Skip to content

platformd: fix multiple reconciliations of ongoing operation #210

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
freggy merged 1 commit into from
Mar 29, 2026
Merged

platformd: fix multiple reconciliations of ongoing operation #210

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
2 changes: 1 addition & 1 deletion platformd/checkpoint/service.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -393,7 +393,7 @@ func (s *ServiceImpl) podConfig(id string) *runtimev1.PodSandboxConfig {
func (s *ServiceImpl) ctrConfig(checkID string, baseImgURL string) *runtimev1.ContainerConfig {
return &runtimev1.ContainerConfig{
Metadata: &runtimev1.ContainerMetadata{
Name: "payload",
Name: "payload_" + checkID,
},
Image: &runtimev1.ImageSpec{
UserSpecifiedImage: baseImgURL,
Expand Down
26 changes: 13 additions & 13 deletions platformd/reconciler.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@ import (
"log/slog"
"maps"
"strconv"
"sync"
"time"

instancev1alpha1 "github.com/spacechunks/explorer/api/instance/v1alpha1"
Expand Down Expand Up @@ -139,10 +140,18 @@ func (r *reconciler) tick(ctx context.Context) {
return
}

var wg sync.WaitGroup

for _, ins := range discResp.Instances {
go r.reconcile(ctx, ins)
wg.Add(1)
go func() {
r.reconcile(ctx, ins)
wg.Done()
}()
}

wg.Wait()

var (
statuses = r.store.View()
items = make([]*instancev1alpha1.InstanceStatusReport, 0, len(statuses))
Expand Down Expand Up @@ -238,14 +247,12 @@ func (r *reconciler) reconcile(ctx context.Context, ins *instancev1alpha1.Instan
}
}

func (r *reconciler) handleInstanceCreation(ctx context.Context, instance *instancev1alpha1.Instance) error {
func (r *reconciler) handleInstanceCreation(ctx context.Context, instance *instancev1alpha1.Instance) (reterr error) {
var (
id = instance.GetId()
attempt = r.attempts[id]
)

r.logger.InfoContext(ctx, "handling pending instance", "instance_id", id, "attempt", attempt)

// if the instance is not in state CREATING, skip it.
// this check is necessary, because it can happen that we
// receive an instance that is still in PENDING state from the
Expand All @@ -256,18 +263,11 @@ func (r *reconciler) handleInstanceCreation(ctx context.Context, instance *insta
if st := r.store.Get(id); st != nil &&
st.WorkloadStatus != nil &&
st.WorkloadStatus.State != status.WorkloadStateCreating {
r.logger.InfoContext(ctx, "skip", "instance_id", id)
r.logger.InfoContext(ctx, "instance currently creating, skip", "instance_id", id)
return nil
}

if attempt >= r.cfg.MaxAttempts {
r.store.Update(id, status.Status{
WorkloadStatus: &status.WorkloadStatus{
State: status.WorkloadStateCreationFailed,
},
})
return errMaxAttemptsReached
}
r.logger.InfoContext(ctx, "handling pending instance", "instance_id", id, "attempt", attempt)

attempt++

Expand Down
Loading