bigmac label update

giantswarm · Jun 11, 2024 · aca2acd · aca2acd
1 parent a1161ea
commit aca2acd
Show file tree

Hide file tree

Showing 5 changed files with 10 additions and 14 deletions.
diff --git a/helm/prometheus-rules/templates/kaas/bigmac/alerting-rules/cert-manager.rules.yml b/helm/prometheus-rules/templates/kaas/bigmac/alerting-rules/cert-manager.rules.yml
@@ -29,7 +29,7 @@ spec:
       annotations:
         description: '{{`cert-manager in namespace {{ $labels.namespace }} is down.`}}'
         opsrecipe: cert-manager-down/
-      expr: label_replace(up{app=~"cert-manager-(app|controller)"}, "ip", "$1.$2.$3.$4", "node", "ip-(\\d+)-(\\d+)-(\\d+)-(\\d+).*") == 0
+      expr: label_replace(up{job=~"cert-manager-(app|controller)"}, "ip", "$1.$2.$3.$4", "node", "ip-(\\d+)-(\\d+)-(\\d+)-(\\d+).*") == 0
       for: 15m
       labels:
         area: kaas

diff --git a/helm/prometheus-rules/templates/kaas/bigmac/alerting-rules/dex.rules.yml b/helm/prometheus-rules/templates/kaas/bigmac/alerting-rules/dex.rules.yml
@@ -17,7 +17,7 @@ spec:
       annotations:
         description: '{{`Dex running on {{ $labels.cluster_id }} is reporting an increased error rate.`}}'
         opsrecipe: dex-error-rate-high/
-      expr: sum(increase(http_requests_total{app="dex", handler!="/token", code=~"^[4]..$|[5]..$", cluster_type="management_cluster"}[5m])) by (cluster_id, installation, pipeline, provider) > 10
+      expr: sum(increase(http_requests_total{job="dex", handler!="/token", code=~"^[4]..$|[5]..$", cluster_type="management_cluster"}[5m])) by (cluster_id, installation, pipeline, provider) > 10
       for: 30m
       labels:
         area: kaas

diff --git a/helm/prometheus-rules/templates/kaas/bigmac/alerting-rules/teleport.rules.yml b/helm/prometheus-rules/templates/kaas/bigmac/alerting-rules/teleport.rules.yml
@@ -22,10 +22,10 @@ spec:
               "secret",
               "(.*)-teleport-join-token"
             )
-        ) by (cluster_id, installation, provider, pipeline)
+        ) by (cluster_id, installation, provider)
         != sum (
             capi_cluster_status_phase{phase="Provisioned"}
-        ) by (cluster_id, installation, provider, pipeline)
+        ) by (cluster_id, installation, provider)
       for: 60m
       labels:
         area: kaas
@@ -48,10 +48,10 @@ spec:
               "configmap",
               "(.*)-teleport-kube-agent-config"
             )
-        ) by (cluster_id, installation, provider, pipeline)
+        ) by (cluster_id, installation, provider)
         != sum (
             capi_cluster_status_phase{phase="Provisioned"}
-        ) by (cluster_id, installation, provider, pipeline)
+        ) by (cluster_id, installation, provider)
       for: 60m
       labels:
         area: kaas

diff --git a/test/tests/providers/capi/capz/kaas/bigmac/alerting-rules/cert-manager.rules.test.yml b/test/tests/providers/capi/capz/kaas/bigmac/alerting-rules/cert-manager.rules.test.yml
@@ -5,15 +5,14 @@ rule_files:
 tests:
   - interval: 1m
     input_series:
-      - series: 'up{app="cert-manager-app", cluster_id="12345", cluster_type="workload_cluster", container="cert-manager", customer="giantswarm", installation="golem", instance="10.0.0.0:1234", job="12345-prometheus/workload-12345/0", namespace="kube-system", node="ip-10-0-0-0.eu-central-1.compute.internal", organization="giantswarm", pod="cert-manager-controller-7fcc585578-gnprd", provider="capa", service_priority="highest"}'
+      - series: 'up{cluster_id="12345", cluster_type="workload_cluster", container="cert-manager", customer="giantswarm", installation="golem", instance="10.0.0.0:1234", job="12345-prometheus/workload-12345/0", namespace="kube-system", organization="giantswarm", pod="cert-manager-controller-7fcc585578-gnprd", provider="capa", service_priority="highest"}'
         values: "0+0x60"
     alert_rule_test:
       - alertname: CertManagerDown
         eval_time: 15m
         exp_alerts:
           - exp_labels:
               alertname: CertManagerDown
-              app: cert-manager-app
               area: kaas
               cancel_if_cluster_status_creating: "true"
               cancel_if_cluster_status_deleting: "true"
@@ -27,7 +26,6 @@ tests:
               ip: 10.0.0.0
               job: 12345-prometheus/workload-12345/0
               namespace: kube-system
-              node: ip-10-0-0-0.eu-central-1.compute.internal
               organization: giantswarm
               pod: cert-manager-controller-7fcc585578-gnprd
               provider: capa
@@ -41,7 +39,7 @@ tests:
               opsrecipe: "cert-manager-down/"
   - interval: 1m
     input_series:
-      - series: 'up{app="cert-manager-app", cluster_id="12345", cluster_type="workload_cluster", container="cert-manager", customer="giantswarm", installation="golem", instance="10.0.0.0:1234", job="12345-prometheus/workload-12345/0", namespace="kube-system", node="ip-10-0-0-0.eu-central-1.compute.internal", organization="giantswarm", pod="cert-manager-controller-7fcc585578-gnprd", provider="capa", service_priority="highest"}'
+      - series: 'up{cluster_id="12345", cluster_type="workload_cluster", container="cert-manager", customer="giantswarm", installation="golem", instance="10.0.0.0:1234", job="12345-prometheus/workload-12345/0", namespace="kube-system", organization="giantswarm", pod="cert-manager-controller-7fcc585578-gnprd", provider="capa", service_priority="highest"}'
         values: "1+0x60"
     alert_rule_test:
       - alertname: CertManagerDown

diff --git a/test/tests/providers/vintage/aws/kaas/bigmac/alerting-rules/cert-manager.rules.test.yml b/test/tests/providers/vintage/aws/kaas/bigmac/alerting-rules/cert-manager.rules.test.yml
@@ -5,15 +5,14 @@ rule_files:
 tests:
   - interval: 1m
     input_series:
-      - series: 'up{app="cert-manager-app", cluster_id="12345", cluster_type="workload_cluster", container="cert-manager", customer="giantswarm", installation="gollem", instance="10.0.0.0:1234", job="12345-prometheus/workload-12345/0", namespace="kube-system", node="ip-10-0-0-0.eu-central-1.compute.internal", organization="giantswarm", pod="cert-manager-controller-7fcc585578-gnprd", provider="aws", service_priority="highest"}'
+      - series: 'up{cluster_id="12345", cluster_type="workload_cluster", container="cert-manager", customer="giantswarm", installation="gollem", instance="10.0.0.0:1234", job="12345-prometheus/workload-12345/0", namespace="kube-system", organization="giantswarm", pod="cert-manager-controller-7fcc585578-gnprd", provider="aws", service_priority="highest"}'
         values: "0+0x60"
     alert_rule_test:
       - alertname: CertManagerDown
         eval_time: 15m
         exp_alerts:
           - exp_labels:
               alertname: CertManagerDown
-              app: cert-manager-app
               area: kaas
               cancel_if_cluster_status_creating: "true"
               cancel_if_cluster_status_deleting: "true"
@@ -27,7 +26,6 @@ tests:
               ip: 10.0.0.0
               job: 12345-prometheus/workload-12345/0
               namespace: kube-system
-              node: ip-10-0-0-0.eu-central-1.compute.internal
               organization: giantswarm
               pod: cert-manager-controller-7fcc585578-gnprd
               provider: aws
@@ -41,7 +39,7 @@ tests:
               opsrecipe: "cert-manager-down/"
   - interval: 1m
     input_series:
-      - series: 'up{app="cert-manager-app", cluster_id="12345", cluster_type="workload_cluster", container="cert-manager", customer="giantswarm", installation="gollem", instance="10.0.0.0:1234", job="12345-prometheus/workload-12345/0", namespace="kube-system", node="ip-10-0-0-0.eu-central-1.compute.internal", organization="giantswarm", pod="cert-manager-controller-7fcc585578-gnprd", provider="aws", service_priority="highest"}'
+      - series: 'up{cluster_id="12345", cluster_type="workload_cluster", container="cert-manager", customer="giantswarm", installation="gollem", instance="10.0.0.0:1234", job="12345-prometheus/workload-12345/0", namespace="kube-system", organization="giantswarm", pod="cert-manager-controller-7fcc585578-gnprd", provider="aws", service_priority="highest"}'
         values: "1+0x60"
     alert_rule_test:
       - alertname: CertManagerDown