Extend procstat_running-based metric alerts.
Related-PROD: PROD-35435
Change-Id: Ib28f4223d6dbdde41d1e3529a022d0be0e79dfa2
diff --git a/docker/meta/prometheus.yml b/docker/meta/prometheus.yml
index 5aeca2f..e63e692 100644
--- a/docker/meta/prometheus.yml
+++ b/docker/meta/prometheus.yml
@@ -6,6 +6,7 @@
if: >-
procstat_running{process_name="dockerd"} == 0
{%- raw %}
+ for: 2m
labels:
severity: minor
service: docker
@@ -27,6 +28,7 @@
if: >-
count(label_replace(procstat_running{process_name="dockerd"}, "cluster", "$1", "host", "([^0-9]+).+")) by (cluster) == count(label_replace(procstat_running{process_name="dockerd"} == 0, "cluster", "$1", "host", "([^0-9]+).+")) by (cluster)
{%- raw %}
+ for: 2m
labels:
severity: critical
service: docker