Skip to content

Commit 4ae726c

Browse files
rexagodrexagod
committed
follow-up: add test cases for non-HA (two-node)
Signed-off-by: Pranshu Srivastava <[email protected]>
1 parent 56cb80f commit 4ae726c

File tree

1 file changed

+69
-5
lines changed

1 file changed

+69
-5
lines changed

‎tests/tests.yaml‎

Lines changed: 69 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -1448,7 +1448,7 @@ tests:
14481448
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuovercommit
14491449
summary: Cluster has overcommitted CPU resource requests.
14501450

1451-
- name: KubeCPUOvercommit alert (multi-node)
1451+
- name: KubeCPUOvercommit alert (multi-node; non-HA)
14521452
interval: 1m
14531453
input_series:
14541454
- series: 'namespace_cpu:kube_pod_container_resource_requests:sum{cluster="kubernetes", namespace="default"}'
@@ -1459,9 +1459,9 @@ tests:
14591459
values: '1.9x10' # This value was seen on a 2x vCPU node
14601460
- series: 'kube_node_status_allocatable{cluster="kubernetes", node="n2", resource="cpu", job="kube-state-metrics"}'
14611461
values: '1.9x10'
1462-
- series: 'kube_node_role{ cluster="kubernetes", node="n1", role="control-plane"}'
1462+
- series: 'kube_node_role{cluster="kubernetes", node="n1", role="control-plane", job="kube-state-metrics"}'
14631463
values: '1x10'
1464-
- series: 'kube_node_role{ cluster="kubernetes", node="n2", role="control-plane"}'
1464+
- series: 'kube_node_role{cluster="kubernetes", node="n2", role="control-plane", job="kube-state-metrics"}'
14651465
values: '1x10'
14661466
alert_rule_test:
14671467
- eval_time: 9m
@@ -1472,10 +1472,42 @@ tests:
14721472
- exp_labels:
14731473
severity: warning
14741474
exp_annotations:
1475-
description: Cluster has overcommitted CPU resource requests for Pods by 2.1 CPU shares and cannot tolerate node failure.
1475+
description: Cluster has overcommitted CPU resource requests for Pods by 0.20000000000000018 CPU shares and cannot tolerate node failure.
14761476
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuovercommit
14771477
summary: Cluster has overcommitted CPU resource requests.
14781478

1479+
- name: KubeCPUOvercommit alert (multi-node; HA)
1480+
interval: 1m
1481+
input_series:
1482+
- series: 'namespace_cpu:kube_pod_container_resource_requests:sum{cluster="kubernetes", namespace="default"}'
1483+
values: '2x10'
1484+
- series: 'namespace_cpu:kube_pod_container_resource_requests:sum{cluster="kubernetes", namespace="kube-system"}'
1485+
values: '2x10'
1486+
- series: 'kube_node_status_allocatable{cluster="kubernetes", node="n1", resource="cpu", job="kube-state-metrics"}'
1487+
values: '1.9x10' # This value was seen on a 2x vCPU node
1488+
- series: 'kube_node_status_allocatable{cluster="kubernetes", node="n2", resource="cpu", job="kube-state-metrics"}'
1489+
values: '1.9x10'
1490+
- series: 'kube_node_status_allocatable{cluster="kubernetes", node="n3", resource="cpu", job="kube-state-metrics"}'
1491+
values: '1.9x10'
1492+
- series: 'kube_node_role{cluster="kubernetes", node="n1", role="control-plane", job="kube-state-metrics"}'
1493+
values: '1x10'
1494+
- series: 'kube_node_role{cluster="kubernetes", node="n2", role="control-plane", job="kube-state-metrics"}'
1495+
values: '1x10'
1496+
- series: 'kube_node_role{cluster="kubernetes", node="n3", role="control-plane", job="kube-state-metrics"}'
1497+
values: '1x10'
1498+
alert_rule_test:
1499+
- eval_time: 9m
1500+
alertname: KubeCPUOvercommit
1501+
- eval_time: 10m
1502+
alertname: KubeCPUOvercommit
1503+
exp_alerts:
1504+
- exp_labels:
1505+
severity: warning
1506+
exp_annotations:
1507+
description: Cluster has overcommitted CPU resource requests for Pods by 0.20000000000000062 CPU shares and cannot tolerate node failure.
1508+
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuovercommit
1509+
summary: Cluster has overcommitted CPU resource requests.
1510+
14791511
- name: KubeMemoryOvercommit alert (single-node)
14801512
interval: 1m
14811513
input_series:
@@ -1500,7 +1532,7 @@ tests:
15001532
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememoryovercommit
15011533
summary: Cluster has overcommitted memory resource requests.
15021534

1503-
- name: KubeMemoryOvercommit alert (multi-node)
1535+
- name: KubeMemoryOvercommit alert (multi-node; non-HA)
15041536
interval: 1m
15051537
input_series:
15061538
- series: 'namespace_memory:kube_pod_container_resource_requests:sum{cluster="kubernetes", namespace="default"}'
@@ -1527,3 +1559,35 @@ tests:
15271559
description: Cluster has overcommitted memory resource requests for Pods by 2G bytes and cannot tolerate node failure.
15281560
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememoryovercommit
15291561
summary: Cluster has overcommitted memory resource requests.
1562+
1563+
- name: KubeMemoryOvercommit alert (multi-node; HA)
1564+
interval: 1m
1565+
input_series:
1566+
- series: 'namespace_memory:kube_pod_container_resource_requests:sum{cluster="kubernetes", namespace="default"}'
1567+
values: '2000000000x10' # 2 GB
1568+
- series: 'namespace_memory:kube_pod_container_resource_requests:sum{cluster="kubernetes", namespace="kube-system"}'
1569+
values: '2000000000x10'
1570+
- series: 'kube_node_status_allocatable{cluster="kubernetes", node="n1", resource="memory", job="kube-state-metrics"}'
1571+
values: '1000000000x10'
1572+
- series: 'kube_node_status_allocatable{cluster="kubernetes", node="n2", resource="memory", job="kube-state-metrics"}'
1573+
values: '1000000000x10'
1574+
- series: 'kube_node_status_allocatable{cluster="kubernetes", node="n3", resource="memory", job="kube-state-metrics"}'
1575+
values: '1000000000x10'
1576+
- series: 'kube_node_role{cluster="kubernetes", node="n1", role="control-plane", job="kube-state-metrics"}'
1577+
values: '1x10'
1578+
- series: 'kube_node_role{cluster="kubernetes", node="n2", role="control-plane", job="kube-state-metrics"}'
1579+
values: '1x10'
1580+
- series: 'kube_node_role{cluster="kubernetes", node="n3", role="control-plane", job="kube-state-metrics"}'
1581+
values: '1x10'
1582+
alert_rule_test:
1583+
- eval_time: 9m
1584+
alertname: KubeMemoryOvercommit
1585+
- eval_time: 10m
1586+
alertname: KubeMemoryOvercommit
1587+
exp_alerts:
1588+
- exp_labels:
1589+
severity: warning
1590+
exp_annotations:
1591+
description: Cluster has overcommitted memory resource requests for Pods by 2G bytes and cannot tolerate node failure.
1592+
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememoryovercommit
1593+
summary: Cluster has overcommitted memory resource requests.

0 commit comments

Comments
 (0)