25e5cb5850
Sub-cause: on guest pct reboot, in-guest dockerd auto-starts unless-stopped drive-backed apps ~18s BEFORE the agent re-binds the drive; the create-time volume bind fails (mkdir /mnt/felhom-drives/<drive>/userdata: permission denied) and RestartCount=0 means it's never retried -> stuck Exited. The existing recovery (processGuestBootChange) RAN but raced the rebind: it sampled the agent's BoundUnderParent once during fast startup (not live yet), recreated nothing, and persisted the new boot-id -> burned its one-shot. The periodic gate never recovered them either (first observation after the rebind -> no transition). Fix (harden the existing mechanism, no parallel one): processGuestBootChange now gates on the REAL live in-guest bind. driveBindLive checks whether /mnt/felhom-drives/<drive> is an actual mountpoint in the controller's own /mnt (rslave) /proc/self/mountinfo -- true only once the agent's bind propagated, exactly when docker can recreate the app. pollLiveBinds waits for that (bounded ~120s, poll 2s; rebind lands ~18s) and only then recreates via the normal pipeline, including stuck-Exited create-time-failure apps (shouldRecreateOnBoot is state-independent). Single-flight; absent-after-window drives left to the gate; host-reboot path unaffected; guest-only reboot path now covered. Tests: pollLiveBinds waits through the rebind then reports live (recreate fires); never-live drive stays absent; pre-fix companion (single early sample misses the not-yet-live bind). Red-proofed against a no-wait single-sample. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
495 lines
21 KiB
Go
495 lines
21 KiB
Go
package web
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"net/http"
|
|
"os"
|
|
"path"
|
|
"strings"
|
|
"time"
|
|
|
|
"gitea.dooplex.hu/admin/felhom-controller/internal/agentapi"
|
|
"gitea.dooplex.hu/admin/felhom-controller/internal/settings"
|
|
)
|
|
|
|
// bootBindWait / bootBindPoll bound the readiness gate in processGuestBootChange. On a guest reboot
|
|
// the agent re-binds each drive under the stable parent ~18s after boot (well after docker has tried
|
|
// and permanently failed to auto-start the drive-backed apps); the wait must comfortably cover that
|
|
// with margin, the poll be cheap.
|
|
const (
|
|
bootBindWait = 120 * time.Second
|
|
bootBindPoll = 2 * time.Second
|
|
)
|
|
|
|
// driveBindLive reports whether `root` (a /mnt/felhom-drives/<name> stable path) is a REAL live
|
|
// mountpoint in this process's own mount namespace — i.e. the agent's per-drive bind has actually
|
|
// propagated into the controller's `/mnt` (rslave) view, which is exactly the moment docker can
|
|
// (re)create an app whose volume binds under it. It reads /proc/self/mountinfo (pure Go, no syscall;
|
|
// the mount point is always field index 4). Before the agent re-binds the drive post-boot, the stable
|
|
// path is the empty fail-closed placeholder (a plain subdir of the parent, NOT its own mount) → false.
|
|
// This is the load-bearing signal the old code lacked: it sampled the agent's host-side
|
|
// BoundUnderParent ONCE during fast controller startup, racing the ~18s rebind.
|
|
func driveBindLive(root string) bool {
|
|
data, err := os.ReadFile("/proc/self/mountinfo")
|
|
if err != nil {
|
|
return false
|
|
}
|
|
for _, line := range strings.Split(string(data), "\n") {
|
|
f := strings.Fields(line)
|
|
if len(f) >= 5 && f[4] == root {
|
|
return true
|
|
}
|
|
}
|
|
return false
|
|
}
|
|
|
|
// pollLiveBinds waits (bounded by `wait`, polling every `poll`) for each path's drive bind to go LIVE,
|
|
// returning the final liveness map. It breaks early once every path is live. bindLive/sleep/now are
|
|
// injected so the readiness gate is deterministically unit-testable. A path that never goes live
|
|
// within the window stays false (its apps are left to the normal drive gate).
|
|
func pollLiveBinds(paths []string, bindLive func(string) bool, sleep func(time.Duration), now func() time.Time, wait, poll time.Duration) map[string]bool {
|
|
live := make(map[string]bool, len(paths))
|
|
deadline := now().Add(wait)
|
|
for {
|
|
all := true
|
|
for _, p := range paths {
|
|
if live[p] {
|
|
continue
|
|
}
|
|
if bindLive(p) {
|
|
live[p] = true
|
|
} else {
|
|
all = false
|
|
}
|
|
}
|
|
if all || !now().Before(deadline) {
|
|
return live
|
|
}
|
|
sleep(poll)
|
|
}
|
|
}
|
|
|
|
// Intermediary-mount model (controller side). Post-migration a drive is visible in the guest ONLY at its
|
|
// STABLE path /mnt/felhom-drives/<name> (the host swaps the backing drive underneath it; see the agent's
|
|
// internal/localapi/intermediary.go + SPIKE-intermediary-mount). So:
|
|
// - the REGISTERED storage path + every app's HDD_PATH + FileBrowser source = the STABLE path;
|
|
// - the AGENT still operates on the RAW /mnt/<name> host PVE mount (assign/attach/eject/decommission),
|
|
// so controller→agent `where` is mapped back to raw via agentWhere().
|
|
// The drive-absent GATE stops + blocks apps when their drive vanishes and auto-restarts them when it
|
|
// returns (host-side, no guest reboot).
|
|
|
|
// StableParentDir is the permanent in-guest parent the agent binds drives under (mirrors
|
|
// localapi.StableParentDir).
|
|
const StableParentDir = "/mnt/felhom-drives"
|
|
|
|
// stablePathForName maps a drive name to its registered stable in-guest path.
|
|
func stablePathForName(name string) string { return StableParentDir + "/" + name }
|
|
|
|
// agentWhere maps a registered storage path — stable /mnt/felhom-drives/<name> OR a legacy raw /mnt/<name>
|
|
// — to the RAW /mnt/<name> host mount the agent operates on. Idempotent for an already-raw path
|
|
// (path.Base drops the directory either way).
|
|
func agentWhere(registeredPath string) string {
|
|
name := path.Base(strings.TrimRight(registeredPath, "/"))
|
|
if name == "" || name == "." || name == "/" {
|
|
return registeredPath
|
|
}
|
|
return "/mnt/" + name
|
|
}
|
|
|
|
// shouldRecreateOnBoot is the PURE decision for the boot-id recreate: on a fresh guest boot, recreate
|
|
// EVERY deployed drive-backed app whose drive is present (BoundUnderParent) onto its (re-propagated)
|
|
// drive. It is DETERMINISTIC — it depends ONLY on `app.yaml says should run` (deployed) + drive-present,
|
|
// NOT on the app's current container state. The current state must NOT be a filter: a momentarily-stopped
|
|
// app on a fresh reboot (docker hasn't auto-restarted it yet) would otherwise be MISSED — the exact bug
|
|
// the boot-id path replaces (the old container-uptime sample, and a State!=stopped filter, both miss it).
|
|
// (Tradeoff: a UI-stopped drive-backed app is brought back on a guest reboot — `deployed` is the only
|
|
// "should run" signal app.yaml carries; the gate manages drive-backed app lifecycle otherwise.)
|
|
func shouldRecreateOnBoot(deployed bool, hdd string, presentStable map[string]bool) bool {
|
|
return deployed && hdd != "" && strings.HasPrefix(hdd, StableParentDir+"/") && presentStable[hdd]
|
|
}
|
|
|
|
// defaultPromotionTarget decides M1 (never leave zero default). If the path being decommissioned is NOT
|
|
// the current default → ("", false): nothing to do. If it IS the default → pick a promotion target from
|
|
// the OTHER schedulable, non-decommissioned paths (preferring `migratedTo` — the migrate-then-decommission
|
|
// target — when valid); ("", true) = MUST BLOCK (no other usable drive exists). Pure → unit-testable.
|
|
func defaultPromotionTarget(paths []settings.StoragePath, decommissioning, migratedTo string) (target string, mustBlock bool) {
|
|
isDefault := false
|
|
for _, sp := range paths {
|
|
if sp.Path == decommissioning && sp.IsDefault {
|
|
isDefault = true
|
|
}
|
|
}
|
|
if !isDefault {
|
|
return "", false
|
|
}
|
|
usable := func(p string) bool {
|
|
for _, sp := range paths {
|
|
if sp.Path == p && sp.Path != decommissioning && sp.Schedulable && !sp.Decommissioned {
|
|
return true
|
|
}
|
|
}
|
|
return false
|
|
}
|
|
if migratedTo != "" && usable(migratedTo) {
|
|
return migratedTo, false
|
|
}
|
|
for _, sp := range paths {
|
|
if sp.Path != decommissioning && sp.Schedulable && !sp.Decommissioned {
|
|
return sp.Path, false
|
|
}
|
|
}
|
|
return "", true // no other usable drive → block the decommission
|
|
}
|
|
|
|
// appsOnStoragePath returns the deployed stack names whose HDD_PATH equals the given (stable) storage
|
|
// path — the apps that depend on that drive.
|
|
func (s *Server) appsOnStoragePath(storagePath string) []string {
|
|
var names []string
|
|
for _, st := range s.stackMgr.GetStacks() {
|
|
if cfg := s.stackMgr.LoadAppConfigByName(st.Name); cfg != nil && cfg.Env["HDD_PATH"] == storagePath {
|
|
names = append(names, st.Name)
|
|
}
|
|
}
|
|
return names
|
|
}
|
|
|
|
// stopAppsOnPath stops every deployed app on the given storage path and returns their names (the
|
|
// gate-stopped set — distinct from a user stop, which never enters this set). Best-effort per app.
|
|
func (s *Server) stopAppsOnPath(storagePath string) []string {
|
|
var stopped []string
|
|
for _, name := range s.appsOnStoragePath(storagePath) {
|
|
if err := s.stackMgr.StopStack(name); err != nil {
|
|
s.logger.Printf("[WARN] [gate] stop %s on absent %s: %v", name, storagePath, err)
|
|
continue
|
|
}
|
|
stopped = append(stopped, name)
|
|
}
|
|
return stopped
|
|
}
|
|
|
|
// restartStacks starts each named stack (the gate-stopped set on drive return). Best-effort per app.
|
|
func (s *Server) restartStacks(names []string) {
|
|
for _, name := range names {
|
|
if err := s.stackMgr.StartStack(name); err != nil {
|
|
s.logger.Printf("[WARN] [gate] restart %s: %v", name, err)
|
|
}
|
|
}
|
|
}
|
|
|
|
// gateAction is the reconcile's decision for one registered storage path.
|
|
type gateAction struct {
|
|
Path string
|
|
Stop bool // drive ABSENT + not yet marked → stop apps, mark disconnected
|
|
Return bool // drive RETURNED (present + currently disconnected) → re-attach, restart, clear
|
|
Raw string // raw /mnt/<name> for the re-attach
|
|
}
|
|
|
|
// planDriveGates is the PURE decision core: given the registry + the agent's disk list, decide per path
|
|
// whether to gate (stop) or un-gate (return). A drive is "present" iff a disk with a matching GuestPath
|
|
// (stable) or MountPath (legacy raw) is State=="attached". Decommissioned paths are skipped (handled by
|
|
// the decommission flow, not the transient gate). No side effects → unit-testable.
|
|
func planDriveGates(paths []settings.StoragePath, disks []agentapi.DiskInfo) []gateAction {
|
|
present := map[string]bool{}
|
|
rawByPath := map[string]string{}
|
|
for _, d := range disks {
|
|
// A STABLE path is usable only when the drive's felhom-data is actually BOUND UNDER THE PARENT
|
|
// (BoundUnderParent) — NOT merely when the raw drive is host-mounted (State==attached). This is
|
|
// what makes the gate converge a reboot correctly: at boot the raw drive mounts early but the
|
|
// agent binds it under the parent slightly later; until then the apps' stable-path binds are empty,
|
|
// so the gate keeps them stopped and restarts (recreates) them once the bind is live.
|
|
if d.GuestPath != "" {
|
|
present[d.GuestPath] = present[d.GuestPath] || d.BoundUnderParent
|
|
rawByPath[d.GuestPath] = d.MountPath
|
|
}
|
|
if d.MountPath != "" { // legacy raw path registered directly — host mount is the usable signal
|
|
present[d.MountPath] = present[d.MountPath] || d.State == "attached"
|
|
rawByPath[d.MountPath] = d.MountPath
|
|
}
|
|
}
|
|
var actions []gateAction
|
|
for _, sp := range paths {
|
|
if sp.Decommissioned {
|
|
continue
|
|
}
|
|
// ONLY gate EXTERNAL drives — those registered under the stable parent /mnt/felhom-drives/<name>.
|
|
// Internal SSD / system paths (e.g. /mnt/sys_drive/felhom-data) are always-present locals the agent
|
|
// never reports as drives; gating them on "absence" would falsely stop/block their apps. (Legacy
|
|
// raw /mnt/<name> external paths are present via the agent's MountPath during the transition and get
|
|
// repointed under the parent by the migration.)
|
|
if !strings.HasPrefix(sp.Path, StableParentDir+"/") {
|
|
continue
|
|
}
|
|
switch {
|
|
case !present[sp.Path] && !sp.Disconnected:
|
|
actions = append(actions, gateAction{Path: sp.Path, Stop: true})
|
|
case present[sp.Path] && sp.Disconnected:
|
|
actions = append(actions, gateAction{Path: sp.Path, Return: true, Raw: rawByPath[sp.Path]})
|
|
}
|
|
}
|
|
return actions
|
|
}
|
|
|
|
// ReconcileDriveGates enforces the drive-absent gate: an ABSENT registered drive gets its apps STOPPED +
|
|
// recorded (disconnected); a RETURNED drive gets re-bound under the parent and its gate-stopped apps
|
|
// restarted. Best-effort + idempotent — safe to call on a timer and on demand.
|
|
func (s *Server) ReconcileDriveGates() {
|
|
if s.settings == nil || s.stackMgr == nil {
|
|
return
|
|
}
|
|
agent, err := s.agentClient()
|
|
if err != nil {
|
|
return
|
|
}
|
|
ctx, cancel := context.WithTimeout(context.Background(), 15*time.Second)
|
|
defer cancel()
|
|
resp, err := agent.Disks(ctx)
|
|
if err != nil {
|
|
return
|
|
}
|
|
for _, a := range planDriveGates(s.settings.GetStoragePaths(), resp.Disks) {
|
|
switch {
|
|
case a.Stop:
|
|
stopped := s.stopAppsOnPath(a.Path)
|
|
if err := s.settings.SetDisconnected(a.Path, true, stopped); err != nil {
|
|
s.logger.Printf("[WARN] [gate] mark disconnected %s: %v", a.Path, err)
|
|
}
|
|
s.logger.Printf("[WARN] [gate] drive ABSENT %s — stopped+blocked %d app(s): %v", a.Path, len(stopped), stopped)
|
|
go s.SyncFileBrowserMounts()
|
|
case a.Return:
|
|
if a.Raw != "" {
|
|
if err := agent.GuestAttach(ctx, a.Raw); err != nil {
|
|
s.logger.Printf("[WARN] [gate] re-attach %s (raw %s): %v", a.Path, a.Raw, err)
|
|
}
|
|
}
|
|
var stopped []string
|
|
for _, sp := range s.settings.GetStoragePaths() {
|
|
if sp.Path == a.Path {
|
|
stopped = sp.StoppedStacks
|
|
}
|
|
}
|
|
s.restartStacks(stopped)
|
|
if err := s.settings.ClearDisconnected(a.Path); err != nil {
|
|
s.logger.Printf("[WARN] [gate] clear disconnected %s: %v", a.Path, err)
|
|
}
|
|
s.logger.Printf("[INFO] [gate] drive RETURNED %s — re-attached + restarted gate-stopped apps", a.Path)
|
|
go s.SyncFileBrowserMounts()
|
|
}
|
|
}
|
|
}
|
|
|
|
// driveGateLoop runs ReconcileDriveGates on a timer (the periodic absent/return detector — the slice-8C
|
|
// watchdog was retired). Started as a goroutine at server startup. The FIRST action is a one-time
|
|
// startup recreate (see recreateBootStaleApps) to converge a guest reboot deterministically, then the
|
|
// periodic gate.
|
|
func (s *Server) driveGateLoop() {
|
|
// Wait for the stack scan to complete (GetStacks empty at NewServer time) and the agent to come up,
|
|
// so the boot-id recreate sees the real deployed apps + drive state. Bounded poll.
|
|
for i := 0; i < 30; i++ {
|
|
if s.stackMgr != nil && len(s.stackMgr.GetStacks()) > 0 {
|
|
break
|
|
}
|
|
time.Sleep(time.Second)
|
|
}
|
|
s.processGuestBootChange()
|
|
s.ReconcileDriveGates()
|
|
t := time.NewTicker(30 * time.Second)
|
|
defer t.Stop()
|
|
for range t.C {
|
|
s.ReconcileDriveGates()
|
|
}
|
|
}
|
|
|
|
// processGuestBootChange converges a GUEST REBOOT DETERMINISTICALLY. On a guest reboot docker auto-starts
|
|
// the app containers (restart:unless-stopped) BEFORE the agent re-propagates the drive under the parent
|
|
// (~18s later) — so the create-time bind of an app's volume fails (`mkdir …/userdata: permission denied`
|
|
// on the empty fail-closed placeholder) and, being a create-time failure (RestartCount=0), is NEVER
|
|
// retried → the app is stuck Exited forever even after the bind lands. The agent reports a `guest_boot_id`
|
|
// that changes on every guest boot but is stable across a controller-only restart; the controller
|
|
// persists the last-seen value. When it changes (the controller restarts WITH the guest), this:
|
|
// 1. gathers the deployed drive-backed apps' stable drive paths,
|
|
// 2. GATES on the REAL live in-guest bind — `pollLiveBinds`/`driveBindLive` wait (bounded) until each
|
|
// drive's stable path is an actual mountpoint in the controller's own /mnt (rslave) view, which is
|
|
// exactly when docker can recreate the app. (The old code sampled the agent's BoundUnderParent
|
|
// ONCE during fast startup, raced the ~18s rebind, recreated nothing, and persisted the boot-id —
|
|
// burning its one-shot. That is the bug this fixes.)
|
|
// 3. recreates every deployed drive-backed app whose bind is now live (`shouldRecreateOnBoot` is
|
|
// state-independent, so a stuck-Exited create-time-failure app is included), then persists the
|
|
// new boot-id.
|
|
//
|
|
// Apps on a drive that never goes live within the window are left to the normal gate (stop→return→
|
|
// restart). Single-flight (runs once, before the periodic gate, in driveGateLoop). Best-effort.
|
|
func (s *Server) processGuestBootChange() {
|
|
if s.settings == nil || s.stackMgr == nil {
|
|
return
|
|
}
|
|
agent, err := s.agentClient()
|
|
if err != nil {
|
|
return
|
|
}
|
|
ctx, cancel := context.WithTimeout(context.Background(), 15*time.Second)
|
|
resp, derr := agent.Disks(ctx)
|
|
cancel()
|
|
if derr != nil {
|
|
return
|
|
}
|
|
if resp.GuestBootID == "" || resp.GuestBootID == s.settings.GetLastGuestBootID() {
|
|
return // no boot-id, or unchanged (controller-only restart) → no recreate
|
|
}
|
|
|
|
// Distinct stable drive paths that deployed drive-backed apps depend on (HDD_PATH is the drive root).
|
|
needed := map[string]bool{}
|
|
for _, st := range s.stackMgr.GetStacks() {
|
|
cfg := s.stackMgr.LoadAppConfigByName(st.Name)
|
|
if cfg == nil {
|
|
continue
|
|
}
|
|
hdd := cfg.Env["HDD_PATH"]
|
|
if cfg.Deployed && hdd != "" && strings.HasPrefix(hdd, StableParentDir+"/") {
|
|
needed[hdd] = true
|
|
}
|
|
}
|
|
if len(needed) == 0 {
|
|
if serr := s.settings.SetLastGuestBootID(resp.GuestBootID); serr != nil {
|
|
s.logger.Printf("[WARN] [gate] persist boot-id: %v", serr)
|
|
}
|
|
return
|
|
}
|
|
paths := make([]string, 0, len(needed))
|
|
for p := range needed {
|
|
paths = append(paths, p)
|
|
}
|
|
|
|
// READINESS GATE (the fix): wait for the REAL live in-guest bind, not the once-sampled agent view.
|
|
s.logger.Printf("[INFO] [gate] boot %s: waiting (≤%s) for live drive bind(s) %v before recreating drive-backed apps", resp.GuestBootID, bootBindWait, paths)
|
|
presentStable := pollLiveBinds(paths, driveBindLive, time.Sleep, time.Now, bootBindWait, bootBindPoll)
|
|
|
|
skipped := 0
|
|
for _, st := range s.stackMgr.GetStacks() {
|
|
cfg := s.stackMgr.LoadAppConfigByName(st.Name)
|
|
if cfg == nil {
|
|
continue
|
|
}
|
|
if !shouldRecreateOnBoot(cfg.Deployed, cfg.Env["HDD_PATH"], presentStable) {
|
|
if cfg.Deployed && strings.HasPrefix(cfg.Env["HDD_PATH"], StableParentDir+"/") {
|
|
skipped++ // a deployed drive-backed app whose bind never went live → gate's job
|
|
}
|
|
continue
|
|
}
|
|
s.logger.Printf("[INFO] [gate] boot %s: live bind confirmed — recreating drive-backed app %s (state=%s) onto %s", resp.GuestBootID, st.Name, st.State, cfg.Env["HDD_PATH"])
|
|
_ = s.stackMgr.StopStack(st.Name)
|
|
if serr := s.stackMgr.StartStack(st.Name); serr != nil {
|
|
s.logger.Printf("[WARN] [gate] boot recreate %s: %v", st.Name, serr)
|
|
}
|
|
}
|
|
if skipped > 0 {
|
|
s.logger.Printf("[WARN] [gate] boot %s: %d drive-backed app(s) had no live bind within %s — leaving to the drive gate", resp.GuestBootID, skipped, bootBindWait)
|
|
}
|
|
if serr := s.settings.SetLastGuestBootID(resp.GuestBootID); serr != nil {
|
|
s.logger.Printf("[WARN] [gate] persist boot-id: %v", serr)
|
|
}
|
|
}
|
|
|
|
// ---- H1 endpoints (the UI's settings.js calls these; previously 404/unrouted) -----------------
|
|
|
|
// handleStorageDisconnect EJECTS a drive without restart: stop its apps (gate-stopped), agent-detach the
|
|
// felhom-data bind from under the parent (live, fail-closed), and mark it disconnected. The drive is then
|
|
// safely removable. POST {where} where = the registered (stable) path.
|
|
func (s *Server) handleStorageDisconnect(w http.ResponseWriter, r *http.Request) {
|
|
where, ok := s.gateWhere(w, r)
|
|
if !ok {
|
|
return
|
|
}
|
|
stopped := s.stopAppsOnPath(where)
|
|
agent, err := s.agentClient()
|
|
if err == nil {
|
|
if _, derr := agent.EjectDisk(r.Context(), agentWhere(where)); derr != nil {
|
|
s.logger.Printf("[WARN] [web] disconnect: agent detach %s failed: %v", where, derr)
|
|
}
|
|
}
|
|
if err := s.settings.SetDisconnected(where, true, stopped); err != nil {
|
|
writeDiskJSON(w, http.StatusInternalServerError, false, err.Error(), nil)
|
|
return
|
|
}
|
|
go s.SyncFileBrowserMounts()
|
|
writeDiskJSON(w, http.StatusOK, true, "", map[string]any{"where": where, "stopped": stopped})
|
|
}
|
|
|
|
// handleStorageReconnect re-attaches a returned drive without restart: agent-attach the felhom-data bind
|
|
// under the parent (live), restart the gate-stopped apps, clear the disconnected mark.
|
|
// handleStorageReconnect re-enrolls a DISCONNECTED **or** DECOMMISSIONED drive in one click (H3):
|
|
// (for a decommissioned drive) clears the soft marker + restores schedulable, then re-attaches the
|
|
// felhom-data under the parent (agent, raw path, no reboot) and restarts the gate-stopped apps. The data
|
|
// is intact — decommission is non-destructive — so the apps resolve once the bind is live.
|
|
func (s *Server) handleStorageReconnect(w http.ResponseWriter, r *http.Request) {
|
|
where, ok := s.gateWhere(w, r)
|
|
if !ok {
|
|
return
|
|
}
|
|
decommissioned := s.settings.IsDecommissioned(where)
|
|
var stopped []string
|
|
for _, sp := range s.settings.GetStoragePaths() {
|
|
if sp.Path == where {
|
|
stopped = sp.StoppedStacks
|
|
}
|
|
}
|
|
if decommissioned {
|
|
if _, cerr := s.reEnrollClearMarker(where); cerr != nil {
|
|
writeDiskJSON(w, http.StatusInternalServerError, false, cerr.Error(), nil)
|
|
return
|
|
}
|
|
// decommission-anyway stopped the apps WITHOUT persisting StoppedStacks — re-discover them.
|
|
stopped = s.appsOnStoragePath(where)
|
|
}
|
|
agent, err := s.agentClient()
|
|
if err != nil {
|
|
writeDiskJSON(w, http.StatusServiceUnavailable, false, err.Error(), nil)
|
|
return
|
|
}
|
|
if aerr := agent.GuestAttach(r.Context(), agentWhere(where)); aerr != nil {
|
|
writeDiskJSON(w, http.StatusBadGateway, false, "újracsatolás sikertelen: "+aerr.Error(), nil)
|
|
return
|
|
}
|
|
s.restartStacks(stopped)
|
|
if err := s.settings.ClearDisconnected(where); err != nil {
|
|
writeDiskJSON(w, http.StatusInternalServerError, false, err.Error(), nil)
|
|
return
|
|
}
|
|
go s.SyncFileBrowserMounts()
|
|
writeDiskJSON(w, http.StatusOK, true, "", map[string]any{"where": where, "restarted": stopped, "reenrolled": decommissioned})
|
|
}
|
|
|
|
// handleStorageRestartApps restarts the gate-stopped apps on a path (without changing connection state) —
|
|
// the manual "restart the apps that were stopped" action.
|
|
func (s *Server) handleStorageRestartApps(w http.ResponseWriter, r *http.Request) {
|
|
where, ok := s.gateWhere(w, r)
|
|
if !ok {
|
|
return
|
|
}
|
|
var stopped []string
|
|
for _, sp := range s.settings.GetStoragePaths() {
|
|
if sp.Path == where {
|
|
stopped = sp.StoppedStacks
|
|
}
|
|
}
|
|
s.restartStacks(stopped)
|
|
writeDiskJSON(w, http.StatusOK, true, "", map[string]any{"where": where, "restarted": stopped})
|
|
}
|
|
|
|
// gateWhere decodes + validates the {where} body shared by the H1 endpoints.
|
|
func (s *Server) gateWhere(w http.ResponseWriter, r *http.Request) (string, bool) {
|
|
var req struct {
|
|
Where string `json:"where"`
|
|
}
|
|
if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
|
|
writeDiskJSON(w, http.StatusBadRequest, false, "érvénytelen kérés", nil)
|
|
return "", false
|
|
}
|
|
where := path.Clean(strings.TrimSpace(req.Where))
|
|
if where == "" || where == "." || !strings.HasPrefix(where, "/mnt/") {
|
|
writeDiskJSON(w, http.StatusBadRequest, false, "érvénytelen csatlakoztatási pont", nil)
|
|
return "", false
|
|
}
|
|
return where, true
|
|
}
|