agent: the restore test proves only backups of a guest (R-689)
gates / gates (push) Successful in 13s

The golden template in local:backup/ was picked as the newest settled archive on demo-hp and
failed every 6 h. Candidates are now vzdump-<type>-<vmid> files or PBS ct|vm/<vmid> snapshots
with a reported vmid. Red-proofed.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0159rPz1ZhFKsS53msqPYxtS
This commit is contained in:
2026-09-27 12:15:42 +02:00
parent 7403c2a838
commit d4be12ca95
3 changed files with 115 additions and 6 deletions
+52
View File
@@ -5,6 +5,7 @@ import (
"fmt"
"log/slog"
"sort"
"strconv"
"strings"
"sync"
"time"
@@ -362,6 +363,14 @@ func (r *BackupRunner) PickSettledRestoreCandidateOn(ctx context.Context, target
if e.Content != "backup" {
continue
}
// R-689 (v0.135.0): only a backup OF A GUEST is a restore-test candidate. demo-hp keeps its golden
// template in `local:backup/` — content "backup", 654 MB, plausibly complete — and it was picked as
// the newest settled archive every 6 h and failed extractconfig (403) each time, while the guest's
// real archive went untested.
if ok, why := guestBackupArchive(e); !ok {
r.noteNotAGuestBackupOnce(e, why)
continue
}
if !notAfter.IsZero() && e.CTime > notAfter.Unix() {
continue // not settled yet — a newer archive is not a reason to re-prove an older one
}
@@ -591,3 +600,46 @@ func ToHubRestoreTest(res reconcile.RestoreTestResult, testedAt time.Time) hub.R
}
return rt
}
// guestBackupArchive reports whether a storage entry is a whole-guest backup of a known guest — a
// `vzdump-<type>-<vmid>-…` file on a dir storage, or a `backup/{ct,vm}/<vmid>/<time>` snapshot on a PBS
// datastore — whose vmid the storage itself reports. Anything else in a backup content type (a golden
// template, a hand-copied tarball) is not a backup of a guest and is never restore-tested (R-689).
// Pure, so the rule is unit-tested without a storage.
func guestBackupArchive(e proxmox.StorageContent) (bool, string) {
if e.VMID <= 0 {
return false, "not a backup of a guest (the storage reports no vmid)"
}
vol := e.VolID
if i := strings.Index(vol, ":"); i >= 0 {
vol = vol[i+1:]
}
vol = strings.TrimPrefix(vol, "backup/")
vmid := strconv.Itoa(e.VMID)
switch {
case strings.HasPrefix(vol, "vzdump-lxc-"+vmid+"-"), strings.HasPrefix(vol, "vzdump-qemu-"+vmid+"-"):
return true, ""
case strings.HasPrefix(vol, "ct/"+vmid+"/"), strings.HasPrefix(vol, "vm/"+vmid+"/"):
return true, ""
}
return false, "not a vzdump archive or a PBS snapshot of guest " + vmid
}
// noteNotAGuestBackupOnce logs, once per volid, that a backup-content entry is not a restore-test
// candidate because it is not a backup of a guest (R-689). INFO, not WARN: a golden template kept in
// the backup directory is the operator's, and not a fault.
func (r *BackupRunner) noteNotAGuestBackupOnce(e proxmox.StorageContent, why string) {
r.rejectedMu.Lock()
if r.rejected == nil {
r.rejected = map[string]struct{}{}
}
_, seen := r.rejected[e.VolID]
if !seen {
r.rejected[e.VolID] = struct{}{}
}
r.rejectedMu.Unlock()
if !seen {
r.logger.Info("backup: restore-test skips an entry that is not a backup of a guest",
"target", r.target, "volid", e.VolID, "size_bytes", e.Size, "reason", why)
}
}