isvc.deploy(isvc.generate_isvc()) Invalid value: \"\": must be FieldsV1

[zhangchunsheng]

isvc.deploy(isvc.generate_isvc()) Invalid value: "": must be FieldsV1

/home/jupyter/anaconda3/lib/python3.7/site-packages/kfserving/api/kf_serving_client.py in create(self, inferenceservice, namespace, watch, timeout_seconds)
    109             raise RuntimeError(
    110                 "Exception when calling CustomObjectsApi->create_namespaced_custom_object:\
--> 111                  %s\n" % e)
    112 
    113         if watch:

RuntimeError: Exception when calling CustomObjectsApi->create_namespaced_custom_object:                 (422)
Reason: Unprocessable Entity
HTTP response headers: HTTPHeaderDict({'Content-Type': 'application/json', 'Date': 'Wed, 02 Sep 2020 14:13:17 GMT', 'Content-Length': '494'})
HTTP response body: {"kind":"Status","apiVersion":"v1","metadata":{},"status":"Failure","message":"InferenceService.serving.kubeflow.org \"mnist-service-3e23\" is invalid: metadata.managedFields.fieldsType: Invalid value: \"\": must be `FieldsV1`","reason":"Invalid","details":{"name":"mnist-service-3e23","group":"serving.kubeflow.org","kind":"InferenceService","causes":[{"reason":"FieldValueInvalid","message":"Invalid value: \"\": must be `FieldsV1`","field":"metadata.managedFields.fieldsType"}]},"code":422}

[issue-label-bot]

Issue-Label Bot is automatically applying the labels:

Label	Probability
kind/bug	0.98
area/inference	0.82

Please mark this comment with 👍 or 👎 to give our bot feedback!
Links: app homepage, dashboard and code for this bot.

[jinchihe]

@zhangchunsheng Would you please share your kubenertes cluster version?

[zhangchunsheng]

@zhangchunsheng Would you please share your kubenertes cluster version?

I forgot to add the information.

kubectl version

Client Version: version.Info{Major:"1", Minor:"18", GitVersion:"v1.18.8", GitCommit:"9f2892aab98fe339f3bd70e3c470144299398ace", GitTreeState:"clean", BuildDate:"2020-08-13T16:12:48Z", GoVersion:"go1.13.15", Compiler:"gc", Platform:"linux/amd64"}
Server Version: version.Info{Major:"1", Minor:"18", GitVersion:"v1.18.2", GitCommit:"52c56ce7a8272c798dbc29846288d7cd9fbae032", GitTreeState:"clean", BuildDate:"2020-04-16T11:48:36Z", GoVersion:"go1.13.9", Compiler:"gc", Platform:"linux/amd64"}

kfctl version

kfctl v1.1.0-0-g9a3621e

I install kubeflow by kfctl.

kfctl apply -V -f kfctl_k8s_istio.v1.1.0.yaml

[jinchihe]

I guess this is caused by k8s 1.18.x. I think we need to take effort to test fairing on 1.18.x. Thanks.

[zhangchunsheng]

I guess this is caused by k8s 1.18.x. I think we need to take effort to test fairing on 1.18.x. Thanks.

ok

[jinchihe]

@zhangchunsheng I think we can keep the issue open before confirmed :-) Thanks.