File tree Expand file tree Collapse file tree 3 files changed +2
-31
lines changed
ansible/roles/kube_prometheus_stack/tasks
environments/common/inventory/group_vars/all Expand file tree Collapse file tree 3 files changed +2
-31
lines changed Original file line number Diff line number Diff line change 113
113
- port : 9301
114
114
name : ood-exporter
115
115
protocol : TCP
116
-
117
- - name : Creating headless service for OOD server
118
- kubernetes.core.k8s :
119
- namespace : " {{ kube_prometheus_stack_release_namespace }}"
120
- definition :
121
- kind : Service
122
- metadata :
123
- name : ondemand
124
- spec :
125
- clusterIP : None
126
- ports :
127
- - name : https
128
- port : 443
129
- protocol : TCP
130
-
131
- - name : Binding OOD server service to host
132
- kubernetes.core.k8s :
133
- namespace : " {{ kube_prometheus_stack_release_namespace }}"
134
- definition :
135
- kind : Endpoints
136
- metadata :
137
- name : ondemand
138
- subsets :
139
- - addresses :
140
- - ip : " {{ openondemand_ip }}"
141
- ports :
142
- - port : 443
143
- name : https
144
- protocol : TCP
145
116
146
117
- name : Creating headless service for slurm exporter
147
118
kubernetes.core.k8s :
Original file line number Diff line number Diff line change @@ -188,7 +188,7 @@ openondemand_scrape_configs:
188
188
module : [http_2xx]
189
189
static_configs :
190
190
- targets :
191
- - ondemand.monitoring-system
191
+ - " {{ openondemand_address }} "
192
192
relabel_configs :
193
193
- source_labels : [__address__]
194
194
target_label : __param_target
Original file line number Diff line number Diff line change @@ -37,7 +37,7 @@ prometheus_extra_rules:
37
37
summary : ' {% raw %}Blackbox probe failed (target {{ $labels.target }}){% endraw %}'
38
38
description : " {% raw %}Blackbox probe '{{ $labels.target }}' failed{% endraw %}"
39
39
- alert : BlackboxSlowProbe
40
- expr : avg_over_time(probe_duration_seconds[1m]) > 1.2 # around 1.14 expected due to indirection in cluster
40
+ expr : avg_over_time(probe_duration_seconds[1m]) > 1.25 # around 1.14 expected due to indirection in cluster
41
41
for : 1m
42
42
labels :
43
43
severity : warning
You can’t perform that action at this time.
0 commit comments