How to undeploy the Prediction IO model

Question

I am working with logistic regression using prediction io template. I have been deployed a model using pio deploy. It gives me a port where I am testing my problem. My question is how to undeploy the model. Is there any command to undeploy Or I have to find the PID of port using netstat -npl | grep port no and manually kill the PID.

I am in search for the same answer. The best that I have found is to kill the process. — Indrek Ots, Oct 08 '15 at 11:13

score 5 · Answer 1 · answered Oct 31 '15 at 08:55

5

You can use pio undeploy

pio undeploy --ip <user_ip> --port <user_port>

answered Oct 31 '15 at 08:55

teru

51
3

Thanks, tried `pio undeploy` but getting the following response: `[INFO] [Engine$] Undeploying any existing engine instance at http://0.0.0.0:8000 [ERROR] [Engine$] Another process is using http://0.0.0.0:8000, or an existing engine server is not responding properly (HTTP 405). Unable to undeploy` My Engine is sitting idle, still getting the error. – CᴴᴀZ Apr 02 '18 at 12:20

score 2 · Answer 2 · answered Oct 08 '15 at 14:21

2

another way to undeploy your running engine server is to perform a GET on the /stop endpoint of the server.

Using a browser simply goto:

http://<host>:<port>/stop

Using curl it would look like

curl <host>:<port>/stop

Source:

https://github.com/PredictionIO/PredictionIO/blob/develop/core/src/main/scala/io/prediction/workflow/CreateServer.scala#L651

answered Oct 08 '15 at 14:21

Sebastian

281
1
8

Tried on PIO 0.12 build, seems like they support only `POST` now: `HTTP method not allowed, supported methods: POST` – CᴴᴀZ Apr 02 '18 at 12:17

How to undeploy the Prediction IO model

2 Answers2

Linked