admin
6545cccff7
gates / gates (push) Successful in 48s
v0.159.0/v0.159.1 ran the check before every snapshot-mode whole-guest backup, which takes a metadata snapshot of the live pool. Now explainFailure (vzdump start or task failure) is its only caller; the finding is still appended to the failed backup's error. Tests: failure = 1 call, success = 0 calls; red-proved against the v0.159.1 runner.go (2 calls / calls=1). Claude-Session: https://claude.ai/code/session_0159rPz1ZhFKsS53msqPYxtS
68 lines
3.1 KiB
Go
68 lines
3.1 KiB
Go
package backup
|
|
|
|
import (
|
|
"context"
|
|
"errors"
|
|
"strings"
|
|
"testing"
|
|
|
|
"gitea.dooplex.hu/admin/felhom-agent/internal/proxmox"
|
|
)
|
|
|
|
// R-1012: a snapshot backup that fails carries the orphan finding in its error — the text the controller mails to
|
|
// the operator (`whole_guest_backup_failed`). The check runs ONCE, after the failure — never before the run.
|
|
// RED-PROOF (P1/redproof-thincheck.txt): with explainFailure's append removed this test fails. RED-PROOF (2026-10-17
|
|
// night, felhom-agent REPORT.md): with the v0.159.0 pre-run check restored, calls = 2 and this test fails.
|
|
func TestBackup_SnapshotFailure_NamesTheOrphan(t *testing.T) {
|
|
const why = "probable cause: thin pool pve/data holds device 4 that LVM does not know"
|
|
for name, api := range map[string]*fakeBackupAPI{
|
|
"task fails": {vzdumpUPID: "UPID:x", waitErr: errors.New("task failed: job errors")},
|
|
"start fails": {vzdumpErr: errors.New("vzdump: 500")},
|
|
} {
|
|
t.Run(name, func(t *testing.T) {
|
|
r := NewBackupRunner(api, "local", "", "", "", quiet())
|
|
calls := 0
|
|
r.SetThinCheck(func(context.Context, int) string { calls++; return why })
|
|
rec, err := r.Backup(context.Background(), 9201)
|
|
if err == nil || rec.Success {
|
|
t.Fatalf("want a failure, got %+v", rec)
|
|
}
|
|
if !strings.Contains(rec.Error, why) {
|
|
t.Fatalf("the failure does not name the orphan: %q", rec.Error)
|
|
}
|
|
if calls != 1 {
|
|
t.Fatalf("thin check ran %d times, want 1 (after the failure only)", calls)
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
// A successful backup never runs the check (it takes a metadata snapshot of the live pool, and nobody needs the answer)
|
|
// and keeps a clean record; a stop-mode backup takes no snapshot, so the check never runs; an unwired runner behaves
|
|
// exactly as before. RED-PROOF (2026-10-17 night): with the v0.159.0 pre-run check restored, the success leg fails
|
|
// with calls=1.
|
|
func TestBackup_ThinCheck_SilentWhenNotApplicable(t *testing.T) {
|
|
ok := &fakeBackupAPI{vzdumpUPID: "UPID:x",
|
|
content: []proxmox.StorageContent{{VolID: "local:backup/vzdump-lxc-9201-x", Content: "backup", VMID: 9201, Size: 100, CTime: 1}}}
|
|
r := NewBackupRunner(ok, "local", "", "", "", quiet())
|
|
calls := 0
|
|
r.SetThinCheck(func(context.Context, int) string { calls++; return "probable cause: x" })
|
|
rec, err := r.Backup(context.Background(), 9201)
|
|
if err != nil || !rec.Success || rec.Error != "" || calls != 0 {
|
|
t.Fatalf("success: err=%v rec=%+v calls=%d (want no check on a successful backup, clean record)", err, rec, calls)
|
|
}
|
|
|
|
stop := NewBackupRunner(&fakeBackupAPI{vzdumpUPID: "UPID:x", waitErr: errors.New("boom")}, "local", proxmox.ModeStop, "", "", quiet())
|
|
calls = 0
|
|
stop.SetThinCheck(func(context.Context, int) string { calls++; return "probable cause: x" })
|
|
rec, _ = stop.Backup(context.Background(), 9201)
|
|
if calls != 0 || strings.Contains(rec.Error, "probable cause") {
|
|
t.Fatalf("stop mode: calls=%d error=%q", calls, rec.Error)
|
|
}
|
|
|
|
plain := NewBackupRunner(&fakeBackupAPI{vzdumpUPID: "UPID:x", waitErr: errors.New("boom")}, "local", "", "", "", quiet())
|
|
if rec, _ := plain.Backup(context.Background(), 9201); rec.Error != "boom" {
|
|
t.Fatalf("unwired: error = %q, want the task error unchanged", rec.Error)
|
|
}
|
|
}
|