!LuUSGaeArTeoOgUpwk:matrix.org

kubeflow-kfserving

434 Members
3 Servers

You have reached the beginning of time (for this room).


SenderMessageTime
15 May 2022
@_slack_kubeflow_U03DGNK5EBT:matrix.orgAmanjeet Sahu joined the room.08:38:19
16 May 2022
@_slack_kubeflow_U02S0UGJWCV:matrix.orgwenyang zhou截屏2022-05-16 上午11.04.47.png
Download 截屏2022-05-16 上午11.04.47.png
03:06:39
@_slack_kubeflow_U02S0UGJWCV:matrix.orgwenyang zhou There seems to be a lock 03:06:39
@_slack_kubeflow_U02S0UGJWCV:matrix.orgwenyang zhou I have release several revision in a period of time. 03:09:02
@_slack_kubeflow_U02S0UGJWCV:matrix.orgwenyang zhou The old revision can not terminate before it finish pending . 03:09:47
@_slack_kubeflow_U02S0UGJWCV:matrix.orgwenyang zhou And the new revision can not allocate enough resource before the old revision release resource. 03:10:33
@_slack_kubeflow_U02S0UGJWCV:matrix.orgwenyang zhou Could we improve this problem ? 03:10:54
@_slack_kubeflow_U02S0UGJWCV:matrix.orgwenyang zhou Current revision is 15 with 100% traffic percent, and I have roll out the revision 16 with 100% this time. 03:14:19
@_slack_kubeflow_U02S0UGJWCV:matrix.orgwenyang zhou After a few minutes, the revision 16 has release resources. But 13 and 17 keep it. 03:16:32
@_slack_kubeflow_U02S0UGJWCV:matrix.orgwenyang zhou Is this a knative problem? 03:23:19
@_slack_kubeflow_U02S0UGJWCV:matrix.orgwenyang zhou截屏2022-05-16 上午11.32.16.png
Download 截屏2022-05-16 上午11.32.16.png
03:32:32
@_slack_kubeflow_U02S0UGJWCV:matrix.orgwenyang zhou So confused! 03:32:58
@_slack_kubeflow_U02S0UGJWCV:matrix.orgwenyang zhou Revision 13 can not terminate~ 03:33:31
@_slack_kubeflow_U032CM1LH3N:matrix.orgSaurabh Agarwal Shri Javadekar host not found error 06:27:47
@_slack_kubeflow_U032CM1LH3N:matrix.orgSaurabh Agarwal v0.7.0 this is the version 07:36:59
@idahotokens:matrix.org@idahotokens:matrix.org joined the room.11:11:19
@idahotokens:matrix.org@idahotokens:matrix.org left the room.16:30:27
@_slack_kubeflow_U02R5JH4KNK:matrix.orgCesar Flores Hi everyone, is anyone using a way to define the output of the models for downstream applications? like for example having openAPI so the consumers of the models know what the ouutput of the response will be??? 16:30:46
@_slack_kubeflow_U02R5JH4KNK:matrix.orgCesar Flores this is pretty annoying, but if it helps in any way, I solved my issue by using the Host: as the url that appears when you run kubectl get ksvc -n namespace 16:31:53
@_slack_kubeflow_U02AYBVSLSK:matrix.orgAlexandre Brown Saurabh Agarwal Make sure to add the host to the headers 16:32:43
@_slack_kubeflow_U02R5JH4KNK:matrix.orgCesar Flores thanks! yes I meant that the host in the headers shoudl be the URL that appeas in the ksvc type in the cluster 16:33:35
@_slack_kubeflow_U02AYBVSLSK:matrix.orgAlexandre Brown I think you can even omit the http part, I have the host as this in my working sample :
host = f"{model_server_name}.{stage}.svc.cluster.local"
16:34:37
@_slack_kubeflow_U0315UY2WRM:matrix.orgShri Javadekar Also, are you calling this endpoint from inside the cluster? These are my python code snippets for calling from inside the cluster. Alexandre Brown and Cesar Flores are correct that the HOST header needs to be set.
def set_header(hostname):
    headers = {
        'Host': hostname
    }

    return headers

class ProxyHTTPRequestHandler(BaseHTTPRequestHandler):
    protocol_version = 'HTTP/1.1'
    def req_send(self, url, hostname):
        content_len = int(self.headers.get('content-length', 0))
        post_body = self.rfile.read(content_len)
        req_header = self.parse_headers()

        resp = requests.post(url, data=post_body, headers=merge_two_dicts(req_header, set_header(hostname)), verify=False)
        return resp
url = "http://my-model-a.kserve-test.svc.cluster.local/v1/models/my-model-a:predict"
resp = self.req_send(url, hostname)
print(resp.content)
16:40:12

Show newer messages


Back to Room ListRoom Version: 6