Help Center> ModelArts> API Reference> Service Management> Obtaining Service Monitoring

Updated on 2024-04-30 GMT+08:00

View PDF

Obtaining Service Monitoring

Function

This API is used to obtain service monitoring information.

Debugging

You can debug this API through automatic authentication in API Explorer or use the SDK sample code generated by API Explorer.

URI

GET /v1/{project_id}/services/{service_id}/monitor

**Table 1** Path Parameters
Parameter	Mandatory	Type	Description
project_id	Yes	String	Project ID. For details, see Obtaining a Project ID and Name.
service_id	Yes	String	Service ID

**Table 2** Query Parameters
Parameter	Mandatory	Type	Description
node_id	No	String	ID of the edge node to be obtained. This parameter is available only when infer_type is set to edge. By default, all nodes are obtained.

Request Parameters

**Table 3** Request header parameters
Parameter	Mandatory	Type	Description
X-Auth-Token	Yes	String	User token. It can be obtained by calling the IAM API that is used to obtain a user token. The value of X-Subject-Token in the response header is the user token.

Response Parameters

Status code: 200

**Table 4** Response body parameters
Parameter	Type	Description
service_name	String	Service name
service_id	String	Service ID
monitors	Array of Monitor objects	Monitoring details
service_running_instance_count	Integer	Number of running service instances
service_instance_count	Integer	Number of service instances
req_count_per_min	Long	Total number of service calls in the last minute

**Table 5** Monitor
Parameter	Type	Description
failed_times	Integer	Number of times that a model instance fails to be called. This parameter is available for real-time services.
model_version	String	Model version, which is available for real-time services
cpu_memory_total	Integer	Total memory, in MB
gpu_usage	Float	Number of used GPUs
node_name	String	Node name, which is available for edge services
gpu_total	Float	Total number of GPUs
model_id	String	Model ID, which is available for real-time services
invocation_times	Integer	Number of times that a model instance is called. This parameter is available for real-time services.
cpu_core_usage	Float	Number of used CPU cores
cpu_core_total	Float	Total number of CPU cores
model_name	String	Model name, which is available for real-time services
cpu_memory_usage	Integer	Used memory, in MB
node_id	String	Edge node ID, which is available for edge services
model_running_instance_count	Integer	Number of running model instances
model_instance_count	Integer	Number of model instances
gpu_memory_total	Float	Total GPU memory, in MB
gpu_memory_usage	Float	Used GPU memory, in MB
npu_total	Float	Total number of NPUs
npu_usage	Float	Number of used NPUs
npu_memory_total	Float	Total NPU memory, in MB
npu_memory_usage	Float	Used NPU memory, in MB

Example Requests

GET https://{endpoint}/v1/{project_id}/services/{service_id}/monitor

Example Responses

Status code: 200

Monitoring information

{
  "service_name" : "mnist",
  "service_id" : "195c1f2d-136d-40af-a0f3-db5717d2634a",
  "monitors" : [ {
    "failed_times" : 1,
    "model_version" : "1.0.0",
    "cpu_core_total" : 4,
    "cpu_memory_total" : 8192,
    "model_name" : "minst",
    "gpu_usage" : 0.6,
    "cpu_memory_usage" : 2011,
    "gpu_total" : 1,
    "model_id" : "0e07b41b-173e-42db-8c16-8e1b44cc0d44",
    "invocation_times" : 50,
    "cpu_core_usage" : 2.4
  } ]
}