support PMML server

[AnyISalIn]

What this PR does / why we need it:
This request will provide KFServing with PMML model support. It completes the PMML Server package based on pypmml and InferenceService PMML API definition, e2e test cases and some documents

Which issue(s) this PR fixes *
Fixes # #462

Special notes for your reviewer:

1. The mirrors and gfs currently used my private repositories, which are public and can be verified
2. After ISVC adds pmml's api definition The CustomResourceDefinition "inferenceservices.serving.kubeflow.org" is invalid: metadata.annotations: Too long: must have at most 262144 bytes, Exceeds the limit of kubernetes, so the kubectl apply in make deploy-dev cannot take effect normally, need to use kubectl replace or create to replace

Release note:

[kubeflow-bot]

This change is 

[google-cla]

Thanks for your pull request. It looks like this may be your first contribution to a Google open source project (if not, look below for help). Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

📝 Please visit https://cla.developers.google.com/ to sign.

Once you've signed (or fixed any issues), please reply here with @googlebot I signed it! and we'll verify it.

---

What to do if you already signed the CLA

Individual signers

• It's possible we don't have your GitHub username or you're using a different email address on your commit. Check your existing CLA data and verify that your email is set on your git commits.

Corporate signers

• Your company has a Point of Contact who decides which employees are authorized to participate. Ask your POC to be added to the group of authorized contributors. If you don't know who your Point of Contact is, direct the Google project maintainer to go/cla#troubleshoot (Public version).
• The email used to register you as an authorized contributor must be the email used for the Git commit. Check your existing CLA data and verify that your email is set on your git commits.
• The email used to register you as an authorized contributor must also be attached to your GitHub account.

ℹ️ Googlers: Go here for more info.

[k8s-ci-robot]

Hi @AnyISalIn. Thanks for your PR.

I'm waiting for a kubeflow member to verify that this patch is reasonable to test. If it is, they should reply with /ok-to-test on its own line. Until that is done, I will not automatically test new commits in this PR, but the usual testing commands by org members will still work. Regular contributors should join the org to skip this step.

Once the patch is verified, the new status will be reflected by the ok-to-test label.

I understand the commands that are listed here.

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes/test-infra repository.

[AnyISalIn]

@googlebot I signed it!

[animeshsingh]

/ok-to-test

[AnyISalIn]

@animeshsingh Hi, I see that the build fails, The log in Prow only shows

INFO|2020-10-22T00:03:09|/src/kubeflow/testing/py/kubeflow/testing/run_e2e_workflow.py|547| Workflow kubeflow-test-infra/kubeflow-kfserving-presubmit-e2e-1141-493a810-0192-5cb5 finished phase: Failed

Where can I see more detailed logs?

[AnyISalIn]

I found the log of argo, It seems to be stuck in kubectl apply

The CustomResourceDefinition "inferenceservices.serving.kubeflow.org" is invalid: metadata.annotations: Too long: must have at most 262144 characters

[animeshsingh]

cc @yuzisun

[AnyISalIn]

@yuzisun Maybe we can try this solution.
https://community.spinnaker.io/t/halyard-with-v2-metadata-annotations-too-long/894

To circumvent the issue for now, we’ve modified Halyard to not use kubectl apply -f while submitting resources to Kubernetes, but use kubectl replace --force --save-config=false -f - instead. This will delete the old resource and recreate it without the aforementioned field (and also works if the resource wasn’t present to begin with). Still testing if this works for all cases and situations though…

[yuzisun]

/retest

[AnyISalIn]

@yuzisun

It seems that the main problem is the expansion caused by PodSpec, We might be able to learn from Tekton
Delete the definition of some fields, and add x-kubernetes-preserve-unknown-fields: true

Like this

yq d -i config/crd/serving.kubeflow.org_inferenceservices.yaml 'spec.versions[1].schema.openAPIV3Schema.properties.spec.properties.*.properties.affinity.properties'

[AnyISalIn]

/retest

[AnyISalIn]

/retest

[yuzisun]

/retest

[yuzisun]

@jinchihe How are we generating these reference links?

[AnyISalIn]

@yuzisun Hi, I already rebase to the latest, and the e2e test passed, when can we merge this PR?

of course, I have another question, Do I still need to write the definition of v1alpha API?

Thanks.

[yuzisun]

@AnyISalIn Great job, left a final comment otherwise good to merge.

[AnyISalIn]

@yuzisun How do we upload PMML samples to KFServing public GCS and release docker image to DockerHub?

[yuzisun]

@yuzisun How do we upload PMML samples to KFServing public GCS and release docker image to DockerHub?

@yuzisun How do we upload PMML samples to KFServing public GCS and release docker image to DockerHub?

@AnyISalIn We will take care of the docker image publish when releasing 0.5, please also add a OWNER file under pmmlserver directory, I am assuming you are going to own and maintain this server going forward?

[AnyISalIn]

@AnyISalIn We will take care of the docker image publish when releasing 0.5, please also add a OWNER file under pmmlserver directory, I am assuming you are going to own and maintain this server going forward?

@yuzisun I hope to be able to push pmmlserver image to KFServing public gcr.io, maintenance refers to maintaining code or docker image?

[yuzisun]

@AnyISalIn We will take care of the docker image publish when releasing 0.5, please also add a OWNER file under pmmlserver directory, I am assuming you are going to own and maintain this server going forward?

@yuzisun I hope to be able to push pmmlserver image to KFServing public gcr.io, maintenance refers to maintaining code or docker image?

@AnyISalIn I meant for maintaining the pmmlserver related code, OWNER file is for that purpose. Also I created the github action to push pmmlserver to KFS docker registry here #1198.

[yuzisun]

Thanks @AnyISalIn for this great contribution! 🚀

/lgtm
/approve

[k8s-ci-robot]

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: AnyISalIn, yuzisun

The full list of commands accepted by this bot can be found here.

The pull request process is described here

Needs approval from an approver in each of these files:

• OWNERS [yuzisun]

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment