aboutsummaryrefslogtreecommitdiffstats
path: root/kubernetes/namespaces/monitoring
diff options
context:
space:
mode:
authorGravatar Joe Banks <[email protected]>2024-04-01 00:57:01 +0100
committerGravatar Joe Banks <[email protected]>2024-04-01 19:54:53 +0100
commit16cf568178a844e502b1f03ec8f6bd52d119a436 (patch)
treeef3e2c7b760e7e6256d545ece184f43e041c63d0 /kubernetes/namespaces/monitoring
parentAdd some new Django alerts through Prometheus (diff)
Add etcd alerts for increase in failed requests
Diffstat (limited to 'kubernetes/namespaces/monitoring')
-rw-r--r--kubernetes/namespaces/monitoring/alerts/alerts.d/etcd.yaml11
1 files changed, 11 insertions, 0 deletions
diff --git a/kubernetes/namespaces/monitoring/alerts/alerts.d/etcd.yaml b/kubernetes/namespaces/monitoring/alerts/alerts.d/etcd.yaml
new file mode 100644
index 0000000..68ef4a5
--- /dev/null
+++ b/kubernetes/namespaces/monitoring/alerts/alerts.d/etcd.yaml
@@ -0,0 +1,11 @@
+groups:
+ - name: etcd
+ rules:
+ - alert: EtcdErrorsSpike
+ expr: rate(etcd_request_error_total[5m]) > 0
+ for: 5m
+ labels:
+ severity: page
+ annotations:
+ summary: "Etcd request errors are spiking"
+ description: "Etcd request errors are spiking on {{ $labels.instance }} for {{ $labels.operation }}s to {{ $labels.type }}"