Google Vertex AI monitoring

Dynatrace Google Cloud integration leverages data collected from the Google Operation API to constantly monitor health and performance of Google Cloud Services. While combining all relevant data into dashboards, it also enables alerting and event tracking.

Prerequisites

Set up integration

Add services and feature sets optional

After integration, Dynatrace automatically monitors a number of preset Google Cloud services and feature sets (metrics). Besides these, you can add more services or feature sets to monitoring. For details, see Add or remove services.

For a list of feature sets available for this service, see Metric table.

View metrics

After deploying the integration, you can see metrics from monitored services in the Metrics browser, Data Explorer, and your dashboard tiles.

Metric table

The following feature sets are available for Google Cloud Vertex AI.

Feature set
Name
Unit
GCP metric identifier
vertexai_deployment_resource_pool/default_metrics
Accelerator duty cycle
Percent
aiplatform_googleapis_com/prediction/online/deployment_resource_pool/accelerator/duty_cycle
vertexai_deployment_resource_pool/default_metrics
Accelerator memory usage
Byte
aiplatform_googleapis_com/prediction/online/deployment_resource_pool/accelerator/memory/bytes_used
vertexai_deployment_resource_pool/default_metrics
CPU utilization
Percent
aiplatform_googleapis_com/prediction/online/deployment_resource_pool/cpu/utilization
vertexai_deployment_resource_pool/default_metrics
Memory usage
Byte
aiplatform_googleapis_com/prediction/online/deployment_resource_pool/memory/bytes_used
vertexai_deployment_resource_pool/default_metrics
Network bytes received
Byte
aiplatform_googleapis_com/prediction/online/deployment_resource_pool/network/received_bytes_count
vertexai_deployment_resource_pool/default_metrics
Network bytes sent
Byte
aiplatform_googleapis_com/prediction/online/deployment_resource_pool/network/sent_bytes_count
vertexai_deployment_resource_pool/default_metrics
Replica count
Count
aiplatform_googleapis_com/prediction/online/deployment_resource_pool/replicas
vertexai_deployment_resource_pool/default_metrics
Replica target
Count
aiplatform_googleapis_com/prediction/online/deployment_resource_pool/target_replicas
vertexai_endpoint/default_metrics
Accelerator duty cycle
Percent
aiplatform_googleapis_com/prediction/online/accelerator/duty_cycle
vertexai_endpoint/default_metrics
Accelerator memory usage
Byte
aiplatform_googleapis_com/prediction/online/accelerator/memory/bytes_used
vertexai_endpoint/default_metrics
CPU utilization
Percent
aiplatform_googleapis_com/prediction/online/cpu/utilization
vertexai_endpoint/default_metrics
Number of online prediction errors
Count
aiplatform_googleapis_com/prediction/online/error_count
vertexai_endpoint/default_metrics
Memory usage
Byte
aiplatform_googleapis_com/prediction/online/memory/bytes_used
vertexai_endpoint/default_metrics
Network bytes received
Byte
aiplatform_googleapis_com/prediction/online/network/received_bytes_count
vertexai_endpoint/default_metrics
Network bytes sent
Byte
aiplatform_googleapis_com/prediction/online/network/sent_bytes_count
vertexai_endpoint/default_metrics
Number of online predictions
Count
aiplatform_googleapis_com/prediction/online/prediction_count
vertexai_endpoint/default_metrics
Prediction latencies
MilliSecond
aiplatform_googleapis_com/prediction/online/prediction_latencies
vertexai_endpoint/default_metrics
Private endpoint prediction latencies
MilliSecond
aiplatform_googleapis_com/prediction/online/private/prediction_latencies
vertexai_endpoint/default_metrics
Private endpoint response count
Count
aiplatform_googleapis_com/prediction/online/private/response_count
vertexai_endpoint/default_metrics
Replica count
Count
aiplatform_googleapis_com/prediction/online/replicas
vertexai_endpoint/default_metrics
Response count
Count
aiplatform_googleapis_com/prediction/online/response_count
vertexai_endpoint/default_metrics
Replica target
Count
aiplatform_googleapis_com/prediction/online/target_replicas
vertexai_feature_online_store/feature_store
Request count
Count
aiplatform_googleapis_com/featureonlinestore/online_serving/request_count
vertexai_feature_online_store/feature_store
Response bytes count
Count
aiplatform_googleapis_com/featureonlinestore/online_serving/serving_bytes_count
vertexai_feature_online_store/feature_store
Request latency
MilliSecond
aiplatform_googleapis_com/featureonlinestore/online_serving/serving_latencies
vertexai_feature_online_store/feature_store
Running sycs
Count
aiplatform_googleapis_com/featureonlinestore/running_sync
vertexai_feature_online_store/feature_store
Serving data ages
Second
aiplatform_googleapis_com/featureonlinestore/serving_data_ages
vertexai_feature_online_store/feature_store
Serving data by synced time
Count
aiplatform_googleapis_com/featureonlinestore/serving_data_by_sync_time
vertexai_feature_online_store/feature_store
CPU load
Percent
aiplatform_googleapis_com/featureonlinestore/storage/bigtable_cpu_load
vertexai_feature_online_store/feature_store
CPU load (hottest node)
Percent
aiplatform_googleapis_com/featureonlinestore/storage/bigtable_cpu_load_hottest_node
vertexai_feature_online_store/feature_store
Node count
Count
aiplatform_googleapis_com/featureonlinestore/storage/bigtable_nodes
vertexai_feature_online_store/feature_store
Optimized node count
Count
aiplatform_googleapis_com/featureonlinestore/storage/optimized_nodes
vertexai_feature_online_store/feature_store
Bytes stored
Byte
aiplatform_googleapis_com/featureonlinestore/storage/stored_bytes
vertexai_feature_store/feature_store
CPU load
Percent
aiplatform_googleapis_com/featurestore/cpu_load
vertexai_feature_store/feature_store
CPU load (hottest node)
Percent
aiplatform_googleapis_com/featurestore/cpu_load_hottest_node
vertexai_feature_store/feature_store
Node count
Count
aiplatform_googleapis_com/featurestore/node_count
vertexai_feature_store/feature_store
Entities updated on the Featurestore online storage
Byte
aiplatform_googleapis_com/featurestore/online_entities_updated
vertexai_feature_store/feature_store
Latencies
MilliSecond
aiplatform_googleapis_com/featurestore/online_serving/latencies
vertexai_feature_store/feature_store
Request size
Byte
aiplatform_googleapis_com/featurestore/online_serving/request_bytes_count
vertexai_feature_store/feature_store
Serving count
Count
aiplatform_googleapis_com/featurestore/online_serving/request_count
vertexai_feature_store/feature_store
Response size
Byte
aiplatform_googleapis_com/featurestore/online_serving/response_size
vertexai_feature_store/feature_store
Billable bytes
Byte
aiplatform_googleapis_com/featurestore/storage/billable_processed_bytes
vertexai_feature_store/feature_store
Bytes stored
Byte
aiplatform_googleapis_com/featurestore/storage/stored_bytes
vertexai_feature_store/feature_store
Offline storage write for streaming write
Count
aiplatform_googleapis_com/featurestore/streaming_write/offline_processed_count
vertexai_feature_store/feature_store
Streaming write to offline storage delay time
Second
aiplatform_googleapis_com/featurestore/streaming_write/offline_write_delays
vertexai_location/default_metrics
Executing PipelineJobs
Count
aiplatform_googleapis_com/executing_vertexai_pipeline_jobs
vertexai_location/default_metrics
Executing PipelineTasks
Count
aiplatform_googleapis_com/executing_vertexai_pipeline_tasks
vertexai_location/default_metrics
Generate content requests per minute per project per base model
Count
aiplatform_googleapis_com/generate_content_requests_per_minute_per_project_per_base_model
vertexai_location/default_metrics
Online prediction dedicated requests per base model version
Count
aiplatform_googleapis_com/online_prediction_dedicated_requests_per_base_model_version
vertexai_location/default_metrics
Online prediction dedicated tokens per minute per base model version
Count
aiplatform_googleapis_com/online_prediction_dedicated_tokens_per_base_model_version
vertexai_location/default_metrics
Online prediction requests per base model
Count
aiplatform_googleapis_com/online_prediction_requests_per_base_model
vertexai_location/default_metrics
Online prediction tokens per minute per base model
Count
aiplatform_googleapis_com/online_prediction_tokens_per_minute_per_base_model
vertexai_location/default_metrics
Generate content requests per minute per project per base model quota exceeded error
Count
aiplatform_googleapis_com/quota/generate_content_requests_per_minute_per_project_per_base_model/exceeded
vertexai_location/default_metrics
Generate content requests per minute per project per base model quota limit
Count
aiplatform_googleapis_com/quota/generate_content_requests_per_minute_per_project_per_base_model/limit
vertexai_location/default_metrics
Generate content requests per minute per project per base model quota usage
Count
aiplatform_googleapis_com/quota/generate_content_requests_per_minute_per_project_per_base_model/usage
vertexai_location/default_metrics
Online prediction dedicated requests per base model version quota exceeded error
Count
aiplatform_googleapis_com/quota/online_prediction_dedicated_requests_per_base_model_version/exceeded
vertexai_location/default_metrics
Online prediction dedicated requests per base model version quota limit
Count
aiplatform_googleapis_com/quota/online_prediction_dedicated_requests_per_base_model_version/limit
vertexai_location/default_metrics
Online prediction dedicated requests per base model version quota usage
Count
aiplatform_googleapis_com/quota/online_prediction_dedicated_requests_per_base_model_version/usage
vertexai_location/default_metrics
Online prediction dedicated tokens per minute per base model version quota exceeded error
Count
aiplatform_googleapis_com/quota/online_prediction_dedicated_tokens_per_base_model_version/exceeded
vertexai_location/default_metrics
Online prediction dedicated tokens per minute per base model version quota limit
Count
aiplatform_googleapis_com/quota/online_prediction_dedicated_tokens_per_base_model_version/limit
vertexai_location/default_metrics
Online prediction dedicated tokens per minute per base model version quota usage
Count
aiplatform_googleapis_com/quota/online_prediction_dedicated_tokens_per_base_model_version/usage
vertexai_location/default_metrics
Online prediction requests per base model quota exceeded
Count
aiplatform_googleapis_com/quota/online_prediction_requests_per_base_model/exceeded
vertexai_location/default_metrics
Online prediction requests per base model quota limit
Count
aiplatform_googleapis_com/quota/online_prediction_requests_per_base_model/limit
vertexai_location/default_metrics
Online prediction requests per base model quota usage
Count
aiplatform_googleapis_com/quota/online_prediction_requests_per_base_model/usage
vertexai_location/default_metrics
Online prediction tokens per minute per base model quota exceeded
Count
aiplatform_googleapis_com/quota/online_prediction_tokens_per_minute_per_base_model/exceeded
vertexai_location/default_metrics
Online prediction tokens per minute per base model quota limit
Count
aiplatform_googleapis_com/quota/online_prediction_tokens_per_minute_per_base_model/limit
vertexai_location/default_metrics
Online prediction tokens per minute per base model quota usage
Count
aiplatform_googleapis_com/quota/online_prediction_tokens_per_minute_per_base_model/usage
vertexai_pipeline_job/pipelines
PipelineJob duration
Second
aiplatform_googleapis_com/pipelinejob/duration
vertexai_pipeline_job/pipelines
Completed PipelineTasks
Count
aiplatform_googleapis_com/pipelinejob/task_completed_count
vertexai_index/vector_search
Datapoint count
Count
aiplatform_googleapis_com/matching_engine/stream_update/datapoint_count
vertexai_index/vector_search
Stream update latencies
MilliSecond
aiplatform_googleapis_com/matching_engine/stream_update/latencies
vertexai_index/vector_search
Request count
Count
aiplatform_googleapis_com/matching_engine/stream_update/request_count
vertexai_index_endpoint/vector_search
CPU request utilization
Percent
aiplatform_googleapis_com/matching_engine/cpu/request_utilization
vertexai_index_endpoint/vector_search
Current replicas
Count
aiplatform_googleapis_com/matching_engine/current_replicas
vertexai_index_endpoint/vector_search
Current shards
Count
aiplatform_googleapis_com/matching_engine/current_shards
vertexai_index_endpoint/vector_search
Memory usage
Byte
aiplatform_googleapis_com/matching_engine/memory/used_bytes
vertexai_index_endpoint/vector_search
Request latency
MilliSecond
aiplatform_googleapis_com/matching_engine/query/latencies
vertexai_index_endpoint/vector_search
Request count
Count
aiplatform_googleapis_com/matching_engine/query/request_count
vertexai_publisher_model/default_metrics
Character count
Count
aiplatform_googleapis_com/publisher/online_serving/character_count
vertexai_publisher_model/default_metrics
Characters
Count
aiplatform_googleapis_com/publisher/online_serving/characters
vertexai_publisher_model/default_metrics
Character Throughput
Count
aiplatform_googleapis_com/publisher/online_serving/consumed_throughput/count
vertexai_publisher_model/default_metrics
First token latencies
MilliSecond
aiplatform_googleapis_com/publisher/online_serving/first_token_latencies
vertexai_publisher_model/default_metrics
Model invocation count
Count
aiplatform_googleapis_com/publisher/online_serving/model_invocation_count
vertexai_publisher_model/default_metrics
Model invocation latencies
MilliSecond
aiplatform_googleapis_com/publisher/online_serving/model_invocation_latencies
vertexai_publisher_model/default_metrics
Token count
Count
aiplatform_googleapis_com/publisher/online_serving/token_count
vertexai_publisher_model/default_metrics
Tokens
Count
aiplatform_googleapis_com/publisher/online_serving/tokens
visionai_instance/vision_ai
Request count
Count
visionai_googleapis_com/platform/connected_service/request_count
visionai_instance/vision_ai
Request latencies
MilliSecond
visionai_googleapis_com/platform/connected_service/request_latencies
visionai_instance/vision_ai
Prediction count
Count
visionai_googleapis_com/platform/custom_model/predict_count
visionai_instance/vision_ai
Prediction latencies
MilliSecond
visionai_googleapis_com/platform/custom_model/predict_latencies
visionai_instance/vision_ai
Uptime
MilliSecond
visionai_googleapis_com/platform/instance/uptime
visionai_stream/vision_ai
Received bytes
Byte
visionai_googleapis_com/stream/network/received_bytes_count
visionai_stream/vision_ai
Received packets
Count
visionai_googleapis_com/stream/network/received_packets_count
visionai_stream/vision_ai
Sent bytes
Byte
visionai_googleapis_com/stream/network/sent_bytes_count
visionai_stream/vision_ai
Sent packets
Count
visionai_googleapis_com/stream/network/sent_packets_count

Related topics