Let a Proxy finish deleting when its instance can no longer be reached
reconcileDelete asked Get first and dropped the finalizer only on not-found, so a permanent Get retried forever: a KVM host removed from the config, or a providerID the provider cannot resolve, left the Proxy in Terminating with no way out. It now tries Delete anyway, which is idempotent and can still finish where Get cannot converge, and releases the object when that succeeds. crawl.example.com/skip-cleanup abandons the instance for the cases that stay stuck, such as revoked credentials. It is checked before the provider lookup, so it also frees a Proxy whose provider is gone from the config. In the KVM provider, Delete over an unconfigured host is now a no-op success, mirroring removeVolumes over a missing pool. Get keeps failing permanently there on purpose: the live path reads not-found as "rebuild it", so a typo in hosts must not look like a missing VM. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -451,7 +451,8 @@ func mapState(s libvirt.DomainState, ip string) provider.InstanceState {
|
||||
// domain is not destroyed again, a missing domain is not undefined, and
|
||||
// the per-VM volumes are removed by name even when the domain is already
|
||||
// gone, so a crash between volume creation and define is cleaned up on the
|
||||
// next reconcile.
|
||||
// next reconcile. A providerID naming a host that is no longer configured
|
||||
// is a no-op success rather than an error.
|
||||
func (p *Provider) Delete(ctx context.Context, providerID string) error {
|
||||
hostName, name, err := parseProviderID(providerID)
|
||||
if err != nil {
|
||||
@@ -459,7 +460,14 @@ func (p *Provider) Delete(ctx context.Context, providerID string) error {
|
||||
}
|
||||
host, err := p.host(hostName)
|
||||
if err != nil {
|
||||
return p.wrapErr("delete", providerID, err)
|
||||
// The host is no longer configured, so this operator has no way to
|
||||
// reach the domain and nothing left to clean. Same reasoning as
|
||||
// removeVolumes over a missing pool: refusing would pin the Proxy's
|
||||
// finalizer. Whatever is still running there is the admin's to remove,
|
||||
// and orphan GC cannot see it either — see docs/kvm-provider.md.
|
||||
p.logger(ctx).Info("host is not configured; delete has nothing to clean up",
|
||||
"host", hostName, "providerID", providerID)
|
||||
return nil
|
||||
}
|
||||
log := p.logger(ctx).WithValues("host", host.Name, "name", name)
|
||||
err = p.hosts.call(ctx, log, host, func(api libvirtAPI) error {
|
||||
|
||||
@@ -726,6 +726,29 @@ func TestDelete_missingPoolIsNotAnError(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// A host dropped from the config leaves the operator no way to reach the
|
||||
// domain, so Delete has nothing left to clean. Failing instead would pin
|
||||
// the Proxy's finalizer forever, since the reconciler's delete path cannot
|
||||
// make progress without a Delete that can succeed.
|
||||
func TestDelete_unconfiguredHostIsNotAnError(t *testing.T) {
|
||||
t.Parallel()
|
||||
api := readyHost()
|
||||
managedDomain(t, api, testName, testUID, true, nil)
|
||||
p := newTestProvider(hostFakes{"nas1": api}, "nas1")
|
||||
|
||||
if err := p.Delete(context.Background(), "hosts/nas9/domains/"+testName); err != nil {
|
||||
t.Fatalf("Delete over an unconfigured host: %v", err)
|
||||
}
|
||||
if api.domain(testName) == nil {
|
||||
t.Error("domain on the configured host was touched; only the named host's state may change")
|
||||
}
|
||||
// Get still refuses, so the live path cannot mistake a config typo for a
|
||||
// missing VM and recreate it somewhere else.
|
||||
if _, err := p.Get(context.Background(), "hosts/nas9/domains/"+testName); provider.Class(err) != provider.ErrPermanent {
|
||||
t.Errorf("Get class = %v, want ErrPermanent", provider.Class(err))
|
||||
}
|
||||
}
|
||||
|
||||
func TestDelete_errors(t *testing.T) {
|
||||
t.Parallel()
|
||||
cases := []struct {
|
||||
@@ -735,7 +758,6 @@ func TestDelete_errors(t *testing.T) {
|
||||
class error
|
||||
}{
|
||||
{"malformed id", "nope", func(*testing.T) hostFakes { return hostFakes{"nas1": readyHost()} }, provider.ErrPermanent},
|
||||
{"host not configured", "hosts/nas9/domains/x", func(*testing.T) hostFakes { return hostFakes{"nas1": readyHost()} }, provider.ErrPermanent},
|
||||
{"host unreachable", "hosts/nas1/domains/x", func(*testing.T) hostFakes { return hostFakes{} }, provider.ErrTransient},
|
||||
{
|
||||
"undefine fails", "hosts/nas1/domains/" + testName,
|
||||
|
||||
Reference in New Issue
Block a user