Files
felhom-agent/internal/guesthook/netreassert.go
T
admin 474b858c0b v0.84.0: ReassertNetworkMounts — NAS automount survives guest reboots (RCA fix 1)
Storage §8 decision table (stop + enable --now on idle triggers; active mounts untouched),
daemon leg at startup with per-running-guest visibility verify, guest-hook post-start leg
(root, direct systemctl, non-fatal). Red-proofs: always-rearm table FAIL; unwired hook FAIL.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PSK5g6qYLknKj8u3QAFEr6
2026-07-11 20:46:59 +02:00

82 lines
3.2 KiB
Go

package guesthook
import (
"context"
"fmt"
"log/slog"
"os"
"strings"
"gitea.dooplex.hu/admin/felhom-agent/internal/proxmox"
"gitea.dooplex.hu/admin/felhom-agent/internal/storage"
)
// post-start network-storage reassert (RCA AUDIT-nas-cwa-rca-2026-07-11 fix 1, hook leg).
//
// A freshly started guest's namespace does NOT inherit an idle NAS autofs trigger (only real
// mounts), so its /mnt/felhom-drives/<share> path is a silent local stub until the trigger is
// re-created host-side. PVE runs the hookscript as root in the start task, so this leg calls
// systemctl DIRECTLY (no sudo) — the daemon leg (localapi.ReassertNetworkMounts) is the sudo path.
// Like the pre-start heal, this must NEVER fail the hook: all errors go to stderr (the PVE task
// log) and the guest start proceeds regardless.
// netReasserter is the reassert capability (satisfied by *storage.SudoHostOps; faked in tests).
type netReasserter interface {
ReassertNetworkAutomounts(ctx context.Context) []storage.NetReassertResult
}
// PostStartNetworkReassert re-arms idle NAS automount triggers after vmid started, then verifies
// the (now running) guest actually sees each share path. Best-effort throughout.
func PostStartNetworkReassert(ctx context.Context, vmid string) {
runner := &proxmox.ExecRunner{Mode: proxmox.RunnerDirect}
ops := storage.NewSudoHostOps(storage.SudoHostOpsConfig{
Runner: runner,
Logger: slog.New(slog.NewTextHandler(os.Stderr, &slog.HandlerOptions{Level: slog.LevelInfo})),
})
postStartNetworkReassert(ctx, vmid, ops, func(ctx context.Context, vmid, path string) bool {
return GuestSeesPath(ctx, runner, vmid, path)
})
}
// postStartNetworkReassert is the seam-injected core (unit-tested; the wrapper above binds the
// real host surface).
func postStartNetworkReassert(ctx context.Context, vmid string, ops netReasserter, sees func(ctx context.Context, vmid, path string) bool) {
for _, res := range ops.ReassertNetworkAutomounts(ctx) {
if res.Err != nil || res.Action == storage.NetReassertSkipNone {
continue // already reported by the ops logger / nothing expected in the guest
}
if sees(ctx, vmid, res.Where) {
fmt.Fprintf(os.Stderr, "felhom-agent guest-hook: vmid %s post-start — network share %s visible in guest (%s)\n",
vmid, res.Name, res.Action)
} else {
fmt.Fprintf(os.Stderr, "felhom-agent guest-hook: vmid %s post-start — WARNING: network share %s NOT visible in guest after reassert (%s)\n",
vmid, res.Name, res.Action)
}
}
}
// GuestSeesPath reports whether vmid's guest has `path` as a mount target in its own namespace —
// the hook-process mirror of localapi's GuestBinder.GuestSeesMount (which is method-bound to the
// daemon's binder and unavailable here). Resolution/read errors → false.
func GuestSeesPath(ctx context.Context, runner proxmox.Runner, vmid, path string) bool {
out, _, err := runner.Run(ctx, "lxc-info", "-n", vmid, "-p", "-H")
if err != nil {
return false
}
pid := strings.TrimSpace(string(out))
if pid == "" {
return false
}
data, err := os.ReadFile("/proc/" + pid + "/mountinfo")
if err != nil {
return false
}
for _, line := range strings.Split(string(data), "\n") {
f := strings.Fields(line)
if len(f) >= 5 && f[4] == path {
return true
}
}
return false
}