Merge "Cosmetic changes for alerts"
diff --git a/heat/meta/prometheus.yml b/heat/meta/prometheus.yml
index d70d223..48be8c2 100644
--- a/heat/meta/prometheus.yml
+++ b/heat/meta/prometheus.yml
@@ -6,7 +6,7 @@
{% raw %}
server:
alert:
- HeatAPIDown:
+ HeatApiDown:
if: >-
openstack_api_check_status{name=~"heat.*"} == 0
labels:
@@ -16,7 +16,7 @@
summary: "{{ $labels.name }} endpoint is not accessible"
description: >-
Heat API is not accessible for the {{ $labels.name }} endpoint.
- HeatAPIOutage:
+ HeatApiOutage:
if: >-
max(openstack_api_check_status{name=~"heat.*"}) == 0
labels:
@@ -26,7 +26,7 @@
summary: "Heat API outage"
description: >-
Heat API is not accessible for all available Heat endpoints in the OpenStack service catalog.
- HeatAPIServiceDown:
+ HeatApiEndpointDown:
if: >-
http_response_status{name=~"heat.*-api"} == 0
for: 2m
@@ -34,11 +34,11 @@
severity: minor
service: heat
annotations:
- summary: "Host {{ $labels.name }} endpoint is not accessible"
+ summary: "{{ $labels.name }} endpoint is not accessible"
description: >-
- The host {{ $labels.name }} endpoint on the {{ $labels.host }} node is not accessible for at least 2 minutes.
+ The {{ $labels.name }} endpoint on the {{ $labels.host }} node is not accessible for 2 minutes.
{%- endraw %}
- HeatAPIServiceDownMajor:
+ HeatApiEndpointsDownMajor:
if: >-
count(http_response_status{name=~"heat.*-api"} == 0) by (name) >= count(http_response_status{name=~"heat.*-api"}) by (name) * {{ major_threshold }}
for: 2m
@@ -46,10 +46,10 @@
severity: major
service: heat
annotations:
- summary: "{{major_threshold * 100}}% of host {% raw %}{{ $labels.name }} endpoints are not accessible"
+ summary: "{{major_threshold * 100}}% of {% raw %}{{ $labels.name }} endpoints are not accessible"
description: >-
- {{ $value }} host {{ $labels.name }} endpoints are not accessible for at least 2 minutes (at least {% endraw %}{{major_threshold * 100}}{% raw %}%).
- HeatAPIServiceOutage:
+ {{ $value }} {{ $labels.name }} endpoints (>= {% endraw %}{{major_threshold * 100}}{% raw %}%) are not accessible for 2 minutes.
+ HeatApiEndpointsOutage:
if: >-
count(http_response_status{name=~"heat.*-api"} == 0) by (name) == count(http_response_status{name=~"heat.*-api"}) by (name)
for: 2m
@@ -57,9 +57,9 @@
severity: critical
service: heat
annotations:
- summary: "Host {{ $labels.name }} outage"
+ summary: "{{ $labels.name }} endpoints outage"
description: >-
- All available host {{ $labels.name }} endpoints are not accessible for at least 2 minutes.
+ All available {{ $labels.name }} endpoints are not accessible for 2 minutes.
{%- endraw %}
HeatErrorLogsTooHigh:
{%- set log_threshold = monitoring.error_log_rate|float %}