Files
felhom-controller/controller/internal/backup/opstatus.go
T

108 lines
4.7 KiB
Go

package backup
import "time"
// Restore op-status (Part B): a lightweight, in-memory surface for the ASYNC restore family so the
// backups page can show a progress banner (running → success/failure) instead of blocking the HTTP
// request until the restore completes. It is display-only and mutex-guarded on the Manager's `mu`;
// it does NOT gate concurrency (that stays the restore functions' internal single-flight acquire).
// PERSISTED since v0.246.0 (R-550, operator ruling 2026-09-17 — a reversal of the original in-memory
// choice, for the restore record only; notification cooldowns stay in memory). See restore_record.go.
// RestoreOpResult is the terminal record of the most recent restore op.
type RestoreOpResult struct {
Op string `json:"op"` // "restore" | "tier2-restore" | "offbox-restore"
Stack string `json:"stack"`
OK bool `json:"ok"`
Message string `json:"message"`
FinishedAt time.Time `json:"finished_at"`
// Interrupted marks a restore that was still in flight when the controller stopped (R-550): found
// at the next start, recorded as a failure with RestoreInterruptedMessage.
Interrupted bool `json:"interrupted,omitempty"`
// PutBack marks an interrupted restore that the start-up put the data back for (D22, R-1195): the message then
// says the app's data is as it was before the restore, not „start it again".
PutBack bool `json:"put_back,omitempty"`
}
// RestoreResultWindow bounds how long a finished restore still counts as "what just happened".
//
// ONE EXPRESSION, TWO SURFACES (R-351). The wizard's phase strip and the list page's banner both
// need this bound, and until now only the wizard had one — it lived in internal/web as an
// unexported constant. A second copy in the JS would be exactly the "two copies that already
// differed" shape this repo keeps paying for, so the window is defined HERE, beside the status it
// bounds, and both surfaces read it from the payload.
const RestoreResultWindow = 10 * time.Minute
// RestoreOpStatus is the shape served at GET /api/backup/restore-status.
type RestoreOpStatus struct {
Running bool `json:"running"`
Op string `json:"op,omitempty"`
Stack string `json:"stack,omitempty"`
StartedAt time.Time `json:"started_at,omitempty"`
Last *RestoreOpResult `json:"last,omitempty"`
// LastRecent reports whether Last finished recently enough to still be worth showing to someone
// who was NOT watching when it happened.
//
// R-351, the measured defect: the banner's JS gated the terminal result on a page-local
// `sawRunning` flag, so a restore that finished before the page was opened — or in under one
// poll interval — was shown to nobody. The 2026-08-21 OpenGist restore finished in 8.7s and the
// operator could not tell from any screen whether it had completed; the answer existed only in
// a container log. A result nobody can see is the same defect class as no result at all.
LastRecent bool `json:"last_recent,omitempty"`
}
// BeginRestoreOp marks a restore op in flight (called by the handler just before launching the
// background goroutine). Idempotent enough for display; concurrency is enforced elsewhere.
func (m *Manager) BeginRestoreOp(op, stack string) {
m.mu.Lock()
defer m.mu.Unlock()
m.opRunning = true
m.opName = op
m.opStack = stack
m.opStartedAt = time.Now()
// A new restore of this app supersedes its interrupted notice (R-550).
delete(m.opInterrupted, stack)
m.persistRestoreRecordLocked()
}
// EndRestoreOp records the terminal result (called from the goroutine on completion, success or
// failure). Message carries the error (failure) or a human note like the scratch path (offbox).
func (m *Manager) EndRestoreOp(ok bool, message string) {
m.mu.Lock()
defer m.mu.Unlock()
m.opLast = &RestoreOpResult{
Op: m.opName,
Stack: m.opStack,
OK: ok,
Message: message,
FinishedAt: time.Now(),
}
m.opRunning = false
m.persistRestoreRecordLocked()
}
// RestoreStatus returns a deep copy of the current restore op-status for the page/API.
func (m *Manager) RestoreStatus() RestoreOpStatus {
m.mu.Lock()
defer m.mu.Unlock()
st := RestoreOpStatus{
Running: m.opRunning,
Op: m.opName,
Stack: m.opStack,
StartedAt: m.opStartedAt,
}
if m.opLast != nil {
cp := *m.opLast
st.Last = &cp
// Recency is decided here, on the clock the result was stamped with, so neither surface has
// to hold its own copy of the window. A zero FinishedAt is never recent — an unstamped
// result must not be drawn as "just now".
if !cp.FinishedAt.IsZero() {
if d := time.Since(cp.FinishedAt); d >= 0 && d < RestoreResultWindow {
st.LastRecent = true
}
}
}
return st
}