kacerr/egress-proxies-operator
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

proxmox: review fixes, real-host validation record, changelog

Browse Source 
Phase 10. Two review passes (go-operator-reviewer, /code-review high)
over the branch, recorded in docs/reviews/2026-09-23-proxmox-provider-review/:
9 findings fixed, 3 accepted as documented limits, 7 rejected with a
reason.

- Delete removes the seed between the stop and the destroy, so a failed
  seed delete leaves the VM for the next Delete instead of leaking the
  ISO; a Permanent refusal on the every-node path fails the call.
- Create skips a probe VMID whose listed name is someone else's without
  waiting on its lock.
- The three answers Phase 0 never captured are fixtures now: a missing
  storage is a 400 (the Checker reports StorageNotFound), a hibernated
  VM is destroyable (Delete destroys ours), a paused VM stops.
- TestProxmox_lifecycle and TestProxmoxCheck_realHost passed on pv1-1
  (PVE 9.2.20); the docs record the run and drop "not yet run".

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
kacerr
2026-09-24 10:28:28 +00:00
co-authored by Claude Opus 5.5
parent 7f2073f94b
commit 3d72507894
28 changed files with 882 additions and 201 deletions
Download Patch File Download Diff File Expand all files Collapse all files
internal/provider/proxmox/delete_test.go
+62 -20
View File
@@ -203,6 +203,14 @@ func TestDelete_unmarkedLeavesVMAlone(t *testing.T) {
// wait for the stop fails.
func TestDelete_runningVMStoppedFirst(t *testing.T) {
t.Parallel()
// pv1-1 took a stop on a paused VM as a task that ended OK with the VM
// stopped (Phase 10 captures), which is what the fake does for all three.
accepted := readCapture(t, "stop_paused_response")
done := decodeData[taskStatus](t, "task_status_stop_paused")
after := decodeData[vmStatus](t, "status_current_after_stop_paused")
if accepted.Status != http.StatusOK || done.Type != "qmstop" || done.ExitStatus != "OK" || after.Status != "stopped" || after.QMPStatus != "stopped" {
t.Fatalf("captures = %d, %+v, %+v; want the stop accepted, OK, and the VM stopped", accepted.Status, done, after)
}
for _, qmp := range []string{"running", "paused", "prelaunch"} {
t.Run(qmp, func(t *testing.T) {
t.Parallel()
@@ -215,8 +223,8 @@ func TestDelete_runningVMStoppedFirst(t *testing.T) {
if stop < 0 || destroy < stop {
t.Fatalf("calls = %v, want Stop before Destroy", log)
}
if n := callsBefore(log[stop:], "TaskStatus", "Destroy"); n != fx.fake.taskPolls+1 {
t.Errorf("stop task polled %d times before Destroy, want %d", n, fx.fake.taskPolls+1)
if n := callsBefore(log[stop:], "TaskStatus", "DeleteVolume"); n != fx.fake.taskPolls+1 {
t.Errorf("stop task polled %d times before the seed delete, want %d", n, fx.fake.taskPolls+1)
}
if _, ok := fx.fake.vmSnapshot(testVMID); ok {
t.Error("VM still exists")
@@ -230,7 +238,7 @@ func TestDelete_stoppedVMSkipsStop(t *testing.T) {
fx := newFixture(t, 1)
fx.addOurVM(testVMID, testName, "stopped")
fx.delete()
want := []string{"ClusterResources", "VMConfig", "Destroy", "TaskStatus", "DeleteVolume", "TaskStatus"}
want := []string{"ClusterResources", "VMConfig", "DeleteVolume", "TaskStatus", "Destroy", "TaskStatus"}
if got := fx.fake.callLog(); !slices.Equal(got, want) {
t.Errorf("calls = %v, want %v", got, want)
}
@@ -291,26 +299,32 @@ func TestDelete_unknownStatusIsTransient(t *testing.T) {
}
}
// TestDelete_hibernatedVMIsPermanentIfOurs matches Create's ownership
// check: Destroy refuses the suspended lock, which never clears on its own,
// so an admin must act. A hibernated VM that is not ours is left alone.
func TestDelete_hibernatedVMIsPermanentIfOurs(t *testing.T) {
// TestDelete_hibernatedVMIsDestroyedIfOurs: on pv1-1 the destroy took a
// hibernated VM, suspend state volume included, and its task ended OK.
// Delete used to refuse it as Permanent on the belief that the destroy
// would. A hibernated VM that is not ours is still left alone.
func TestDelete_hibernatedVMIsDestroyedIfOurs(t *testing.T) {
t.Parallel()
t.Run("ours", func(t *testing.T) {
t.Parallel()
accepted := readCapture(t, "destroy_hibernated_response")
done := decodeData[taskStatus](t, "task_status_destroy_hibernated")
if accepted.Status != http.StatusOK || done.Type != "qmdestroy" || done.ExitStatus != "OK" {
t.Fatalf("captures = %d, %+v; want the destroy accepted and its task OK", accepted.Status, done)
}
fx := newFixture(t, 1)
fx.addOurVM(testVMID, testName, "stopped").lock = lockSuspended
fx.putSeed()
if msg := fx.deleteFails(provider.ErrPermanent); !strings.Contains(msg, "resume or destroy it in Proxmox") {
t.Errorf("error = %s, want the admin action", msg)
fx.delete()
want := []string{"ClusterResources", "VMConfig", "DeleteVolume", "TaskStatus", "Destroy", "TaskStatus"}
if got := fx.fake.callLog()[2:]; !slices.Equal(got, want) {
t.Errorf("calls = %v, want %v: no stop, since the VM is not running", got, want)
}
for _, method := range []string{"Stop", "Destroy", "DeleteVolume"} {
if n := fx.fake.callCount(method); n != 0 {
t.Errorf("%s calls = %d, want 0", method, n)
}
if _, ok := fx.fake.vmSnapshot(testVMID); ok {
t.Error("hibernated VM still exists")
}
if _, err := fx.fake.Destroy(fx.ctx, fakeNode, testVMID); !isLocked(err) {
t.Errorf("fake Destroy on the hibernated VM error = %v, want the lock answer", err)
if fx.seedPresent() {
t.Error("seed still exists")
}
})
t.Run("someone else's", func(t *testing.T) {
@@ -367,7 +381,7 @@ func TestDelete_seedDeleteIsTaskAndIdempotent(t *testing.T) {
for log[last] != "DeleteVolume" {
last--
}
if n := callsBefore(log[last:], "TaskStatus", ""); n != fx.fake.taskPolls+1 {
if n := callsBefore(log[last:], "TaskStatus", "Destroy"); n != fx.fake.taskPolls+1 {
t.Errorf("seed delete task polled %d times, want %d: %v", n, fx.fake.taskPolls+1, log)
}
if fx.seedPresent() {
@@ -377,6 +391,9 @@ func TestDelete_seedDeleteIsTaskAndIdempotent(t *testing.T) {
}
}
// TestDelete_seedDeleteFailureOnVMNodeFails: the VM outlives a failed seed
// delete, so Get keeps finding it and the next Delete finishes the job with
// the same class of answer (review findings CR1, CR2, P1).
func TestDelete_seedDeleteFailureOnVMNodeFails(t *testing.T) {
t.Parallel()
tests := []struct {
@@ -403,9 +420,22 @@ func TestDelete_seedDeleteFailureOnVMNodeFails(t *testing.T) {
fx := newFixture(t, 1)
fx.addOurVM(testVMID, testName, "stopped")
tc.setup(fx)
fx.putSeed()
fx.deleteFails(tc.class)
if n := fx.fake.callCount("Destroy"); n != 0 {
t.Errorf("Destroy calls = %d, want 0 while the seed is still there", n)
}
if _, err := fx.p.Get(fx.ctx, fx.id()); errors.Is(err, provider.ErrNotFound) {
t.Fatalf("Get = %v, want the VM still found so Delete runs again", err)
}
fx.deleteFails(tc.class)
fx.fake.clearHooks()
fx.delete()
if _, ok := fx.fake.vmSnapshot(testVMID); ok {
t.Error("VM still exists: the destroy should have run before the seed delete")
t.Error("VM still exists after the retry")
}
if fx.seedPresent() {
t.Error("seed still exists after the retry")
}
})
}
@@ -436,6 +466,18 @@ func TestDelete_seedDeleteNodeFailureSkippedWhenNodeUnknown(t *testing.T) {
t.Error("seed still exists after pv1-2's delete")
}
})
t.Run("a refused privilege fails the call", func(t *testing.T) {
t.Parallel()
fx := twoNodeFixture(t)
fx.putSeed()
fx.fake.failWith("DeleteVolume", loadAPIError(t, "err_forbidden_volume_delete"))
if msg := fx.deleteFails(provider.ErrPermanent); !strings.Contains(msg, "Datastore.Allocate") {
t.Errorf("error = %s, want the missing privilege named", msg)
}
if n := fx.fake.callCount("DeleteVolume"); n != 1 {
t.Errorf("DeleteVolume calls = %d, want 1: every node would refuse the same", n)
}
})
t.Run("ended ctx fails the call", func(t *testing.T) {
t.Parallel()
fx := twoNodeFixture(t)
@@ -465,8 +507,8 @@ func TestDelete_destroyTaskFailureIsTransient(t *testing.T) {
if _, ok := fx.fake.vmSnapshot(testVMID); !ok {
t.Error("VM gone after a failed destroy task")
}
if !fx.seedPresent() {
t.Error("seed deleted although the VM is still there")
if fx.seedPresent() {
t.Error("seed still exists: it goes before the destroy")
}
if lines := fx.logs.matching(`"msg"="proxmox task failed"`); len(lines) != 1 {
t.Errorf("task failed lines = %v, want one", lines)
@@ -485,7 +527,7 @@ func TestDelete_goneMidwayIsSuccess(t *testing.T) {
wantNodes []string
}{
{name: "before the config read", status: "stopped", method: "VMConfig", wantNodes: []string{fakeNode, "pv1-2"}},
{name: "before the stop", status: "running", method: "Stop", wantNodes: []string{fakeNode}},
{name: "before the stop", status: "running", method: "Stop", wantDestroy: 1, wantNodes: []string{fakeNode}},
{name: "before the destroy", status: "stopped", method: "Destroy", wantDestroy: 1, wantNodes: []string{fakeNode}},
}
for _, tc := range tests {