Google Vertex AI Feature Online Store metrics

A Vertex AI feature online store serves features for real-time prediction, backed either by Bigtable or by optimized storage. The health of a feature online store reflects both its serving metrics and the state that Google reports for it, such as stable, updating, or error. Ensure your cloud platform is configured in SolarWinds Observability SaaS to collect this service's data. See Add a GCP cloud account.

The Bigtable metrics are reported only for a store that uses Bigtable storage, and the multi-region metrics only for a store deployed across more than one region.

Many of the collected metrics from Vertex AI Feature Online Store entities are displayed as widgets in SolarWinds Observability explorers; additional metrics may be collected and available in the Metrics Explorer. You can also create an alert for when an entity's metric value moves out of a specific range. See Entities in SolarWinds Observability SaaS for information about entity types in SolarWinds Observability SaaS.

The following table lists some of the metrics collected for these entities. To see the Vertex AI Feature Online Store metrics in the Metrics Explorer, type aiplatform.googleapis.com/featureonlinestore in the search box.

Metric	Unit	Description
sw.metrics.healthscore	Percent (%)	Health state. The health state provides real-time insight into the overall health and performance of your monitored entities. The health state is determined based on anomalies detected for the entity, alerts triggered for the entity's metrics, and the status of the entity. The health state is displayed as one of the following four states and colors: Good, Moderate, Bad, or Unknown. You can determine the impact of the alerts, anomalies, and statuses on the health of an entity type by going to Settings > Health, and selecting a specific entity type. You can also customize the impact. To view the health of Google Vertex AI Feature Online Store entities in the Metrics Explorer, filter the sw.metrics.healthscore metric by entity_types and select gcpvertexaifeatureonlinestore.
gcp.aiplatform.googleapis.com. featureonlinestore.onlineServing.requestCount	Count per second	Number of online serving requests to the feature online store.
gcp.aiplatform.googleapis.com. featureonlinestore.onlineServing.servingLatencies	Milliseconds (ms)	Latency distribution for online serving requests to the feature online store.
gcp.aiplatform.googleapis.com. featureonlinestore.onlineServing.servingBytesCount	Bytes per second	Number of bytes served in online serving responses.
gcp.aiplatform.googleapis.com. featureonlinestore.servingDataAges	seconds (s)	Age of the data being served, as an indication of data freshness. Higher values mean staler data.
gcp.aiplatform.googleapis.com. featureonlinestore.runningSync	Count	Number of sync operations running in the feature online store at a given point in time.
gcp.aiplatform.googleapis.com. featureonlinestore.storage.storedBytes	Bytes	Bytes stored in the feature online store.
gcp.aiplatform.googleapis.com. featureonlinestore.storage.bigtableCpuLoad	Scaled percentage	Average CPU load across the Bigtable nodes backing the feature online store.
gcp.aiplatform.googleapis.com. featureonlinestore.storage.bigtableCpuLoadHottestNode	Scaled percentage	CPU load of the busiest Bigtable node backing the feature online store.
gcp.aiplatform.googleapis.com. featureonlinestore.storage.bigtableNodes	Count	Number of Bigtable nodes backing the feature online store.
gcp.aiplatform.googleapis.com. featureonlinestore.storage.multiRegionBigtableCpuLoad	Scaled percentage	Average CPU load across the Bigtable nodes in a multi-region feature online store.
gcp.aiplatform.googleapis.com. featureonlinestore.storage.multiRegionBigtableNodes	Count	Number of Bigtable nodes across all regions in a multi-region feature online store.
gcp.aiplatform.googleapis.com. featureonlinestore.storage.optimizedNodes	Count	Number of nodes in a feature online store that uses optimized storage.