608962441b
Closes the schedule reconciliation loop end-to-end.
* New `internal/agent/scheduler` package wraps robfig/cron/v3 with
the lifecycle the agent needs:
- Apply(ScheduleSetPayload, Sender) stops the prior cron (waiting
for in-flight entries to return), rebuilds from scratch, starts,
and emits schedule.ack with the version we just applied.
- Disabled entries skipped silently; bad cron exprs (which
shouldn't reach us — the server validates — but defensive)
log a warn and skip.
- On each cron tick the entry sends a new schedule.fire envelope
to the server with {schedule_id, scheduled_at}. The scheduler
itself never builds CommandRunPayloads — server is the source
of truth for jobs.
- tx is swapped on every Apply, so reconnect is handled
naturally: cron entries that fire against a dropped tx log
"no active connection" and skip the tick.
- Stop() is idempotent and waits for the cron's in-flight
workers via cron.Stop().Done().
* New wire message api.MsgScheduleFire + api.ScheduleFirePayload
for the agent → server "I just fired locally" RPC.
* Server-side dispatch (schedule_push.go: dispatchScheduledJob):
looks up the schedule by id, validates ownership + that it's
enabled, builds args from kind (paths for backup; other kinds
are still arg-less in Phase 2 and grow as those job kinds land
in P2-05..08), persists a jobs row with actor_kind=schedule +
scheduled_id, and writes command.run back on the same conn so
the agent runs through its existing dispatch path.
* store.CreateJob now writes scheduled_id. This column was in the
schema since 0001 but never populated — the original P1 path
only had operator-driven jobs, so actor_kind was always 'user'
and scheduled_id was always nil.
* cmd/agent/main.go integration: dispatcher gains a
*scheduler.Scheduler; the MsgScheduleSet case now hands the
payload to scheduler.Apply (in a goroutine so the WS read loop
keeps draining other messages).
* WS dispatcher gains OnScheduleFire alongside OnScheduleAck.
* Tests:
- scheduler unit tests (4): ack-on-apply, cron tick fires
schedule.fire envelope, disabled entries don't fire, replace-
prior-state stops the old cron.
- Server-side end-to-end: schedule.fire → command.run with the
right job_id / kind / args, plus jobs row with actor_kind=
"schedule" and scheduled_id linking back to the schedule.
Persistence of next-fire times across agent restarts is
deliberately deferred. A missed fire window during downtime
simply fires once on reconnect — that's the desirable behaviour
(the operator wants the missed backup to run, not be silently
skipped because we lost track of when it was due).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
160 lines
3.6 KiB
Go
160 lines
3.6 KiB
Go
package scheduler
|
|
|
|
import (
|
|
"sync"
|
|
"testing"
|
|
"time"
|
|
|
|
"gitea.dcglab.co.uk/steve/restic-manager/internal/api"
|
|
)
|
|
|
|
// recSender is a Sender that records every envelope it gets. Tests
|
|
// inspect it after a tick to assert the right messages were emitted.
|
|
type recSender struct {
|
|
mu sync.Mutex
|
|
envs []api.Envelope
|
|
}
|
|
|
|
func (r *recSender) Send(env api.Envelope) error {
|
|
r.mu.Lock()
|
|
defer r.mu.Unlock()
|
|
r.envs = append(r.envs, env)
|
|
return nil
|
|
}
|
|
|
|
func (r *recSender) snapshot() []api.Envelope {
|
|
r.mu.Lock()
|
|
defer r.mu.Unlock()
|
|
out := make([]api.Envelope, len(r.envs))
|
|
copy(out, r.envs)
|
|
return out
|
|
}
|
|
|
|
func TestApplyEmitsAck(t *testing.T) {
|
|
t.Parallel()
|
|
tx := &recSender{}
|
|
s := New()
|
|
defer s.Stop()
|
|
|
|
s.Apply(api.ScheduleSetPayload{
|
|
Version: 7,
|
|
Schedules: []api.Schedule{
|
|
{ID: "s1", Kind: api.JobBackup, CronExpr: "@hourly", Enabled: true},
|
|
},
|
|
}, tx)
|
|
|
|
if got := s.Version(); got != 7 {
|
|
t.Fatalf("Version: got %d, want 7", got)
|
|
}
|
|
|
|
envs := tx.snapshot()
|
|
if len(envs) != 1 {
|
|
t.Fatalf("expected 1 envelope (ack), got %d", len(envs))
|
|
}
|
|
if envs[0].Type != api.MsgScheduleAck {
|
|
t.Fatalf("envelope type: got %s, want %s", envs[0].Type, api.MsgScheduleAck)
|
|
}
|
|
var ack api.ScheduleAckPayload
|
|
_ = envs[0].UnmarshalPayload(&ack)
|
|
if ack.Version != 7 {
|
|
t.Fatalf("ack version: got %d", ack.Version)
|
|
}
|
|
}
|
|
|
|
func TestApplyTickFiresScheduleFire(t *testing.T) {
|
|
t.Parallel()
|
|
tx := &recSender{}
|
|
s := New()
|
|
defer s.Stop()
|
|
|
|
// Cron expression that fires roughly every second; close enough
|
|
// to be reliable in CI without making the test slow.
|
|
s.Apply(api.ScheduleSetPayload{
|
|
Version: 1,
|
|
Schedules: []api.Schedule{
|
|
{ID: "every-second", Kind: api.JobBackup, CronExpr: "@every 1s", Enabled: true},
|
|
},
|
|
}, tx)
|
|
|
|
deadline := time.Now().Add(3 * time.Second)
|
|
for time.Now().Before(deadline) {
|
|
envs := tx.snapshot()
|
|
for _, e := range envs {
|
|
if e.Type == api.MsgScheduleFire {
|
|
var p api.ScheduleFirePayload
|
|
_ = e.UnmarshalPayload(&p)
|
|
if p.ScheduleID == "every-second" {
|
|
return
|
|
}
|
|
}
|
|
}
|
|
time.Sleep(50 * time.Millisecond)
|
|
}
|
|
t.Fatal("schedule.fire did not arrive within 3s")
|
|
}
|
|
|
|
func TestApplyDisabledEntriesSkipped(t *testing.T) {
|
|
t.Parallel()
|
|
tx := &recSender{}
|
|
s := New()
|
|
defer s.Stop()
|
|
|
|
s.Apply(api.ScheduleSetPayload{
|
|
Version: 1,
|
|
Schedules: []api.Schedule{
|
|
{ID: "off", Kind: api.JobBackup, CronExpr: "@every 1s", Enabled: false},
|
|
},
|
|
}, tx)
|
|
|
|
// A disabled schedule must never fire — give the cron a couple
|
|
// of ticks to confirm it's silent.
|
|
time.Sleep(2200 * time.Millisecond)
|
|
for _, e := range tx.snapshot() {
|
|
if e.Type == api.MsgScheduleFire {
|
|
t.Fatalf("disabled schedule fired: %+v", e)
|
|
}
|
|
}
|
|
}
|
|
|
|
func TestApplyReplacesPriorState(t *testing.T) {
|
|
t.Parallel()
|
|
tx := &recSender{}
|
|
s := New()
|
|
defer s.Stop()
|
|
|
|
s.Apply(api.ScheduleSetPayload{
|
|
Version: 1,
|
|
Schedules: []api.Schedule{
|
|
{ID: "old", Kind: api.JobBackup, CronExpr: "@every 1s", Enabled: true},
|
|
},
|
|
}, tx)
|
|
|
|
// Wait long enough for the first version to fire at least once.
|
|
time.Sleep(1500 * time.Millisecond)
|
|
|
|
// Now replace with version 2 that doesn't include "old".
|
|
s.Apply(api.ScheduleSetPayload{
|
|
Version: 2,
|
|
Schedules: []api.Schedule{},
|
|
}, tx)
|
|
|
|
// Snapshot count *after* the replacement.
|
|
before := 0
|
|
for _, e := range tx.snapshot() {
|
|
if e.Type == api.MsgScheduleFire {
|
|
before++
|
|
}
|
|
}
|
|
time.Sleep(2 * time.Second)
|
|
after := 0
|
|
for _, e := range tx.snapshot() {
|
|
if e.Type == api.MsgScheduleFire {
|
|
after++
|
|
}
|
|
}
|
|
if after != before {
|
|
t.Fatalf("schedule.fire count grew after replacement (before=%d after=%d) — old cron still firing",
|
|
before, after)
|
|
}
|
|
}
|