Skip to content

Commit

Permalink
Merge pull request #201 from appuio/feat/make-4.14-default
Browse files Browse the repository at this point in the history 
Make OpenShift 4.14 the default
  • Loading branch information
@simu
simu authored Apr 15, 2024
2 parents 3303b38 + 54fc07c commit fc3409b
Show file tree
Hide file tree
Showing 8 changed files with 379 additions and 634 deletions.
2 changes: 1 addition & 1 deletion class/defaults.yml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ parameters:
alert-patching.libsonnet: openshift4-monitoring-alert-patching.libsonnet
namespace: openshift-monitoring
# TODO: select based on reported OCP version once we have dynamic facts
manifests_version: release-4.13
manifests_version: release-4.14
=_cluster_monitoring_operator_version_map:
release-4.13: release-4.13
release-4.14: release-4.14
Expand Down
93 changes: 50 additions & 43 deletions ...alerts-with-node-labels/openshift4-monitoring/openshift4-monitoring/prometheus_rules.yaml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -249,7 +249,7 @@ spec:
- alert: SYN_ClusterOperatorDown
annotations:
description: The {{ $labels.name }} operator may be down or disabled because
${{ $labels.reason }}, and the components it manages may be unavailable
{{ $labels.reason }}, and the components it manages may be unavailable
or degraded. Cluster upgrades may not complete. For more information
refer to 'oc get -o yaml clusteroperator {{ $labels.name }}'{{ with
$console_url := "console_url" | query }}{{ if ne (len (label "url" (first
Expand Down Expand Up @@ -285,7 +285,7 @@ spec:
- alert: SYN_ClusterReleaseNotAccepted
annotations:
description: The desired cluster release has not been accepted because
${{ $labels.reason }}, and the cluster will continue to reconcile an
{{ $labels.reason }}, and the cluster will continue to reconcile an
earlier release instead of moving towards that desired release. For
more information refer to 'oc adm upgrade'{{ with $console_url := "console_url"
| query }}{{ if ne (len (label "url" (first $console_url ) ) ) 0}} or
Expand Down Expand Up @@ -339,6 +339,7 @@ spec:
- alert: SYN_KubeSchedulerDown
annotations:
description: KubeScheduler has disappeared from Prometheus target discovery.
runbook_url: https://github.com/openshift/runbooks/blob/master/alerts/cluster-kube-scheduler-operator/KubeSchedulerDown.md
summary: Target disappeared from Prometheus target discovery.
syn_component: openshift4-monitoring
expr: |
Expand Down Expand Up @@ -610,6 +611,7 @@ spec:
> 0.01
for: 15m
labels:
namespace: openshift-monitoring
severity: warning
syn: 'true'
syn_component: openshift4-monitoring
Expand Down Expand Up @@ -1076,6 +1078,7 @@ spec:
sum(changes(kube_node_status_condition{job="kube-state-metrics",status="true",condition="Ready"}[15m])) by (cluster, node) > 2
for: 15m
labels:
namespace: kube-system
severity: warning
syn: 'true'
syn_component: openshift4-monitoring
Expand Down Expand Up @@ -1129,6 +1132,7 @@ spec:
node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile{quantile="0.99"} >= 10
for: 5m
labels:
namespace: kube-system
severity: warning
syn: 'true'
syn_component: openshift4-monitoring
Expand All @@ -1142,6 +1146,7 @@ spec:
histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (cluster, instance, le)) * on(cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"} > 60
for: 15m
labels:
namespace: kube-system
severity: warning
syn: 'true'
syn_component: openshift4-monitoring
Expand Down Expand Up @@ -1170,7 +1175,7 @@ spec:
mapi_mao_collector_up == 0
for: 5m
labels:
severity: critical
severity: warning
syn: 'true'
syn_component: openshift4-monitoring
- name: syn-machine-health-check-unterminated-short-circuit
Expand Down Expand Up @@ -1245,10 +1250,12 @@ spec:
rules:
- alert: SYN_MCCDrainError
annotations:
message: 'Drain failed on {{ $labels.exported_node }} , updates may be
blocked. For more details check MachineConfigController pod logs: oc
logs -f -n {{ $labels.namespace }} machine-config-controller-xxxxx -c
machine-config-controller'
description: 'Drain failed on {{ $labels.exported_node }} , updates may
be blocked. For more details check MachineConfigController pod logs:
oc logs -f -n {{ $labels.namespace }} machine-config-controller-xxxxx
-c machine-config-controller'
summary: Alerts the user to a failed node drain. Always triggers when
the failure happens one or more times.
syn_component: openshift4-monitoring
expr: |
mcc_drain_err > 0
Expand All @@ -1257,11 +1264,32 @@ spec:
severity: warning
syn: 'true'
syn_component: openshift4-monitoring
- name: syn-mcc-pool-alert
rules:
- alert: SYN_MCCPoolAlert
annotations:
description: 'Node {{ $labels.exported_node }} has triggered a pool alert
due to a label change. For more details check MachineConfigController
pod logs: oc logs -f -n {{ $labels.namespace }} machine-config-controller-xxxxx
-c machine-config-controller'
summary: Triggers when nodes in a pool have overlapping labels such as
master, worker, and a custom label therefore a choice must be made as
to which is honored.
syn_component: openshift4-monitoring
expr: |
mcc_pool_alert > 0
labels:
namespace: openshift-machine-config-operator
severity: warning
syn: 'true'
syn_component: openshift4-monitoring
- name: syn-mcd-kubelet-health-state-error
rules:
- alert: SYN_KubeletHealthState
annotations:
message: Kubelet health failure threshold reached
description: Kubelet health failure threshold reached
summary: This keeps track of Kubelet health failures, and tallys them.
The warning is triggered if 2 or more failures occur.
syn_component: openshift4-monitoring
expr: |
mcd_kubelet_state > 2
Expand All @@ -1274,9 +1302,11 @@ spec:
rules:
- alert: SYN_MCDPivotError
annotations:
message: 'Error detected in pivot logs on {{ $labels.node }} , upgrade
description: 'Error detected in pivot logs on {{ $labels.node }} , upgrade
may be blocked. For more details: oc logs -f -n {{ $labels.namespace
}} {{ $labels.pod }} -c machine-config-daemon '
summary: Alerts the user when an error is detected upon pivot. This triggers
if the pivot errors are above zero for 2 minutes.
syn_component: openshift4-monitoring
expr: |
mcd_pivot_errors_total > 0
Expand All @@ -1290,9 +1320,11 @@ spec:
rules:
- alert: SYN_MCDRebootError
annotations:
message: 'Reboot failed on {{ $labels.node }} , update may be blocked.
description: 'Reboot failed on {{ $labels.node }} , update may be blocked.
For more details: oc logs -f -n {{ $labels.namespace }} {{ $labels.pod
}} -c machine-config-daemon '
summary: Alerts the user that a node failed to reboot one or more times
over a span of 5 minutes.
syn_component: openshift4-monitoring
expr: |
mcd_reboots_failed_total > 0
Expand Down Expand Up @@ -1356,20 +1388,6 @@ spec:
severity: warning
syn: 'true'
syn_component: openshift4-monitoring
- alert: SYN_NodeDiskIOSaturation
annotations:
description: |
Disk IO queue (aqu-sq) is high on {{ $labels.device }} at {{ $labels.instance }}, has been above 10 for the last 30 minutes, is currently at {{ printf "%.2f" $value }}.
This symptom might indicate disk saturation.
summary: Disk IO queue is high.
syn_component: openshift4-monitoring
expr: |
rate(node_disk_io_time_weighted_seconds_total{job="node-exporter", device=~"mmcblk.p.+|nvme.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+"}[5m]) > 10
for: 30m
labels:
severity: warning
syn: 'true'
syn_component: openshift4-monitoring
- alert: SYN_NodeFileDescriptorLimit
annotations:
description: File descriptors limit at {{ $labels.instance }} is currently
Expand Down Expand Up @@ -1502,19 +1520,6 @@ spec:
severity: warning
syn: 'true'
syn_component: openshift4-monitoring
- alert: SYN_NodeMemoryHighUtilization
annotations:
description: |
Memory is filling up at {{ $labels.instance }}, has been above 90% for the last 15 minutes, is currently at {{ printf "%.2f" $value }}%.
summary: Host is running out of memory.
syn_component: openshift4-monitoring
expr: |
100 - (node_memory_MemAvailable_bytes{job="node-exporter"} / node_memory_MemTotal_bytes{job="node-exporter"} * 100) > 90
for: 15m
labels:
severity: warning
syn: 'true'
syn_component: openshift4-monitoring
- alert: SYN_NodeMemoryMajorPagesFaults
annotations:
description: |
Expand Down Expand Up @@ -1565,7 +1570,7 @@ spec:
syn_component: openshift4-monitoring
expr: |
node_systemd_unit_state{job="node-exporter", state="failed"} == 1
for: 5m
for: 15m
labels:
severity: warning
syn: 'true'
Expand Down Expand Up @@ -2166,7 +2171,7 @@ spec:
summary: Prometheus operator not ready
syn_component: openshift4-monitoring
expr: |
min by (controller,namespace) (max_over_time(prometheus_operator_ready{job="prometheus-operator", namespace=~"openshift-monitoring|openshift-user-workload-monitoring"}[5m]) == 0)
min by (cluster,controller,namespace) (max_over_time(prometheus_operator_ready{job="prometheus-operator", namespace=~"openshift-monitoring|openshift-user-workload-monitoring"}[5m]) == 0)
for: 5m
labels:
severity: warning
Expand All @@ -2180,7 +2185,7 @@ spec:
summary: Errors while reconciling objects.
syn_component: openshift4-monitoring
expr: |
(sum by (controller,namespace) (rate(prometheus_operator_reconcile_errors_total{job="prometheus-operator", namespace=~"openshift-monitoring|openshift-user-workload-monitoring"}[5m]))) / (sum by (controller,namespace) (rate(prometheus_operator_reconcile_operations_total{job="prometheus-operator", namespace=~"openshift-monitoring|openshift-user-workload-monitoring"}[5m]))) > 0.1
(sum by (cluster,controller,namespace) (rate(prometheus_operator_reconcile_errors_total{job="prometheus-operator", namespace=~"openshift-monitoring|openshift-user-workload-monitoring"}[5m]))) / (sum by (cluster,controller,namespace) (rate(prometheus_operator_reconcile_operations_total{job="prometheus-operator", namespace=~"openshift-monitoring|openshift-user-workload-monitoring"}[5m]))) > 0.1
for: 10m
labels:
severity: warning
Expand Down Expand Up @@ -2208,7 +2213,7 @@ spec:
summary: Errors while updating objects status.
syn_component: openshift4-monitoring
expr: |
(sum by (controller,namespace) (rate(prometheus_operator_status_update_errors_total{job="prometheus-operator", namespace=~"openshift-monitoring|openshift-user-workload-monitoring"}[5m]))) / (sum by (controller,namespace) (rate(prometheus_operator_status_update_operations_total{job="prometheus-operator", namespace=~"openshift-monitoring|openshift-user-workload-monitoring"}[5m]))) > 0.1
(sum by (cluster,controller,namespace) (rate(prometheus_operator_status_update_errors_total{job="prometheus-operator", namespace=~"openshift-monitoring|openshift-user-workload-monitoring"}[5m]))) / (sum by (cluster,controller,namespace) (rate(prometheus_operator_status_update_operations_total{job="prometheus-operator", namespace=~"openshift-monitoring|openshift-user-workload-monitoring"}[5m]))) > 0.1
for: 10m
labels:
severity: warning
Expand All @@ -2234,7 +2239,7 @@ spec:
summary: Errors while performing watch operations in controller.
syn_component: openshift4-monitoring
expr: |
(sum by (controller,namespace) (rate(prometheus_operator_watch_operations_failed_total{job="prometheus-operator", namespace=~"openshift-monitoring|openshift-user-workload-monitoring"}[5m])) / sum by (controller,namespace) (rate(prometheus_operator_watch_operations_total{job="prometheus-operator", namespace=~"openshift-monitoring|openshift-user-workload-monitoring"}[5m]))) > 0.4
(sum by (cluster,controller,namespace) (rate(prometheus_operator_watch_operations_failed_total{job="prometheus-operator", namespace=~"openshift-monitoring|openshift-user-workload-monitoring"}[5m])) / sum by (cluster,controller,namespace) (rate(prometheus_operator_watch_operations_total{job="prometheus-operator", namespace=~"openshift-monitoring|openshift-user-workload-monitoring"}[5m]))) > 0.4
for: 15m
labels:
severity: warning
Expand All @@ -2244,14 +2249,16 @@ spec:
rules:
- alert: SYN_SystemMemoryExceedsReservation
annotations:
message: System memory usage of {{ $value | humanize }} on {{ $labels.node
description: System memory usage of {{ $value | humanize }} on {{ $labels.node
}} exceeds 95% of the reservation. Reserved memory ensures system processes
can function even when the node is fully allocated and protects against
workload out of memory events impacting the proper functioning of the
node. The default reservation is expected to be sufficient for most
configurations and should be increased (https://docs.openshift.com/container-platform/latest/nodes/nodes/nodes-nodes-managing.html)
when running nodes with high numbers of pods (either due to rate of
change or at steady state).
summary: Alerts the user when, for 15 miutes, a specific node is using
more memory than is reserved
syn_component: openshift4-monitoring
expr: |
sum by (node) (container_memory_rss{id="/system.slice"}) > ((sum by (node) (kube_node_status_capacity{resource="memory"} - kube_node_status_allocatable{resource="memory"})) * 0.95)
Expand Down
Loading

0 comments on commit fc3409b

Please sign in to comment.