openstack/charm-ceph-mon
Code Issues Proposed changes

Add alerting rules for RGW multisite deployments

Browse Source 
Add default prometheus alerting rules for RadosGW multisite deployments based
on the built-in Ceph RGW multisite metrics.

Note that the included prometheus_alerts.yml.default rule file
is included for reference only. The ceph-mon charm will utilize the
resource file from https://charmhub.io/ceph-mon/resources/alert-rules
for deployment so that operators can easily customize these rules.

Change-Id: I5a12162d73686963132a952bddd85ec205964de4
This commit is contained in:
Peter Sabaini 2024-01-17 16:50:37 +01:00
parent 7223f2634f
commit 24fccea832
1 changed files with 47 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
files/prometheus_alert_rules/prometheus_alerts.yml.default
View File

@ -633,3 +633,50 @@ groups:
oid: "1.3.6.1.4.1.50495.1.2.1.1.2" oid: "1.3.6.1.4.1.50495.1.2.1.1.2"
severity: "critical" severity: "critical"
type: "ceph_default" type: "ceph_default"
- name: "rgwmultisite"
rules:
- alert: "CephRGWMultisiteFetchError"
annotations:
description: "Unsuccessful Object Replications from source zone threshold has been exceeded. The threshold is defined as 2 errors per 15min"
summary: "Unsuccessful Object Replications from Source Zone Threshold Exceeded"
expr: "increase(ceph_data_sync_from_zone_fetch_errors[15m]) > 2"
for: "5m"
labels:
severity: "warning"
type: "ceph_default"
- alert: "CephRGWMultisitePollError"
annotations:
description: "Unsuccessful Object Replications from Source Zone Threshold Exceeded. The threshold is defined as 2 errors per 15min"
summary: "Unsuccessful Object Replications from Source Zone Threshold Exceeded"
expr: "increase(ceph_data_sync_from_zone_poll_errors[15m]) > 2"
for: "5m"
labels:
severity: "warning"
type: "ceph_default"
- alert: "CephRGWMultisiteFetchErrorCritical"
annotations:
description: "Critical: Unsuccessful Object Replications from source zone threshold has been exceeded. The threshold is defined as 50 errors per 15min"
summary: "Critical: Unsuccessful Object Replications from Source Zone Threshold Exceeded"
expr: "increase(ceph_data_sync_from_zone_fetch_errors[15m]) > 50"
for: "5m"
labels:
severity: "critical"
type: "ceph_default"
- alert: "CephRGWMultisitePollErrorCritical"
annotations:
description: "Critical: Unsuccessful Object Replications from source zone threshold has been exceeded. The threshold is defined as 50 errors per 15min"
summary: "Critical: Unsuccessful Object Replications from Source Zone Threshold Exceeded"
expr: "increase(ceph_data_sync_from_zone_poll_errors[15m]) > 50"
for: "5m"
labels:
severity: "critical"
type: "ceph_default"
- alert: "CephRGWMultisitePollLatency"
annotations:
description: "Latency for poll request threshold exceeded. The threshold is defined as 600s latency per 15min"
summary: "Poll Request Latency Threshold Exceeded"
expr: "increase(ceph_data_sync_from_zone_poll_latency_sum[15m]) > 600"
for: "5m"
labels:
severity: "warning"
type: "ceph_default"