ModelArts Metrics¶
Description¶
The cloud service platform provides Cloud Eye to help you better understand the status of your ModelArts real-time services and models. You can use Cloud Eye to automatically monitor your ModelArts real-time services and models in real time and manage alarms and notifications, so that you can keep track of performance metrics of ModelArts and models.
Namespace¶
SYS.ModelArts
Monitoring Metrics¶
Metric ID | Metric Name | Meaning | Value Range | Measurement Object & Dimension | Monitoring Interval |
|---|---|---|---|---|---|
cpu_usage | CPU Usage | CPU usage of ModelArts Unit: % | >= 0% | Measurement object: ModelArts models Dimension: model_id | 1 minute |
mem_usage | Memory Usage | Memory usage of ModelArts Unit: % | >= 0% | Measurement object: ModelArts models Dimension: model_id | 1 minute |
gpu_util | GPU Usage | GPU usage of ModelArts Unit: % | >= 0% | Measurement object: ModelArts models Dimension: model_id | 1 minute |
successfully_called_times | Number of Successful Calls | Times that ModelArts has been successfully called Unit: Times/min | >=Count/min | Measurement object: ModelArts models ModelArts real-time services Dimension: model_id, service_id | 1 minute |
failed_called_times | Number of Failed Calls | Times that ModelArts failed to be called Unit: Times/min | >=Count/min | Measurement object: ModelArts models ModelArts real-time services Dimension: model_id, service_id | 1 minute |
total_called_times | API Calls | Times that ModelArts is called Unit: Times/min | >=Count/min | Measurement object: ModelArts models ModelArts real-time services Dimension: model_id, service_id | 1 minute |
If a measurement object has multiple measurement dimensions, all the measurement dimensions are mandatory when you use an API to query monitoring metrics.
|
Dimensions¶
Key | Value |
|---|---|
service_id | Real-time service ID |
model_id | Model ID |