Skip to content

feature(webhook): add BackendRuntimeConfig resources validation #170

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Sep 23, 2024
Merged

feature(webhook): add BackendRuntimeConfig resources validation #170

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 17 additions & 0 deletions pkg/webhook/playground_webhook.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@ package webhook

import (
"context"
"fmt"

"k8s.io/apimachinery/pkg/runtime"
"k8s.io/apimachinery/pkg/util/validation"
Expand Down Expand Up @@ -122,5 +123,21 @@ func (w *PlaygroundWebhook) generateValidate(obj runtime.Object) field.ErrorList
allErrs = append(allErrs, field.Forbidden(specPath.Child("modelClaims", "models"), "only one main model is allowed"))
}
}

if playground.Spec.BackendRuntimeConfig != nil && playground.Spec.BackendRuntimeConfig.Resources != nil {
requirements := playground.Spec.BackendRuntimeConfig.Resources
for resourceName, limit := range requirements.Limits {
request, ok := requirements.Requests[resourceName]
if !ok {
continue
}

if limit.Cmp(request) == -1 {
allErrs = append(allErrs, field.Forbidden(specPath.Child("backendRuntimeConfig", "resources"),
fmt.Sprintf("limit (%v) for %s must be greater than or equal to request (%v)", limit, resourceName, request)))
}
}
}

return allErrs
}
12 changes: 12 additions & 0 deletions test/integration/webhook/playground_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,6 +69,18 @@ var _ = ginkgo.Describe("Playground default and validation", func() {
},
failed: true,
}),
ginkgo.Entry("invalid BackendRuntime resources", &testValidatingCase{
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could you add another example to cover the scenario: resources in limits but not in requests to make sure there's no panic.

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done

playground: func() *inferenceapi.Playground {
return wrapper.MakePlayground("playground", ns.Name).Replicas(1).ModelClaim("llama3-8b").BackendRuntimeRequest("cpu", "10").BackendRuntimeLimit("cpu", "5").Obj()
},
failed: true,
}),
ginkgo.Entry("valid BackendRuntime resources with limit but without request", &testValidatingCase{
playground: func() *inferenceapi.Playground {
return wrapper.MakePlayground("playground", ns.Name).Replicas(1).ModelClaim("llama3-8b").BackendRuntimeLimit("cpu", "5").Obj()
},
failed: false,
}),
ginkgo.Entry("no model claim declared", &testValidatingCase{
playground: func() *inferenceapi.Playground {
return wrapper.MakePlayground("playground", ns.Name).Replicas(1).Obj()
Expand Down
Loading