Cosmetic changes for alerts
Change-Id: I9e6b2f4a5876e7d5697236166b4a6dc30cf4615a
Closes-bug: PROD-20466
diff --git a/prometheus/meta/prometheus.yml b/prometheus/meta/prometheus.yml
index 5c78c64..fa9cf20 100644
--- a/prometheus/meta/prometheus.yml
+++ b/prometheus/meta/prometheus.yml
@@ -12,7 +12,7 @@
service: prometheus
annotations:
summary: "Prometheus target is down"
- description: "The Prometheus target for the {{ $labels.job }} job on the {{ $labels.host or $labels.instance }} node is down for at least 2 minutes."
+ description: "The Prometheus target for the {{ $labels.job }} job on the {{ $labels.host or $labels.instance }} node is down for 2 minutes."
PrometheusTargetSamplesOrderWarning:
if: increase(prometheus_target_scrapes_sample_out_of_order_total[1m]) > 0
labels:
@@ -20,7 +20,7 @@
service: prometheus
annotations:
summary: "Prometheus samples are out of order"
- description: "{{ $value }} last-minute samples of Prometheus on the {{ $labels.instance }} instance are out of order."
+ description: "{{ $value }} Prometheus samples on the {{ $labels.instance }} instance are out of order (as measured over the last minute)."
PrometheusTargetSamplesBoundsWarning:
if: increase(prometheus_target_scrapes_sample_out_of_bounds_total[1m]) > 0
labels:
@@ -28,7 +28,7 @@
service: prometheus
annotations:
summary: "Prometheus samples timestamps are out of bounds"
- description: "{{ $value }} last-minute samples of Prometheus on the {{ $labels.instance }} instance have timestamps out of bounds."
+ description: "{{ $value }} Prometheus samples on the {{ $labels.instance }} instance have timestamps out of bounds (as measured over the last minute)."
PrometheusTargetSamplesDuplicateWarning:
if: increase(prometheus_target_scrapes_sample_duplicate_timestamp_total[1m]) > 0
labels:
@@ -36,7 +36,7 @@
service: prometheus
annotations:
summary: "Prometheus samples have duplicate timestamps"
- description: "{{ $value }} last-minute samples of Prometheus on the {{ $labels.instance }} instance have duplicate timestamps."
+ description: "{{ $value }} Prometheus samples on the {{ $labels.instance }} instance have duplicate timestamps (as measured over the last minute)."
{% endraw %}
{%- if server.version == 1.7 %}
{% raw %}
@@ -48,7 +48,7 @@
service: prometheus
annotations:
summary: "Prometheus is in the rushed mode"
- description: "The Prometheus service writes on the {{ $labels.instance }} instance do not keep up with data ingestion speed for at least 10 minutes."
+ description: "The Prometheus service writes on the {{ $labels.instance }} instance do not keep up with data ingestion speed for 10 minutes."
{% endraw %}
{%- endif %}
{%- endif %}
@@ -63,8 +63,8 @@
severity: warning
service: prometheus
annotations:
- summary: "Prometheus remote storage queue is full in {%- endraw %} {{ threshold }}{%- raw %}%"
- description: "The Prometheus remote storage queue on the {{ $labels.instance }} instance is {{ $value }}% full for at least 2 minutes."
+ summary: "Prometheus remote storage queue is {%- endraw %} {{ threshold }}{%- raw %}% full"
+ description: "The Prometheus remote storage queue on the {{ $labels.instance }} instance is {{ $value }}% full for 2 minutes."
{%- endraw %}
{%- endif %}
{%- if remote_storage_adapter.get('enabled', False) %}
@@ -77,8 +77,8 @@
severity: warning
service: remote_storage_adapter
annotations:
- summary: "Ratio of sent to received remote storage adapter metrics is {%- endraw %} {{ threshold }}{%- raw %}"
- description: "The ratio of the sent to received metrics of the remote storage adapter on the {{ $labels.instance }} instance is {{ $value }}."
+ summary: "Remote storage adapter metrics sent/received ratio reached limit of {%- endraw %} {{ threshold }}{%- raw %}"
+ description: "The remote storage adapter metrics on sent to received ratio the {{ $labels.instance }} instance is {{ $value }}."
{% endraw %}
RemoteStorageAdapterMetricsIgnoredWarning:
{%- set threshold = monitoring.remote_storage_adapter.ignored_vs_sent_ratio|float %}
@@ -104,7 +104,7 @@
service: alertmanager
annotations:
summary: "Alertmanager notifications fail"
- description: "An average of {{ $value }} Alertmanager {{ $labels.integration }} notifications on the {{ $labels.instance }} instance fail for at least 2 minutes."
+ description: "An average of {{ $value }} Alertmanager {{ $labels.integration }} notifications on the {{ $labels.instance }} instance fail for 2 minutes."
AlertmanagerAlertsInvalidWarning:
if: >-
increase(alertmanager_alerts_invalid_total[2m]) > 0
@@ -114,8 +114,7 @@
service: alertmanager
annotations:
summary: "Alertmanager alerts are invalid"
- description: "An average of {{ $value }} Alertmanager {{ $labels.integration }} alerts on the {{ $labels.instance }} instance are invalid for at least 2 minutes."
+ description: "An average of {{ $value }} Alertmanager {{ $labels.integration }} alerts on the {{ $labels.instance }} instance are invalid for 2 minutes."
{%- endraw %}
{%- endif %}
{%- endif %}
-