aboutsummaryrefslogtreecommitdiffstats
path: root/kubernetes/namespaces/monitoring
diff options
context:
space:
mode:
authorGravatar Joe Banks <[email protected]>2024-04-01 00:56:31 +0100
committerGravatar Joe Banks <[email protected]>2024-04-01 19:54:53 +0100
commit603e86b6d591f1e5ffe1244ff51ccac7b54ddaff (patch)
tree9b6d611b97dc89d4a96f0e04f5d7c6149a7132cc /kubernetes/namespaces/monitoring
parentAdd PagerDuty to AlertManager channels (diff)
Add some new Django alerts through Prometheus
Diffstat (limited to 'kubernetes/namespaces/monitoring')
-rw-r--r--kubernetes/namespaces/monitoring/alerts/alerts.d/django.yaml20
1 files changed, 20 insertions, 0 deletions
diff --git a/kubernetes/namespaces/monitoring/alerts/alerts.d/django.yaml b/kubernetes/namespaces/monitoring/alerts/alerts.d/django.yaml
new file mode 100644
index 0000000..1444a87
--- /dev/null
+++ b/kubernetes/namespaces/monitoring/alerts/alerts.d/django.yaml
@@ -0,0 +1,20 @@
+groups:
+ - name: django
+ rules:
+ - alert: DjangoErrors
+ expr: increase(django_http_responses_total_by_status_total{status=~"5.."}[5m]) > 0
+ for: 5m
+ labels:
+ severity: page
+ annotations:
+ summary: "Django is experiencing 5xx errors"
+ description: "Django is experiencing 5xx errors on {{ $labels.namespace }}/{{ $labels.job }}"
+
+ - alert: DjangoLatencyHigh
+ expr: histogram_quantile(0.95, rate(django_http_requests_latency_seconds_by_view_method_bucket[5m])) > 1.0
+ for: 3m
+ labels:
+ severity: page
+ annotations:
+ summary: "Django route is experiencing high latency"
+ description: "Django route {{ $labels.method }} {{ $labels.view }} is experiencing high latency"