Vladimir Kozhukalov 8b29037cec Move values overrides to a separate directory
This is the action item to implement the spec:
doc/source/specs/2025.1/chart_versioning.rst

Also add overrides env variables

- OSH_VALUES_OVERRIDES_PATH
- OSH_INFRA_VALUES_OVERRIDES_PATH

This commit temporarily disables all jobs that involve scripts
in the OSH git repo because they need to be updated to work
with the new values_overrides structure in the OSH-infra repo.
Once this is merged I4974785c904cf7c8730279854e3ad9b6b7c35498
all these disabled test jobs must be enabled.

Depends-On: I327103c18fc0e10e989a17f69b3bff9995c45eb4
Change-Id: I7bfdef3ea2128bbb4e26e3a00161fe30ce29b8e7
2024-12-13 12:04:44 -06:00

34 lines
1.6 KiB
YAML

---
conf:
prometheus:
rules:
alertmanager:
groups:
- name: alertmanager.rules
rules:
- alert: AlertmanagerConfigInconsistent
expr: count_values("config_hash", alertmanager_config_hash) BY (service) / ON(service) GROUP_LEFT() label_replace(prometheus_operator_alertmanager_spec_replicas, "service", "alertmanager-$1", "alertmanager", "(.*)") != 1
for: 5m
labels:
severity: critical
annotations:
description: The configuration of the instances of the Alertmanager cluster `{{$labels.service}}` are out of sync.
summary: Alertmanager configurations are inconsistent
- alert: AlertmanagerDownOrMissing
expr: label_replace(prometheus_operator_alertmanager_spec_replicas, "job", "alertmanager-$1", "alertmanager", "(.*)") / ON(job) GROUP_RIGHT() sum(up) BY (job) != 1
for: 5m
labels:
severity: warning
annotations:
description: An unexpected number of Alertmanagers are scraped or Alertmanagers disappeared from discovery.
summary: Alertmanager down or not discovered
- alert: FailedReload
expr: alertmanager_config_last_reload_successful == 0
for: 10m
labels:
severity: warning
annotations:
description: Reloading Alertmanager's configuration has failed for {{ $labels.namespace }}/{{ $labels.pod }}.
summary: Alertmanager configuration reload has failed
...