linetest: a test on request for a box that seeds all day (R-1250)
gates / gates (push) Successful in 1m37s

GET /host/line-test reports waiting_for_quiet (due, in the window, tunnel up, only the quiet
missing); POST /host/line-test/run runs one measurement with a 5 s settle and a 10 s quiet
check instead of 10 quiet minutes, runs 5 s apart (~55 s). Every other weekly rule holds.
Commit only; the release rides the next train.
This commit is contained in:
2026-10-24 13:18:59 +02:00
parent 08ca67861f
commit 29bcf4403e
7 changed files with 377 additions and 14 deletions
+20
View File
@@ -1,3 +1,23 @@
## Unreleased (next: v0.165.0) — the line test for a box that seeds all day (R-1250) (2026-10-24) — committed, not released
Attended brief 2026-10-24, Part 4 (commit only; the release rides the next normal train). The weekly test (v0.164.0)
starts only after 10 quiet minutes; a torrent app that seeds all day never gives them, so that box never got a tested
line and qBittorrent never got its 50 % limit. Now:
- **`linetest.Tester.WaitingForQuiet`** — due, inside the window, tries left, tunnel up, and only the quiet missing.
`GET /host/line-test` carries it as `waiting_for_quiet`; a controller with a seeding torrent app acts only on it.
- **`linetest.Tester.RunNow`** and **`POST /host/line-test/run`** (synchronous, about 55 s) — a test on request while the
controller holds its app's upload low: every weekly rule holds (due, window, `MaxTriesPerDay`, tunnel, the one heavy-op
gate) except the 10 quiet minutes, which become a 5 s settle and a 10 s quiet check (below 2 Mbit/s, so a request
never measures the family's own upload); the three runs are 5 s apart instead of 30. A refusal answers its code
(`not-due`, `outside-window`, `tries-used`, `no-tunnel`, `heavy-op`, `not-quiet`, `server-busy`); a failed request
spends one of the day's tries. `Tick` and `RunNow` now share one `ready()` check.
- Tests (each seen failing): `TestSeedingBoxIsWaitingForQuietAndRunNowMeasuresIt` (the sleeps, the 60 s bound),
`TestRunNowRefusesAnUplinkThatIsStillBusy`, `TestRunNowKeepsTheWeeklyRules`, `TestRunNowFailuresSpendTheDaysTries`,
`TestQuietBoxIsNotWaiting`, `TestLineTestRunRoute`; a compile-time assertion that the Tester serves the request half.
**No sudoers or config-bundle change. MinController: none** — an older controller never calls the route.
## v0.164.0 — the weekly upload line test (R-1247) (2026-10-24) — RELEASED on the operator's ruling (attended release run); vouched by the operator 09:44:58 CEST
Binary sha256 `1b803d8b70f8afbe1546f6989f35b6b0e29c9ed63f6acb3843d3c04ef0d24b2b`; config bundle sha256
+8
View File
@@ -5,8 +5,16 @@ import (
"go/parser"
"go/token"
"testing"
"gitea.dooplex.hu/admin/felhom-agent/internal/linetest"
"gitea.dooplex.hu/admin/felhom-agent/internal/localapi"
)
// R-1250: SetLineTest takes a LineTestReader and finds the request half by a type assertion, so a Tester that lost
// WaitingForQuiet or RunNow would compile and silently answer 503 to every seeding box. This line makes it a build
// failure instead.
var _ localapi.LineTestRequester = (*linetest.Tester)(nil)
// R-1247: the weekly line test has the fstrim shape (component + reporter seam + goroutine) plus a local-API reader,
// so its wiring is asserted from the AST. It must share the ONE heavy-op gate (heavyOps) — or it could run beside a
// backup — and take its server from the tunnel manager, never a literal address.
+110 -11
View File
@@ -19,6 +19,10 @@
// - No tunnel (no operational wg-felhom with a server address) → no test and no value; the controller then keeps its
// passive floor and sets no qBittorrent limit.
// - The last result is persisted, so a restart neither loses it nor re-tests.
// - A box whose torrent app seeds all day is never quiet for 10 minutes (R-1250). For it the controller holds the
// app's upload limit very low and asks for a test on request (RunNow): every rule above except the 10 quiet
// minutes still holds, the quiet is checked over RequestQuietWindow instead, and the runs are RequestRunGap
// apart, so the whole request ends in about 55 s.
package linetest
import (
@@ -56,6 +60,11 @@ const (
TickInterval = time.Minute
FirstTickDelay = 5 * time.Minute
GateName = "line-test"
// A test on request (R-1250): the controller holds the app's limit while it waits, so it is short.
RequestSettle = 5 * time.Second // the held app's last packets leave before the quiet is read
RequestQuietWindow = 10 * time.Second // the uplink must send below QuietMbps over this window
RequestRunGap = 5 * time.Second
)
// ScheduleText is carried on the host report.
@@ -258,30 +267,52 @@ func (t *Tester) Run(ctx context.Context) {
}
}
// Tick is one look.
func (t *Tester) Tick(ctx context.Context) {
// Refusal is why a test on request did not run (RunNow). Code is stable for the controller.
type Refusal struct {
Code string // not-due | outside-window | tries-used | no-tunnel | heavy-op | not-quiet
Msg string
}
func (r *Refusal) Error() string { return "linetest: " + r.Code + ": " + r.Msg }
// ready applies every rule except the quiet one: due this week, inside the window (the slot on the due day), tries
// left today, the tunnel up. It answers the server address and the local day.
func (t *Tester) ready() (addr, day string, refusal *Refusal) {
lt := t.now().In(t.loc)
t.mu.Lock()
st := t.st
samples := append([]txSample(nil), t.samples...)
t.mu.Unlock()
if !Due(st, lt) {
return
return "", "", &Refusal{"not-due", "measured this week"}
}
anchor := weekAnchor(lt)
anchorDay := lt.YearDay() == anchor.YearDay() && lt.Year() == anchor.Year()
if !EligibleAt(lt, t.slot, anchorDay) {
return
return "", "", &Refusal{"outside-window", "a test starts 10:00-15:59 local, from this host's slot on the due day"}
}
day := lt.Format("2006-01-02")
day = lt.Format("2006-01-02")
if st.TriesDay == day && st.TriesToday >= MaxTriesPerDay {
return
return "", "", &Refusal{"tries-used", fmt.Sprintf("%d tries today", st.TriesToday)}
}
ip, ok := t.target()
if !ok {
t.logger.Debug("linetest: no operational tunnel — no test")
return "", "", &Refusal{"no-tunnel", "no operational tunnel"}
}
return netip.AddrPortFrom(ip, ServerPort).String(), day, nil
}
// Tick is one look.
func (t *Tester) Tick(ctx context.Context) {
addr, day, refusal := t.ready()
if refusal != nil {
if refusal.Code == "no-tunnel" {
t.logger.Debug("linetest: no operational tunnel — no test")
}
return
}
t.mu.Lock()
samples := append([]txSample(nil), t.samples...)
t.mu.Unlock()
if q, worst := quiet(samples); !q {
t.logger.Debug("linetest: uplink not quiet — waiting", "worst_minute_mbps", fmt.Sprintf("%.1f", worst), "samples", len(samples))
return
@@ -292,16 +323,77 @@ func (t *Tester) Tick(ctx context.Context) {
return
}
defer release()
t.measure(ctx, netip.AddrPortFrom(ip, ServerPort).String(), day)
t.measure(ctx, addr, day, RunGap)
}
func (t *Tester) measure(ctx context.Context, addr, day string) {
// WaitingForQuiet reports that a measurement is due and could start now but the uplink has not been quiet for
// QuietMinutes — the case a seeding torrent app makes permanent (R-1250). The controller reads it from
// GET /host/line-test and only then holds its app's limit and calls RunNow.
func (t *Tester) WaitingForQuiet() bool {
if _, _, refusal := t.ready(); refusal != nil {
return false
}
t.mu.Lock()
samples := append([]txSample(nil), t.samples...)
t.mu.Unlock()
q, _ := quiet(samples)
return !q
}
// RunNow is a test on request (POST /host/line-test/run, R-1250): every rule of the weekly test except the 10 quiet
// minutes, which the caller replaces by holding its own upload down. The uplink must still be quiet over
// RequestQuietWindow (after RequestSettle), so a request never measures the family's upload against itself. A
// *Refusal says why nothing ran; any other error is a failed measurement (the same as a failed weekly attempt).
func (t *Tester) RunNow(ctx context.Context) (mbps float64, runs []float64, err error) {
addr, day, refusal := t.ready()
if refusal != nil {
return 0, nil, refusal
}
release, busy, ok := t.gate.TryAcquire(GateName)
if !ok {
return 0, nil, &Refusal{"heavy-op", busy}
}
defer release()
if t.uplink == nil {
return 0, nil, &Refusal{"not-quiet", "no uplink counter"}
}
if !t.sleep(ctx, RequestSettle) {
return 0, nil, ctx.Err()
}
tx0, err0 := t.uplink()
at0 := t.now()
if !t.sleep(ctx, RequestQuietWindow) {
return 0, nil, ctx.Err()
}
tx1, err1 := t.uplink()
if err0 != nil || err1 != nil || tx1 < tx0 {
return 0, nil, &Refusal{"not-quiet", "uplink counter unreadable or reset"}
}
secs := t.now().Sub(at0).Seconds()
if secs <= 0 {
secs = RequestQuietWindow.Seconds()
}
if m := float64(tx1-tx0) * 8 / secs / 1e6; m >= QuietMbps {
t.logger.Info("linetest: test on request refused — the uplink is not quiet", "mbps", fmt.Sprintf("%.1f", m))
return 0, nil, &Refusal{"not-quiet", fmt.Sprintf("the uplink sent %.1f Mbit/s while held", m)}
}
t.logger.Info("linetest: test on request (a held torrent app, R-1250)", "server", addr)
if err := t.measure(ctx, addr, day, RequestRunGap); err != nil {
return 0, nil, err
}
t.mu.Lock()
defer t.mu.Unlock()
return t.st.Mbps, append([]float64(nil), t.st.RunsMbps...), nil
}
// measure runs the runs, gap apart, and stores the result. It returns nil only when a value was stored.
func (t *Tester) measure(ctx context.Context, addr, day string, gap time.Duration) error {
start := t.now()
var runs []float64
var lastErr error
busy := false
for i := 0; i < RunsPerMeasurement; i++ {
if i > 0 && !t.sleep(ctx, RunGap) {
if i > 0 && !t.sleep(ctx, gap) {
break
}
rctx, cancel := context.WithTimeout(ctx, RunTimeout)
@@ -356,6 +448,13 @@ func (t *Tester) measure(ctx context.Context, addr, day string) {
if err := t.saveLocked(); err != nil {
t.logger.Warn("linetest: state save failed — the result will not survive a restart", "path", t.statePath, "err", err)
}
if len(runs) > 0 {
return nil
}
if lastErr == nil {
lastErr = errors.New("linetest: no run succeeded")
}
return lastErr
}
// Value is the measured line (ok=false: never measured).
+118
View File
@@ -431,3 +431,121 @@ func TestQuietNeedsTenFullMinutes(t *testing.T) {
t.Fatal("a gap in the samples must not read quiet")
}
}
// ── a test on request (R-1250): a torrent app that seeds all day ───────────────────────────────────────────────────
// seedingRig: due and eligible, but every minute of the last ten sent at the line's speed — the weekly Tick never runs.
func seedingRig(t *testing.T, outs ...runOut) *rig {
r := newRig(t, outs...)
for i := 0; i < QuietMinutes+1; i++ {
r.minute(600_000_000) // 80 Mbit/s: a seed at the line's speed
}
return r
}
func TestSeedingBoxIsWaitingForQuietAndRunNowMeasuresIt(t *testing.T) {
r := seedingRig(t, runOut{mbps: 88}, runOut{mbps: 92}, runOut{mbps: 90})
r.t.Tick(context.Background())
if r.run.calls != 0 {
t.Fatal("the weekly Tick tested a seeding box")
}
if !r.t.WaitingForQuiet() {
t.Fatal("a due, eligible, seeding box must report waiting_for_quiet")
}
var slept []time.Duration
r.t.sleep = func(_ context.Context, d time.Duration) bool { slept = append(slept, d); return true }
mbps, runs, err := r.t.RunNow(context.Background()) // the controller holds the app: the counter stands still
if err != nil || mbps != 92 || len(runs) != RunsPerMeasurement || r.run.calls != RunsPerMeasurement {
t.Fatalf("RunNow = %.1f %v %v, calls %d; want the best of 3 = 92", mbps, runs, err, r.run.calls)
}
want := []time.Duration{RequestSettle, RequestQuietWindow, RequestRunGap, RequestRunGap}
if len(slept) != len(want) {
t.Fatalf("slept %v, want %v", slept, want)
}
var total time.Duration
for i := range want {
if slept[i] != want[i] {
t.Fatalf("slept %v, want %v", slept, want)
}
total += slept[i]
}
if total+RunsPerMeasurement*TestTime > 60*time.Second {
t.Fatalf("a request holds the app %v + runs; it must end inside 60 s", total)
}
if v, _, ok := r.t.Value(); !ok || v != 92 {
t.Fatalf("the requested measurement was not stored: %.1f %v", v, ok)
}
if r.t.WaitingForQuiet() {
t.Fatal("measured this week: no longer waiting")
}
if _, _, err := r.t.RunNow(context.Background()); refusalCode(err) != "not-due" {
t.Fatalf("a second request this week: %v, want not-due", err)
}
}
func refusalCode(err error) string {
var ref *Refusal
if errors.As(err, &ref) {
return ref.Code
}
return ""
}
// The held app is not the only uploader: a request still refuses to measure a busy uplink.
func TestRunNowRefusesAnUplinkThatIsStillBusy(t *testing.T) {
r := seedingRig(t, runOut{mbps: 90}, runOut{mbps: 90}, runOut{mbps: 90})
r.t.uplink = func() (uint64, error) { r.tx += 20_000_000; return r.tx, nil } // 20 MB per 10 s = 16 Mbit/s
if _, _, err := r.t.RunNow(context.Background()); refusalCode(err) != "not-quiet" || r.run.calls != 0 {
t.Fatalf("RunNow on a busy uplink: %v, calls %d; want not-quiet and no run", err, r.run.calls)
}
}
// Every other rule of the weekly test holds for a request.
func TestRunNowKeepsTheWeeklyRules(t *testing.T) {
r := seedingRig(t)
r.gate.busy = "backup:felhom-pbs"
if _, _, err := r.t.RunNow(context.Background()); refusalCode(err) != "heavy-op" {
t.Fatalf("beside a backup: %v, want heavy-op", err)
}
r.gate.busy = ""
r.tunnel = false
if _, _, err := r.t.RunNow(context.Background()); refusalCode(err) != "no-tunnel" {
t.Fatalf("no tunnel: %v, want no-tunnel", err)
}
if r.t.WaitingForQuiet() {
t.Fatal("no tunnel: a request could not run, so it must not be invited")
}
r.tunnel = true
r.now = time.Date(2026, 10, 20, 3, 0, 0, 0, time.UTC) // Tuesday 03:00 — the night chain
if _, _, err := r.t.RunNow(context.Background()); refusalCode(err) != "outside-window" {
t.Fatalf("at night: %v, want outside-window", err)
}
if r.run.calls != 0 {
t.Fatalf("%d runs on refused requests", r.run.calls)
}
}
// A failed request counts as a try, so a controller cannot request more than MaxTriesPerDay tests a day.
func TestRunNowFailuresSpendTheDaysTries(t *testing.T) {
var outs []runOut
for i := 0; i < MaxTriesPerDay*RunsPerMeasurement; i++ {
outs = append(outs, runOut{err: errors.New("connection refused")})
}
r := seedingRig(t, outs...)
for i := 0; i < MaxTriesPerDay; i++ {
if _, _, err := r.t.RunNow(context.Background()); err == nil || refusalCode(err) != "" {
t.Fatalf("try %d: %v, want a failed measurement", i+1, err)
}
}
if _, _, err := r.t.RunNow(context.Background()); refusalCode(err) != "tries-used" {
t.Fatalf("after %d failures: %v, want tries-used", MaxTriesPerDay, err)
}
}
// A quiet box tests itself on the weekly Tick: it must not invite the controller to hold its app.
func TestQuietBoxIsNotWaiting(t *testing.T) {
r := newRig(t)
if r.t.WaitingForQuiet() {
t.Fatal("ten quiet minutes: the weekly Tick runs; waiting_for_quiet must be false")
}
}
+55 -3
View File
@@ -1,8 +1,12 @@
package localapi
import (
"context"
"errors"
"net/http"
"time"
"gitea.dooplex.hu/admin/felhom-agent/internal/linetest"
)
// LineTestReader is the R-1247 weekly upload line test (internal/linetest.Tester) as the local API reads it.
@@ -10,6 +14,13 @@ type LineTestReader interface {
Value() (mbps float64, at time.Time, ok bool)
}
// LineTestRequester is the R-1250 half: a due test the uplink never lets start, and a test on request. The Tester
// satisfies it; a reader without it answers waiting_for_quiet:false and 503 on the POST.
type LineTestRequester interface {
WaitingForQuiet() bool
RunNow(ctx context.Context) (mbps float64, runs []float64, err error)
}
// LineTestResponse is GET /host/line-test. Present=false: never measured, or the job is not wired (no tunnel, disabled,
// or an agent before the route answers 404 — the controller reads all three as „unknown").
type LineTestResponse struct {
@@ -17,6 +28,19 @@ type LineTestResponse struct {
Mbps float64 `json:"mbps,omitempty"`
MeasuredAt string `json:"measured_at,omitempty"` // RFC3339 UTC
Method string `json:"method,omitempty"` // "iperf3-tunnel": a 10-second upload to ep0 inside the tunnel
// WaitingForQuiet: a measurement is due and could start now, but the uplink has not been quiet for 10 minutes
// (R-1250). The controller with a seeding torrent app then holds its limit and POSTs /host/line-test/run.
WaitingForQuiet bool `json:"waiting_for_quiet,omitempty"`
}
// LineTestRunResponse is POST /host/line-test/run. OK=false with Refused: nothing ran (Refused is linetest.Refusal's
// code, or "server-busy"); OK=false without it: the runs failed.
type LineTestRunResponse struct {
OK bool `json:"ok"`
Mbps float64 `json:"mbps,omitempty"`
RunsMbps []float64 `json:"runs_mbps,omitempty"`
Refused string `json:"refused,omitempty"`
Error string `json:"error,omitempty"`
}
// SetLineTest wires the weekly line test (main.go builds it after the local API server).
@@ -27,11 +51,39 @@ func (s *Server) handleLineTest(w http.ResponseWriter, r *http.Request, vmid int
writeOK(w, LineTestResponse{Present: false})
return
}
var waiting bool
if q, ok := s.lineTest.(LineTestRequester); ok {
waiting = q.WaitingForQuiet()
}
mbps, at, ok := s.lineTest.Value()
if !ok {
writeOK(w, LineTestResponse{Present: false})
writeOK(w, LineTestResponse{Present: false, WaitingForQuiet: waiting})
return
}
s.logger.Debug("local-api: /host/line-test served", "vmid", vmid, "mbps", mbps, "measured_at", at.UTC().Format(time.RFC3339))
writeOK(w, LineTestResponse{Present: true, Mbps: mbps, MeasuredAt: at.UTC().Format(time.RFC3339), Method: "iperf3-tunnel"})
s.logger.Debug("local-api: /host/line-test served", "vmid", vmid, "mbps", mbps, "measured_at", at.UTC().Format(time.RFC3339), "waiting_for_quiet", waiting)
writeOK(w, LineTestResponse{Present: true, Mbps: mbps, MeasuredAt: at.UTC().Format(time.RFC3339), Method: "iperf3-tunnel", WaitingForQuiet: waiting})
}
// handleLineTestRun is POST /host/line-test/run (R-1250): a test on request, synchronous (about 55 s). The answer is
// always 200 with the outcome in the body, except 503 when no line test is wired.
func (s *Server) handleLineTestRun(w http.ResponseWriter, r *http.Request, vmid int) {
q, ok := s.lineTest.(LineTestRequester)
if s.lineTest == nil || !ok {
writeErr(w, http.StatusServiceUnavailable, "line test not configured")
return
}
s.logger.Info("local-api: line test requested", "vmid", vmid)
mbps, runs, err := q.RunNow(r.Context())
var ref *linetest.Refusal
switch {
case err == nil:
writeOK(w, LineTestRunResponse{OK: true, Mbps: mbps, RunsMbps: runs})
case errors.As(err, &ref):
s.logger.Info("local-api: line test request refused", "vmid", vmid, "reason", ref.Code, "detail", ref.Msg)
writeOK(w, LineTestRunResponse{Refused: ref.Code, Error: ref.Msg})
case errors.Is(err, linetest.ErrBusy):
writeOK(w, LineTestRunResponse{Refused: "server-busy", Error: err.Error()})
default:
writeOK(w, LineTestRunResponse{Error: err.Error()})
}
}
+65
View File
@@ -1,12 +1,16 @@
package localapi
import (
"context"
"encoding/json"
"errors"
"log/slog"
"net/http/httptest"
"strings"
"testing"
"time"
"gitea.dooplex.hu/admin/felhom-agent/internal/linetest"
)
type fixedLine struct {
@@ -49,3 +53,64 @@ func TestLineTestRoute(t *testing.T) {
t.Fatalf("measured: %+v", got)
}
}
type requestableLine struct {
fixedLine
waiting bool
mbps float64
err error
calls int
}
func (r *requestableLine) WaitingForQuiet() bool { return r.waiting }
func (r *requestableLine) RunNow(context.Context) (float64, []float64, error) {
r.calls++
if r.err != nil {
return 0, nil, r.err
}
return r.mbps, []float64{r.mbps - 1, r.mbps}, nil
}
func lineTestRun(t *testing.T, s *Server) (int, LineTestRunResponse) {
t.Helper()
rec := httptest.NewRecorder()
s.handleLineTestRun(rec, httptest.NewRequest("POST", "/host/line-test/run", nil), 9201)
var env struct {
OK bool `json:"ok"`
Data LineTestRunResponse `json:"data"`
}
_ = json.Unmarshal(rec.Body.Bytes(), &env)
return rec.Code, env.Data
}
// R-1250: the controller acts only on waiting_for_quiet, and reads a refusal by its code — never as a measurement.
func TestLineTestRunRoute(t *testing.T) {
s := &Server{logger: slog.Default()}
if code, _ := lineTestRun(t, s); code != 503 {
t.Fatalf("not wired: HTTP %d, want 503", code)
}
s.SetLineTest(fixedLine{ok: true, mbps: 90})
if code, _ := lineTestRun(t, s); code != 503 {
t.Fatalf("a reader without the request half: HTTP %d, want 503", code)
}
l := &requestableLine{fixedLine: fixedLine{ok: false}, waiting: true, mbps: 93.5}
s.SetLineTest(l)
if got := lineTestBody(t, s); got.Present || !got.WaitingForQuiet {
t.Fatalf("GET while waiting: %+v, want present:false waiting_for_quiet:true", got)
}
if code, got := lineTestRun(t, s); code != 200 || !got.OK || got.Mbps != 93.5 || len(got.RunsMbps) != 2 {
t.Fatalf("a measured request: HTTP %d %+v", code, got)
}
l.err = &linetest.Refusal{Code: "not-quiet", Msg: "the uplink sent 16.0 Mbit/s while held"}
if _, got := lineTestRun(t, s); got.OK || got.Refused != "not-quiet" || got.Mbps != 0 {
t.Fatalf("a refusal: %+v, want ok:false refused:not-quiet", got)
}
l.err = linetest.ErrBusy
if _, got := lineTestRun(t, s); got.OK || got.Refused != "server-busy" {
t.Fatalf("server busy: %+v, want refused:server-busy", got)
}
l.err = errors.New("dial tcp 10.77.0.1:5201: i/o timeout")
if _, got := lineTestRun(t, s); got.OK || got.Refused != "" || got.Error == "" {
t.Fatalf("a failed run: %+v, want ok:false, no refusal, the error", got)
}
}
+1
View File
@@ -577,6 +577,7 @@ func (s *Server) Handler() http.Handler {
// R-1247: the weekly upload line test's last measurement — the controller's qBittorrent limit and upload watch
// read it. Read-only; never measured (or the job not wired) = present:false.
mux.HandleFunc("GET /host/line-test", s.withGuest(s.handleLineTest))
mux.HandleFunc("POST /host/line-test/run", s.withGuest(s.handleLineTestRun)) // R-1250: a test on request
// Disk management (slice 8C) — self-scoped; format routes through the data-bearing classifier+gate.
mux.HandleFunc("GET /disks", s.withGuest(s.handleDisks))
mux.HandleFunc("GET /disks/candidates", s.withGuest(s.handleDiskCandidates))