Help Center> ModelArts> API Reference> Service Management> Querying Service Update Logs
View PDF

Querying Service Update Logs

Function

This API is used to query the update logs of a real-time service. Only the services whose infer_type is real-time or edge can be queried.

URI

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

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

Request Body

None

Response Body

Table 2 describes the response parameters.

Table 2 Parameter description

Parameter

Type

Description

service_id

String

Service ID

service_name

String

Service name

logs

log array

Service update logs. For details, see Table 3.
Table 3 log parameters

Parameter

Type

Description

update_time

Number

Time when a service is updated, in milliseconds calculated from 1970.1.1 0:0:0 UTC

result

String

Update result. The value can be SUCCESS, FAIL, or RUNNING.

config

config array

Updated service configurations. For details, see Table 4.

success_num

Number

Number of nodes that are successfully operated. This parameter is returned when infer_type is set to edge.

failed_num

Number

Number of nodes that fail to be operated. This parameter is returned when infer_type is set to edge.

result_detail

result array

Operation result details. This parameter is returned when infer_type is set to edge. For details, see Table 5.

cluster_id

String

ID of a dedicated resource pool

extend_config

List

Personalized configuration
Table 4 config parameters

Parameter

Type

Description

model_id

String

Model ID

model_name

String

Model name

model_version

String

Model version

weight

Integer

Traffic weight allocated to a model. This parameter is returned when infer_type is set to real-time.

specification

String

Resource flavor. This parameter is returned when infer_type is set to real-time or edge.

instance_count

Integer

Number of instances deployed in a model. This parameter is returned when infer_type is set to real-time.

envs

Map<String, String>

Environment variable key-value pair required for running a model

cluster_id

String

ID of a dedicated resource pool
Table 5 result parameters

Parameter

Type

Description

node_id

String

Node ID

node_name

String

Node name

operation

String

Operation type. The value can be deploy or delete.

result

Boolean

Operation result. true indicates operation success, and false indicates operation failure.

Samples

The following shows how to query the update logs of the real-time service whose ID is xxxxxx and name is mnist.

  • Sample request 
    GET    https://endpoint/v1/{project_id}/services/xxxxxx/logs
  • Sample response 
    {
	"service_id": "e2122bbd-f7c8-4bf8-bacc-59616276194b",
	"service_name": "service-demo",
	"logs": [{
		"config": [{
			"model_id": "f565ac47-6239-4e8c-b2dc-0665dc52e302",
			"model_name": "model-demo",
			"model_version": "0.0.1",
			"specification": "modelarts.vm.cpu.2u",
			"custom_spec": {},
			"weight": 100,
			"instance_count": 1,
			"scaling": false,
			"envs": {},
			"cluster_id": "2c9080f86d37da64016d381fe5940002"
		}],
		"extend_config": [],
		"update_time": 1586250930708,
		"result": "RUNNING",
		"cluster_id": "2c9080f86d37da64016d381fe5940002"
	}]
}

Status Code

For details about the status code, see Table 1.

Parent topic: Service Management