An Azure managed PostgreSQL database service for app development and deployment.
Hi Askardeen Buhari,
The issue occurred due to a code defect in the Azure PostgreSQL Flexible Server monitoring pipeline that introduced a race condition in the component responsible for publishing customer-visible storage metrics. Because of this condition, the storage-related metrics (storage_percent, storage_used, and storage_free) were never successfully emitted for the affected server, even though the server itself was healthy and correctly configured. This is why metric queries consistently returned zero data points from the time of server creation, while an identically configured dev server was unaffected.
Mitigation and Resolution
Resolving this issue required manual backend intervention to repair the metric emission state on the affected PostgreSQL Flexible Server. Once the correction was applied, the monitoring pipeline was able to process and publish storage metrics normally. No configuration changes were required from the customer side.
Current Status
After the backend fix, storage metrics are expected to populate going forward. Historical data prior to the correction cannot be backfilled, but new metric data should now appear correctly in Azure Monitor.