Help Center> ModelArts> API Reference> Service Management> Querying Service Monitoring Information
View PDF

Querying Service Monitoring Information

Function

This API is used to query service monitoring information. Only the services whose infer_type is real-time or edge can be queried.

URI

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

Table 1 describes the required parameters.
Table 1 Parameter description

Parameter

Mandatory

Type

Description

project_id

Yes

String

Project ID. For details about how to obtain the project ID, see Obtaining a Project ID.

service_id

Yes

String

Service ID
Table 2 Parameter description

Parameter

Mandatory

Type

Description

node_id

No

String

ID of the node to be queried. This parameter is available only when infer_type is set to edge. By default, all nodes are queried.

Request Body

None

Response Body

Table 3 describes the response parameters.
Table 3 Parameter description

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
Table 4 monitor parameters of real-time

Parameter

Type

Description

model_id

String

Model ID

model_name

String

Model name

model_version

String

Model version

invocation_times

Long

Total number of model instance calls

failed_times

Long

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 MBs

cpu_memory_total

Integer

Total memory, in MBs

gpu_usage

Float

Number used GPUs

gpu_total

Float

Total number of GPUs
Table 5 monitor parameters of edge

Parameter

Type

Description

node_id

String

Node ID

node_name

String

Node name

cpu_core_usage

Float

Number of used CPUs

cpu_core_total

Float

Total number of CPUs

cpu_memory_usage

Integer

Used memory, in MBs

cpu_memory_total

Integer

Total memory, in MBs

gpu_usage

Float

Number used GPUs

gpu_total

Float

Total number of GPUs

Samples

The following shows how to query the monitoring information about a real-time service.

  • Sample request 
    GET    https://endpoint/v1/{project_id}/services/{service_id}/monitor
  • Sample response 
    {
    "service_id": "xxx",
    "service_name": "mnist",
    "monitors": 
    [{
        "model_id": "xxxx",
        "model_name": "minst",
        "model_version": "1.0.0",
        "invocation_times": 50,
        "failed_times": 1,
        "cpu_core_usage": "2.4",
        "cpu_core_total": "4",
        "cpu_memory_usage": "2011",
        "cpu_memory_total": "8192",
        "gpu_usage": "0.6",
        "gpu_total": "1"
   } ]
}

Status Code

For details about the status code, see Table 1.

Parent topic: Service Management