easylinux/kube-prometheus
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Cut release-0.7

Browse Source 
Signed-off-by: Damien Grisonnet <dgrisonn@redhat.com>
This commit is contained in:
Damien Grisonnet
2020-12-09 11:37:59 +01:00
parent 0cfe5bba45
commit 6a05efd636
13 changed files with 63 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
manifests/grafana-dashboardDefinitions.yaml
View File

@@ -16657,7 +16657,7 @@ items:
"tableColumn": "",
"targets": [
{
"expr": "sum(kubelet_running_pods{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"})",
"expr": "sum(kubelet_running_pods{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}) OR sum(kubelet_running_pod_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@@ -16741,7 +16741,7 @@ items:
"tableColumn": "",
"targets": [
{
"expr": "sum(kubelet_running_containers{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"})",
"expr": "sum(kubelet_running_containers{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}) OR sum(kubelet_running_container_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@@ -26924,7 +26924,7 @@ items:
"steppedLine": false,
"targets": [
{
"expr": "(\n prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"} \n- \n ignoring(remote_name, url) group_right(instance) prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}\n)\n",
"expr": "(\n prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"} \n- \n ignoring(remote_name, url) group_right(instance) (prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"} != 0)\n)\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
@@ -27017,7 +27017,7 @@ items:
"steppedLine": false,
"targets": [
{
"expr": "(\n rate(prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) \n- \n ignoring (remote_name, url) group_right(instance) rate(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n)\n",
"expr": "clamp_min(\n rate(prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) \n- \n ignoring (remote_name, url) group_right(instance) rate(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n, 0)\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",

2
manifests/grafana-deployment.yaml
View File

@@ -13,7 +13,7 @@ spec:
template:
metadata:
annotations:
checksum/grafana-dashboards: b44634653e3bb90dacd5c15f42200fae
checksum/grafana-dashboards: ce13f0b50d04c73fb01da858eb1fb608
checksum/grafana-datasources: 48faab41f579fc8efde6034391496f6a
labels:
app: grafana

4
manifests/prometheus-operator-serviceMonitor.yaml
View File

@@ -4,7 +4,7 @@ metadata:
labels:
app.kubernetes.io/component: controller
app.kubernetes.io/name: prometheus-operator
app.kubernetes.io/version: v0.44.0
app.kubernetes.io/version: v0.44.1
name: prometheus-operator
namespace: monitoring
spec:
@@ -19,4 +19,4 @@ spec:
matchLabels:
app.kubernetes.io/component: controller
app.kubernetes.io/name: prometheus-operator
app.kubernetes.io/version: v0.44.0
app.kubernetes.io/version: v0.44.1

42
manifests/prometheus-rules.yaml
View File

@@ -1902,21 +1902,6 @@ spec:
for: 15m
labels:
severity: warning
- alert: PrometheusErrorSendingAlertsToAnyAlertmanager
annotations:
description: '{{ printf "%.1f" $value }}% minimum errors while sending alerts from Prometheus {{$labels.namespace}}/{{$labels.pod}} to any Alertmanager.'
summary: Prometheus encounters more than 3% errors sending alerts to any Alertmanager.
expr: |
min without(alertmanager) (
rate(prometheus_notifications_errors_total{job="prometheus-k8s",namespace="monitoring"}[5m])
/
rate(prometheus_notifications_sent_total{job="prometheus-k8s",namespace="monitoring"}[5m])
)
* 100
> 3
for: 15m
labels:
severity: critical
- alert: PrometheusNotConnectedToAlertmanagers
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not connected to any Alertmanagers.
@@ -1951,7 +1936,15 @@ spec:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not ingesting samples.
summary: Prometheus is not ingesting samples.
expr: |
rate(prometheus_tsdb_head_samples_appended_total{job="prometheus-k8s",namespace="monitoring"}[5m]) <= 0
(
rate(prometheus_tsdb_head_samples_appended_total{job="prometheus-k8s",namespace="monitoring"}[5m]) <= 0
and
(
sum without(scrape_job) (prometheus_target_metadata_cache_entries{job="prometheus-k8s",namespace="monitoring"}) > 0
or
sum without(rule_group) (prometheus_rule_group_rules{job="prometheus-k8s",namespace="monitoring"}) > 0
)
)
for: 10m
labels:
severity: warning
@@ -2001,7 +1994,7 @@ spec:
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
(
max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job="prometheus-k8s",namespace="monitoring"}[5m])
- on(job, instance) group_right
- ignoring(remote_name, url) group_right
max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job="prometheus-k8s",namespace="monitoring"}[5m])
)
> 120
@@ -2050,6 +2043,21 @@ spec:
for: 15m
labels:
severity: warning
- alert: PrometheusErrorSendingAlertsToAnyAlertmanager
annotations:
description: '{{ printf "%.1f" $value }}% minimum errors while sending alerts from Prometheus {{$labels.namespace}}/{{$labels.pod}} to any Alertmanager.'
summary: Prometheus encounters more than 3% errors sending alerts to any Alertmanager.
expr: |
min without (alertmanager) (
rate(prometheus_notifications_errors_total{job="prometheus-k8s",namespace="monitoring"}[5m])
/
rate(prometheus_notifications_sent_total{job="prometheus-k8s",namespace="monitoring"}[5m])
)
* 100
> 3
for: 15m
labels:
severity: critical
- name: general.rules
rules:
- alert: TargetDown

2
manifests/setup/prometheus-operator-clusterRole.yaml
View File

@@ -4,7 +4,7 @@ metadata:
labels:
app.kubernetes.io/component: controller
app.kubernetes.io/name: prometheus-operator
app.kubernetes.io/version: v0.44.0
app.kubernetes.io/version: v0.44.1
name: prometheus-operator
rules:
- apiGroups:

2
manifests/setup/prometheus-operator-clusterRoleBinding.yaml
View File

@@ -4,7 +4,7 @@ metadata:
labels:
app.kubernetes.io/component: controller
app.kubernetes.io/name: prometheus-operator
app.kubernetes.io/version: v0.44.0
app.kubernetes.io/version: v0.44.1
name: prometheus-operator
roleRef:
apiGroup: rbac.authorization.k8s.io

8
manifests/setup/prometheus-operator-deployment.yaml
View File

@@ -4,7 +4,7 @@ metadata:
labels:
app.kubernetes.io/component: controller
app.kubernetes.io/name: prometheus-operator
app.kubernetes.io/version: v0.44.0
app.kubernetes.io/version: v0.44.1
name: prometheus-operator
namespace: monitoring
spec:
@@ -18,13 +18,13 @@ spec:
labels:
app.kubernetes.io/component: controller
app.kubernetes.io/name: prometheus-operator
app.kubernetes.io/version: v0.44.0
app.kubernetes.io/version: v0.44.1
spec:
containers:
- args:
- --kubelet-service=kube-system/kubelet
- --prometheus-config-reloader=quay.io/prometheus-operator/prometheus-config-reloader:v0.44.0
image: quay.io/prometheus-operator/prometheus-operator:v0.44.0
- --prometheus-config-reloader=quay.io/prometheus-operator/prometheus-config-reloader:v0.44.1
image: quay.io/prometheus-operator/prometheus-operator:v0.44.1
name: prometheus-operator
ports:
- containerPort: 8080

2
manifests/setup/prometheus-operator-service.yaml
View File

@@ -4,7 +4,7 @@ metadata:
labels:
app.kubernetes.io/component: controller
app.kubernetes.io/name: prometheus-operator
app.kubernetes.io/version: v0.44.0
app.kubernetes.io/version: v0.44.1
name: prometheus-operator
namespace: monitoring
spec:

2
manifests/setup/prometheus-operator-serviceAccount.yaml
View File

@@ -4,6 +4,6 @@ metadata:
labels:
app.kubernetes.io/component: controller
app.kubernetes.io/name: prometheus-operator
app.kubernetes.io/version: v0.44.0
app.kubernetes.io/version: v0.44.1
name: prometheus-operator
namespace: monitoring