Obtaining Service Monitoring Information
You can use the API to obtain the monitoring information about a service.
Sample Code
In ModelArts notebook, you do not need to enter authentication parameters for session authentication. For details about session authentication of other development environments, see Session Authentication.
- Method 1: Obtain the monitoring information of a service based on the service object created in Deploying a Real-Time Service.
1 2 3 4 5 6 7
from modelarts.session import Session from modelarts.model import Predictor session = Session() predictor_instance = Predictor(session, service_id="your_service_id") predictor_monitor = predictor_instance.get_service_monitor() print(predictor_monitor)
- Method 2: Obtain the monitoring information of a service based on the service object returned in Obtaining Service Objects.
1 2 3 4 5 6 7 8
from modelarts.session import Session from modelarts.model import Predictor session = Session() predictor_object_list = Predictor.get_service_object_list(session) predictor_instance = predictor_object_list[0] predictor_monitor = predictor_instance.get_service_monitor() print(predictor_monitor)
Parameters
Parameter | Type | Description |
|---|---|---|
service_id | String | Service ID |
service_name | String | Service name |
monitors | monitor array corresponding to infer_type of a service | Monitoring details |
Parameter | Type | Description |
|---|---|---|
model_id | String | Model ID |
model_name | String | Model name |
model_version | String | Model version |
invocation_times | Number | Total number of model instance calls |
failed_times | Number | Number of failed model instance calls |
cpu_core_usage | Float | Number of used CPUs |
cpu_core_total | Float | Total number of CPUs |
cpu_memory_usage | Integer | Used memory, in MB |
cpu_memory_total | Integer | Total memory, in MB |
gpu_usage | Float | Number of used GPUs |
gpu_total | Float | Total number of GPUs |
Feedback
Was this page helpful?
Provide feedbackThank you very much for your feedback. We will continue working to improve the documentation.
