admin/felhom-agent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

R-899: no OS leg after a household press (trigger=manual); after-boot kernel reports carry the saved ring
gates / gates (push) Successful in 50s
Details

Browse Source 
Unreleased; ships with tomorrow's release.

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:
authentik Default Admin
2026-10-08 07:34:19 +02:00
parent c9013bb47d
commit 4c69c25b48
5 changed files with 95 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
internal/osupdate/kernel.go
+23 -5
View File
@@ -51,6 +51,24 @@ type KernelView struct {
VMID int `json:"vmid"` // the customer guest the step was staged for (the health rule's guest)
}
// kernelReportRing is the ring an after-boot report carries. In the first second after a boot the agent has not
// fetched the hub's block yet, and Block() then answers ring 1 — so a ring-0 box's „judging" report said ring 1
// (seen on demo-felhom, 2026-10-08 night, `audits/kernel-night-2026-10-07/readback/`). Order: the fetched block; the
// block the daemon saved on disk before the reboot (R-866); ring 1 as before. A label only: the hub's approval reads its
// own ring list. Pinned by TestKernelReportRing_BeforeFirstFetch.
func (l *Leg) kernelReportRing() int {
l.mu.Lock()
fetched := l.block
l.mu.Unlock()
if fetched != nil {
return fetched.Ring
}
if b, _, ok := LoadSavedBlock(l.planDir()); ok && b != nil {
return b.Ring
}
return 1
}
func parseKernel(raw json.RawMessage) KernelView {
var v KernelView
_ = json.Unmarshal(raw, &v)
@@ -190,7 +208,7 @@ func (l *Leg) KernelAfterBoot(ctx context.Context, vmid int, j KernelJudge) Repo
if vmid <= 0 {
vmid = v.VMID // after a boot the guest may not run yet — the step's own record names it
}
rep := Report{RunID: runID, Layer: LayerKernel, Trigger: "boot", Ring: l.Block().Ring, VMID: vmid, Mode: "kernel-boot",
rep := Report{RunID: runID, Layer: LayerKernel, Trigger: "boot", Ring: l.kernelReportRing(), VMID: vmid, Mode: "kernel-boot",
ReleaseID: v.To, Kernel: rawOrNil(wr.Kernel)}
switch wr.KernelEvent {
case "fell_back":
@@ -240,7 +258,7 @@ func (l *Leg) judgeKernel(ctx context.Context, runID string, vmid int, v KernelV
for {
if !hubReached && l.Hub != nil {
// the hub's reachability IS this report reaching it (and the operator sees the box is back on the new kernel)
body, _ := json.Marshal(Report{RunID: runID, Layer: LayerKernel, Trigger: "boot", Ring: l.Block().Ring, VMID: vmid,
body, _ := json.Marshal(Report{RunID: runID, Layer: LayerKernel, Trigger: "boot", Ring: l.kernelReportRing(), VMID: vmid,
Mode: "kernel-boot", ReleaseID: v.To, Outcome: "judging", Kernel: mustRaw(v)})
rctx, cancel := context.WithTimeout(ctx, 30*time.Second)
if err := l.Hub.PostOSReport(rctx, body); err == nil {
@@ -280,7 +298,7 @@ func (l *Leg) judgeKernel(ctx context.Context, runID string, vmid int, v KernelV
return Report{}
}
// not healthy by the deadline: tell the hub (best effort), then ONE self-revert into the old kernel
rep := l.finish(ctx, lg, Report{RunID: runID, Layer: LayerKernel, Trigger: "boot", Ring: l.Block().Ring, VMID: vmid,
rep := l.finish(ctx, lg, Report{RunID: runID, Layer: LayerKernel, Trigger: "boot", Ring: l.kernelReportRing(), VMID: vmid,
Mode: "kernel-revert", ReleaseID: v.To, Outcome: "health_failed", HealthReason: why + " — reverting to " + v.From,
Kernel: mustRaw(v)})
lg.Error("osupdate: kernel step — the one-shot boot is NOT healthy; restarting ONCE into the old kernel", "reason", why,
@@ -289,7 +307,7 @@ func (l *Leg) judgeKernel(ctx context.Context, runID string, vmid int, v KernelV
if err != nil || wr.refused() || wr.failed() {
lg.Error("osupdate: kernel self-revert did not start — the box stays on the new kernel; the operator decides",
"err", err, "refused", string(firstRaw(wr.Refused, wr.Failed)))
return l.finish(ctx, lg, Report{RunID: runID, Layer: LayerKernel, Trigger: "boot", Ring: l.Block().Ring, VMID: vmid,
return l.finish(ctx, lg, Report{RunID: runID, Layer: LayerKernel, Trigger: "boot", Ring: l.kernelReportRing(), VMID: vmid,
Mode: "kernel-revert", ReleaseID: v.To, Outcome: "revert_failed", Refused: firstRaw(wr.Refused, wr.Failed),
HealthReason: "the self-revert did not start"})
}
@@ -298,7 +316,7 @@ func (l *Leg) judgeKernel(ctx context.Context, runID string, vmid int, v KernelV
func (l *Leg) kernelGood(ctx context.Context, runID string, vmid int, v KernelView, start time.Time, lg *slog.Logger) Report {
wr, err := l.call(ctx, runID, kernelPlan("kernel-good", vmid, nil))
rep := Report{RunID: runID, Layer: LayerKernel, Trigger: "boot", Ring: l.Block().Ring, VMID: vmid, Mode: "kernel-good",
rep := Report{RunID: runID, Layer: LayerKernel, Trigger: "boot", Ring: l.kernelReportRing(), VMID: vmid, Mode: "kernel-good",
ReleaseID: v.To}
switch {
case err != nil: