troubleshooting.md 2.2 KB

Troubleshooting

View MaaS-Base Logs

You can view MaaS-Base logs with the following commands for the default setup:

docker logs -f gpustack

Enable Debug Mode

You can enable the DEBUG mode by setting the --debug flag when running MaaS-Base:

sudo docker run -d --name gpustack \
    ...
    gpustack/gpustack \
+    --debug
    ...

You can also enable MaaS-Base's debug mode at runtime by running the following command inside the server container:

gpustack reload-config --set debug=true

Configure Log Level

You can configure log level of the MaaS-Base server at runtime by running the following command inside the server container:

curl -X PUT http://localhost/debug/log_level -d "debug"

The same applies to MaaS-Base workers:

curl -X PUT http://localhost:10150/debug/log_level -d "debug"

The available log levels are: trace, debug, info, warning, error, critical.

Reset Admin Password

In case you forgot the admin password, you can reset it by running the following command inside the server container:

gpustack reset-admin-password

If you changed the default port using --port when starting MaaS-Base, specify the MaaS-Base URL using the --server-url parameter. It must be run locally on the server and accessed via localhost:

gpustack reset-admin-password --server-url http://localhost:9090

Assist in Accelerators Detection Diagnosis

After successfully deploying the MaaS-Base Worker as described in the installation guide,
if the Worker fails to detect any devices,
please enter the corresponding Worker container, run the following command, and report the results to MaaS-Base.

time GPUSTACK_RUNTIME_LOG_LEVEL=debug GPUSTACK_RUNTIME_LOG_EXCEPTION=1 gpustack-runtime detect --format json

Assist in Model Deployment Diagnosis

If you experience issues after deploying a model, PLEASE enter the corresponding Worker container, run the following command, and report the results to MaaS-Base.

gpustack-runtime inspect <model instance name>