felhom-agent/internal/fstrim/fstrim_test.go

package fstrim

import (
	"bytes"
	"context"
	"encoding/json"
	"errors"
	"log/slog"
	"path/filepath"
	"reflect"
	"strings"
	"sync"
	"testing"
	"time"

	"gitea.dooplex.hu/admin/felhom-agent/internal/backup"
	"gitea.dooplex.hu/admin/felhom-agent/internal/proxmox"
)

// The real `pct fstrim 9201` output measured on demo-hp 2026-10-06 (audits/ten-answers-2026-10-06/r444-measure.txt).
const measuredOut = "/var/lib/lxc/9201/rootfs/: 30.1 GiB (32277680128 bytes) trimmed\n" +
	"/var/lib/lxc/9201/rootfs/var/lib/felhom: 53.9 GiB (57865633792 bytes) trimmed\n"

const measuredBytes = int64(32277680128 + 57865633792)

type fakeRunner struct {
	mu    sync.Mutex
	calls [][]string
	out   string
	err   error
	onRun func()
}

func (f *fakeRunner) Run(_ context.Context, name string, args ...string) ([]byte, []byte, error) {
	f.mu.Lock()
	f.calls = append(f.calls, append([]string{name}, args...))
	f.mu.Unlock()
	if f.onRun != nil {
		f.onRun()
	}
	if f.err != nil {
		return nil, []byte("mount busy"), f.err
	}
	return []byte(f.out), nil, nil
}

type fakeGuests struct {
	g   []proxmox.Guest
	err error
}

func (f fakeGuests) Guests(context.Context) ([]proxmox.Guest, error) { return f.g, f.err }

// A Wednesday 10:30 in a fixed zone (CEST-like), so the tests do not depend on the machine's zone.
var zone = time.FixedZone("CEST", 2*3600)

func at(day, hour, min int) time.Time { return time.Date(2026, 10, day, hour, min, 0, 0, zone) } // 2026-10-07 = Wednesday

func newT(t *testing.T, r Runner, g GuestSource, gate Gate, now *time.Time) (*Trimmer, *bytes.Buffer, string) {
	t.Helper()
	var logs bytes.Buffer
	path := filepath.Join(t.TempDir(), "guest-disk-trim.json")
	tr := New(r, g, gate, path, slog.New(slog.NewTextHandler(&logs, &slog.HandlerOptions{Level: slog.LevelDebug})))
	tr.loc = zone
	tr.now = func() time.Time { return *now }
	return tr, &logs, path
}

func running(ids ...int) fakeGuests {
	var g []proxmox.Guest
	for _, id := range ids {
		g = append(g, proxmox.Guest{VMID: id, Status: "running", Type: "lxc"})
	}
	return fakeGuests{g: g}
}

func TestParseTrimmedTheMeasuredOutput(t *testing.T) {
	b, m := ParseTrimmed(measuredOut)
	if b != measuredBytes || m != 2 {
		t.Fatalf("ParseTrimmed = %d bytes over %d mounts, want %d over 2", b, m, measuredBytes)
	}
	if b, m := ParseTrimmed("something else\n"); b != 0 || m != 0 {
		t.Fatalf("unrelated output parsed as %d/%d", b, m)
	}
	if got := GiB(measuredBytes); got != "84.0 GiB" {
		t.Fatalf("GiB = %q", got)
	}
}

// The night window (01:00–06:59) must never be eligible, and the daytime window is exactly 10:00–20:59.
func TestEligibleHourNeverInTheNight(t *testing.T) {
	for h := 0; h < 24; h++ {
		lt := time.Date(2026, 10, 7, h, 30, 0, 0, zone)
		got := EligibleHour(lt)
		if h >= 1 && h <= 6 && got {
			t.Errorf("hour %02d is in the night window and must not be eligible", h)
		}
		if want := h >= 10 && h <= 20; got != want {
			t.Errorf("EligibleHour(%02d:30) = %v, want %v", h, got, want)
		}
	}
}

func TestWeekAnchorIsTheLastWednesdayTen(t *testing.T) {
	cases := map[time.Time]time.Time{
		at(7, 10, 0):  at(7, 10, 0),                              // Wednesday 10:00 itself
		at(7, 9, 59):  time.Date(2026, 9, 30, 10, 0, 0, 0, zone), // before 10:00 Wednesday → the previous week
		at(8, 15, 0):  at(7, 10, 0),                              // Thursday
		at(13, 20, 0): at(7, 10, 0),                              // next Tuesday
		at(14, 11, 0): at(14, 10, 0),                             // next Wednesday
	}
	for in, want := range cases {
		if got := weekAnchor(in); !got.Equal(want) {
			t.Errorf("weekAnchor(%s) = %s, want %s", in.Format("Mon 01-02 15:04"), got.Format("Mon 01-02 15:04"), want.Format("Mon 01-02 15:04"))
		}
	}
}

// The consequence: on Wednesday 10:30 a running owned guest is trimmed with the ONE exact argv, the bytes are parsed,
// the positive log line is written, the result is persisted, and the host report carries it.
func TestPassTrimsADueGuestAndReportsIt(t *testing.T) {
	now := at(7, 10, 30)
	r := &fakeRunner{out: measuredOut}
	tr, logs, path := newT(t, r, running(9201), &backup.InFlight{}, &now)
	tr.Pass(context.Background())

	if want := [][]string{{"pct", "fstrim", "9201"}}; !reflect.DeepEqual(r.calls, want) {
		t.Fatalf("runner calls = %q, want %q", r.calls, want)
	}
	if !strings.Contains(logs.String(), "fstrim: guest 9201 trimmed 84.0 GiB in ") {
		t.Fatalf("no positive per-guest log line:\n%s", logs.String())
	}
	st := tr.GuestDiskTrimStatus(context.Background())
	if st == nil || st.Schedule != ScheduleText || len(st.Guests) != 1 {
		t.Fatalf("report stanza = %+v", st)
	}
	g := st.Guests[0]
	if g.VMID != 9201 || !g.OK || g.BytesTrimmed != measuredBytes || g.Mounts != 2 || g.LastOKAt == "" || g.LastAttemptAt == "" {
		t.Fatalf("report guest = %+v", g)
	}
	// Persisted: a NEW Trimmer over the same file (an agent restart) still has it and does not trim again this week.
	now = at(8, 11, 0)
	r2 := &fakeRunner{out: measuredOut}
	tr2 := New(r2, running(9201), &backup.InFlight{}, path, slog.New(slog.NewTextHandler(&bytes.Buffer{}, nil)))
	tr2.loc, tr2.now = zone, func() time.Time { return now }
	if st2 := tr2.GuestDiskTrimStatus(context.Background()); len(st2.Guests) != 1 || st2.Guests[0].BytesTrimmed != measuredBytes {
		t.Fatalf("result lost over a restart: %+v", st2)
	}
	tr2.Pass(context.Background())
	if len(r2.calls) != 0 {
		t.Fatalf("trimmed again in the same week after a restart: %q", r2.calls)
	}
	// Next week it is due again.
	now = at(14, 10, 5)
	tr2.Pass(context.Background())
	if len(r2.calls) != 1 {
		t.Fatalf("not trimmed in the next week: %q", r2.calls)
	}
}

func TestPassNeverRunsInTheNight(t *testing.T) {
	for _, h := range []int{1, 3, 6, 9, 21, 23} {
		now := at(7, h, 15)
		r := &fakeRunner{out: measuredOut}
		tr, _, _ := newT(t, r, running(9201), &backup.InFlight{}, &now)
		tr.Pass(context.Background())
		if len(r.calls) != 0 {
			t.Errorf("trimmed at %02d:15: %q", h, r.calls)
		}
	}
}

// A backup (or restore-test) holding the heavy-op gate DEFERS the trim; the next hour, gate free, it runs. And while
// a trim runs, the gate is held, so a backup cannot start beside it.
func TestPassDefersToAHeavyOperationAndRetriesNextHour(t *testing.T) {
	now := at(7, 10, 30)
	gate := &backup.InFlight{}
	release, _, _ := gate.TryAcquire("backup:9201")
	var busyDuringTrim string
	r := &fakeRunner{out: measuredOut}
	r.onRun = func() { busyDuringTrim = gate.Busy() }
	tr, logs, _ := newT(t, r, running(9201), gate, &now)

	tr.Pass(context.Background())
	if len(r.calls) != 0 {
		t.Fatalf("trimmed beside a running backup: %q", r.calls)
	}
	if !strings.Contains(logs.String(), "fstrim: deferred") || !strings.Contains(logs.String(), "backup:9201") {
		t.Fatalf("the deferral is not logged with what holds the gate:\n%s", logs.String())
	}
	release()
	now = now.Add(time.Hour)
	tr.Pass(context.Background())
	if len(r.calls) != 1 {
		t.Fatalf("not retried the next hour: %q", r.calls)
	}
	if busyDuringTrim != GateName {
		t.Fatalf("the heavy-op gate was %q during the trim, want %q", busyDuringTrim, GateName)
	}
	if gate.Busy() != "" {
		t.Fatalf("the gate was not released after the pass: %q", gate.Busy())
	}
}

func TestFailedTrimWarnsIsRecordedAndRetriedAtMostThreeTimes(t *testing.T) {
	now := at(7, 10, 30)
	r := &fakeRunner{err: errors.New("exit status 255")}
	tr, logs, _ := newT(t, r, running(9201), &backup.InFlight{}, &now)
	for i := 0; i < 6; i++ {
		tr.Pass(context.Background())
		now = now.Add(time.Hour)
	}
	if len(r.calls) != MaxAttemptsPerWeek {
		t.Fatalf("attempts in one week = %d, want %d", len(r.calls), MaxAttemptsPerWeek)
	}
	if !strings.Contains(logs.String(), "level=WARN") || !strings.Contains(logs.String(), "fstrim: guest 9201 trim FAILED") {
		t.Fatalf("no WARN for the failure:\n%s", logs.String())
	}
	g := tr.GuestDiskTrimStatus(context.Background()).Guests[0]
	if g.OK || g.LastOKAt != "" || !strings.Contains(g.Error, "exit status 255") || !strings.Contains(g.Error, "mount busy") {
		t.Fatalf("failed result not recorded as a failure: %+v", g)
	}
	// A success later keeps a clean record.
	r.err = nil
	r.out = measuredOut
	now = at(14, 10, 10)
	tr.Pass(context.Background())
	if g := tr.GuestDiskTrimStatus(context.Background()).Guests[0]; !g.OK || g.Error != "" || g.BytesTrimmed != measuredBytes {
		t.Fatalf("success after failure: %+v", g)
	}
}

func TestOnlyRunningOwnedGuestsAndAFailedListActsOnNothing(t *testing.T) {
	now := at(7, 10, 30)
	r := &fakeRunner{out: measuredOut}
	g := fakeGuests{g: []proxmox.Guest{{VMID: 9201, Status: "stopped"}, {VMID: 9202, Status: "running"}}}
	tr, _, _ := newT(t, r, g, &backup.InFlight{}, &now)
	tr.Pass(context.Background())
	if want := [][]string{{"pct", "fstrim", "9202"}}; !reflect.DeepEqual(r.calls, want) {
		t.Fatalf("calls = %q, want only the running guest", r.calls)
	}
	r2 := &fakeRunner{out: measuredOut}
	tr2, logs, _ := newT(t, r2, fakeGuests{err: errors.New("pool read 403")}, &backup.InFlight{}, &now)
	tr2.Pass(context.Background())
	if len(r2.calls) != 0 || !strings.Contains(logs.String(), "owned-guest list unavailable") {
		t.Fatalf("a failed ownership read must act on nothing: calls %q", r2.calls)
	}
}

func TestReportJSONShape(t *testing.T) {
	now := at(7, 10, 30)
	tr, _, _ := newT(t, &fakeRunner{out: measuredOut}, running(9201), &backup.InFlight{}, &now)
	tr.Pass(context.Background())
	b, err := json.Marshal(tr.GuestDiskTrimStatus(context.Background()))
	if err != nil {
		t.Fatal(err)
	}
	for _, k := range []string{`"schedule":`, `"guests":[{"vmid":9201`, `"last_attempt_at":"2026-10-07T08:30:00Z"`, `"ok":true`,
		`"bytes_trimmed":90143313920`, `"mounts":2`, `"duration_seconds":`, `"last_ok_at":"2026-10-07T08:30:00Z"`} {
		if !strings.Contains(string(b), k) {
			t.Errorf("report JSON lacks %s: %s", k, b)
		}
	}
	if strings.Contains(string(b), `"error"`) {
		t.Errorf("an ok result must omit error: %s", b)
	}
}