMemoryOvercommit
+  - eval_time: 10m
+    alertname: KubeMemoryOvercommit
+    exp_alerts:
+    - exp_labels:
+        severity: warning
+      exp_annotations:
+        description: Cluster has overcommitted memory resource requests for Pods by 3G bytes and cannot tolerate node failure.
+        runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememoryovercommit
+        summary: Cluster has overcommitted memory resource requests.