Expose tritonserver args in values.yaml

[okyspace]

Current k8s_onprem chart has predefined args in deployment.yaml. We could change it from the yaml file though but would be cleaner to customise the args through values.yaml instead.

[rmccorm4]

Seems reasonable to me. CC @nealvaidya for comments

[nealvaidya]

Looks good to me

[rmccorm4]

Hi @okyspace, LGTM overall, just a few things:

1. Rename additionalArgs to serverArgs to be more clear.
2. Can you also share an example command ... --set serverArgs=... and the output showing that server deployed successfully as a sanity check?
3. Have you signed a CLA already? If not, please follow the instructions here and let us know when you've sent it.

[okyspace]

@rmccorm4 , Thanks for your reply.

1. I have updated the naming based on your suggestion.
2. I can work out an example. Can advise where to provide this example?
3. I will follow up with the CLA.

Thanks.

[okyspace]

@rmccorm4, as requested, I have added the examples for sanity check. Any comments?

---

The examples show how you can set the customised serverArgs and verify that they are taking effect.

1. Execute the command below to generate the helm template to check that the serverArgs is being set correctly.
   helm template --set serverArgs="{'--model-repository=s3://192.168.1.110:9000/triton-models', '--repository-poll-secs=8', '--model-control-mode=poll', '--grpc-use-ssl=false'}" triton -n triton .

You should see the generated deployment.yaml. The serverArgs are populated as array args in this example.

2. Run the container using the command.
   helm install --set serverArgs="{'--model-repository=s3://192.168.1.110:9000/triton-models', '--repository-poll-secs=8', '--model-control-mode=poll', '--grpc-use-ssl=false'}" triton -n triton .

Run kubectl describe pods -n triton. You should see the args in the description.

Once the container is successfully running, run kubectl logs <container id> -n triton.
You should see these outputs that indicates the args set for the triton server.

for e.g. model-repository, model-control-mode

for e.g. repository-poll-secs. You can see from the logs that "Polling model repository" happens every 8 secs.

[okyspace]

I have also emailed my signed CLA.

[okyspace]

Hi, is there anything that I need to follow up to close this PR?

[okyspace]

@rmccorm4 , is there something i missed out for this PR?

[rmccorm4]

This LGTM, thanks for your patience @okyspace 🙇 Letting the linters/pre-commit run to double check.

[rmccorm4]

Added suggested fixes for linter errors

[okyspace]

@rmccorm4 Thanks for the reviews and suggestions.

[rmccorm4]

I have also emailed my signed CLA.

Hi @okyspace, can you either resend this email or clarify the name and company attached to it?

[okyspace]

@rmccorm4
I have resend the CLA.
Name: Ong Kai Yong
Company: N/A. I am not submitting on behalf of a company.

[rmccorm4]

Thanks for your contribution and patience @okyspace !