Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add new alert policy for SAP HANA replication status #831

Merged
merged 6 commits into from
Oct 8, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 9 additions & 2 deletions alerts/google-cloud-agent-for-sap/metadata.yaml
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
alert_policy_templates:
- id: "pacemaker-resource-stopped"
display_name: "Pacemaker for SAP: Resource agent stopped"
description: "Alerts whenever a Pacemaker resource agent has been stopped for more than 3 minutes and is unable to restart."
display_name: "Pacemaker for SAP: Resource agent is stopped"
description: "Alerts whenever a Pacemaker resource agent remains stopped for more than 3 minutes and is unable to restart."
version: 1
related_integrations:
- id: google_agent_for_sap
Expand All @@ -10,6 +10,13 @@ alert_policy_templates:
display_name: "Pacemaker for SAP: Location constraint detected"
description: "Alerts whenever a Pacemaker resource agent is restricted from running on a node due to a location constraint."
version: 1
related_integrations:
- id: google_agent_for_sap
platform: GCP
- id: "replication-not-in-sync"
display_name: "SAP HANA replication is not in sync"
description: "Alerts whenever an SAP HANA system is no longer in sync with its secondary site"
version: 1
related_integrations:
- id: google_agent_for_sap
platform: GCP
26 changes: 26 additions & 0 deletions alerts/google-cloud-agent-for-sap/replication-not-in-sync.v1.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,26 @@
{
"displayName": "SAP HANA Replication is not in sync",
"documentation": {
"content": "The replication status of SAP HANA instance ${metric.label.sid} on ${metric.label.metadata_system_name} has returned value \t\n${metric.label.value} and is not in sync. Verify that both SAP HANA primary and secondary sites running and that there they are able to communicate with one another.\n\nFor more information on interpreting the system replication return values refer to the [official SAP HANA Administration guide](https://help.sap.com/docs/SAP_HANA_PLATFORM/4e9b18c116aa42fc84c7dbfd02111aba/f6b1bd1020984ee69e902b21b702c096.html).",
"mimeType": "text/markdown",
"subject": "SAP HANA Replication issue detected on ${metric.label.sid}"
},
"userLabels": {},
"conditions": [
{
"displayName": "SAP HANA replication not in sync",
"conditionPrometheusQueryLanguage": {
"duration": "60s",
"evaluationInterval": "60s",
"query": "topk(1,max by (metadata_system_name,sid)(\n workload_googleapis_com:sap_hana_ha_replication{\n monitored_resource=\"gce_instance\",\n #Uncomment the following line to filter by SID\n #sid=~\"ABC|HDB|XYZ\"\n }) <= 11)"
}
}
],
"alertStrategy": {
"autoClose": "1800s"
},
"combiner": "OR",
"enabled": false,
"notificationChannels": [],
"severity": "WARNING"
}
Loading