Skip to content

[improvement] : add logic to retry if update fails due to conflict #1838

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
Oct 28, 2025
Merged

[improvement] : add logic to retry if update fails due to conflict #1838

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
27 changes: 20 additions & 7 deletions internal/conditions/clusterpolicy.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@ import (
"k8s.io/apimachinery/pkg/api/meta"
metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
"k8s.io/apimachinery/pkg/types"
"k8s.io/client-go/util/retry"
"sigs.k8s.io/controller-runtime/pkg/client"
"sigs.k8s.io/controller-runtime/pkg/log"

Expand Down Expand Up @@ -55,14 +56,12 @@ func (u *clusterPolicyUpdater) SetConditionsError(ctx context.Context, cr any, r
return u.setConditions(ctx, clusterPolicyCr, Error, reason, message)
}

func (u *clusterPolicyUpdater) setConditions(ctx context.Context, cr *nvidiav1.ClusterPolicy, statusType, reason, message string) error {
reqLogger := log.FromContext(ctx)
// updateConditions updates the conditions of the ClusterPolicy CR
func (u *clusterPolicyUpdater) updateConditions(ctx context.Context, cr *nvidiav1.ClusterPolicy, statusType, reason, message string) error {
// Fetch latest instance and update state to avoid version mismatch
instance := &nvidiav1.ClusterPolicy{}
err := u.client.Get(ctx, types.NamespacedName{Name: cr.Name}, instance)
if err != nil {
reqLogger.Error(err, "Failed to get ClusterPolicy instance for status update", "name", cr.Name)
return err
if err := u.client.Get(ctx, types.NamespacedName{Name: cr.Name}, instance); err != nil {
return fmt.Errorf("failed to get ClusterPolicy instance for status update: %w", err)
}

switch statusType {
Expand Down Expand Up @@ -93,9 +92,23 @@ func (u *clusterPolicyUpdater) setConditions(ctx context.Context, cr *nvidiav1.C
Message: message,
})
default:
reqLogger.Error(nil, "Unknown status type provided", "statusType", statusType)
return fmt.Errorf("unknown status type provided: %s", statusType)
}

return u.client.Status().Update(ctx, instance)
}

// setConditions updates the conditions of the ClusterPolicy CR
// with retry on conflict to handle version mismatches
func (u *clusterPolicyUpdater) setConditions(ctx context.Context, cr *nvidiav1.ClusterPolicy, statusType, reason, message string) error {
reqLogger := log.FromContext(ctx)

err := retry.RetryOnConflict(retry.DefaultBackoff, func() error {
return u.updateConditions(ctx, cr, statusType, reason, message)
})

if err != nil {
reqLogger.Error(err, "Failed to update ClusterPolicy status after retries", "name", cr.Name)
}
return err
}
27 changes: 20 additions & 7 deletions internal/conditions/nvidiadriver.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@ import (
"k8s.io/apimachinery/pkg/api/meta"
metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
"k8s.io/apimachinery/pkg/types"
"k8s.io/client-go/util/retry"
"sigs.k8s.io/controller-runtime/pkg/client"
"sigs.k8s.io/controller-runtime/pkg/log"

Expand Down Expand Up @@ -61,14 +62,12 @@ func (u *nvDriverUpdater) SetConditionsError(ctx context.Context, cr any, reason
return u.setConditions(ctx, nvDriverCr, Error, reason, message)
}

func (u *nvDriverUpdater) setConditions(ctx context.Context, cr *nvidiav1alpha1.NVIDIADriver, statusType, reason, message string) error {
reqLogger := log.FromContext(ctx)
// updateConditions updates the conditions of the NVIDIADriver CR
func (u *nvDriverUpdater) updateConditions(ctx context.Context, cr *nvidiav1alpha1.NVIDIADriver, statusType, reason, message string) error {
// Fetch latest instance and update state to avoid version mismatch
instance := &nvidiav1alpha1.NVIDIADriver{}
err := u.client.Get(ctx, types.NamespacedName{Name: cr.Name}, instance)
if err != nil {
reqLogger.Error(err, "Failed to get NVIDIADriver instance for status update", "name", cr.Name)
return err
if err := u.client.Get(ctx, types.NamespacedName{Name: cr.Name}, instance); err != nil {
return fmt.Errorf("failed to get NVIDIADriver instance for status update: %w", err)
}

switch statusType {
Expand Down Expand Up @@ -107,9 +106,23 @@ func (u *nvDriverUpdater) setConditions(ctx context.Context, cr *nvidiav1alpha1.
instance.Status.State = nvidiav1alpha1.NotReady
}
default:
reqLogger.Error(nil, "Unknown status type provided", "statusType", statusType)
return fmt.Errorf("unknown status type provided: %s", statusType)
}

return u.client.Status().Update(ctx, instance)
}

// setConditions updates the conditions of the NVIDIADriver CR
// with retry on conflict to handle version mismatches
func (u *nvDriverUpdater) setConditions(ctx context.Context, cr *nvidiav1alpha1.NVIDIADriver, statusType, reason, message string) error {
reqLogger := log.FromContext(ctx)

err := retry.RetryOnConflict(retry.DefaultBackoff, func() error {
return u.updateConditions(ctx, cr, statusType, reason, message)
})

if err != nil {
reqLogger.Error(err, "Failed to update NVIDIADriver status after retries", "name", cr.Name)
}
return err
}
4 changes: 4 additions & 0 deletions vendor/k8s.io/client-go/util/retry/OWNERS
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

105 changes: 105 additions & 0 deletions vendor/k8s.io/client-go/util/retry/util.go
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

1 change: 1 addition & 0 deletions vendor/modules.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -989,6 +989,7 @@ k8s.io/client-go/util/flowcontrol
k8s.io/client-go/util/homedir
k8s.io/client-go/util/jsonpath
k8s.io/client-go/util/keyutil
k8s.io/client-go/util/retry
k8s.io/client-go/util/workqueue
# k8s.io/component-base v0.34.1
## explicit; go 1.24.0
Expand Down