The Scheduler that D4 was waiting on. Built against CORE's engine
HEADERS (now in main); the real EnginePort and the veloxd wiring wait
for lane/core's stage-8 bodies to reach main (deferrals.md D4a/D4b) —
core/src/task/ is still .gitkeep there, so linking vdm::Engine now
would be an unresolved symbol.
- sched/engine_port — the abstract seam: start/pause/resume/cancel/
provide_auth/decide/refresh_url + the ADR 0011 admission config
(set_task_order / set_max_active_segments / set_host_segment_cap).
Keeps the Scheduler testable without a live engine and the daemon
unbound from the concrete vdm::Engine.
- sched/fake_engine_port — a recording impl for tests.
- sched/scheduler:
* owns the wire-UUID <-> vdm::TaskId map.
* tick(): snapshot queues (schedule window evaluated with an
injectable clock) + non-terminal tasks -> governor.evaluate ->
apply. to_start builds a vdm::task::DownloadSpec from the row and
calls EnginePort::start; to_resume -> resume(); to_pause ->
pause() + writes the pause_reason; priority_order -> set_task_order
over the mapped engine ids. `new` tasks are parked (startMode
manual) and skipped.
* on_engine_state(wire_id, state, err): projects an engine
transition onto the store row (state, pause_reason='auto' when an
error rides a paused transition per ADR 0013 §2, flattened error
columns) so the next tick sees ground truth. This is also the hook
event.task.state will fire from (D5).
* reconcile_after_restart(): CORE-owned states -> queued, paused
keeps its reason (ADR 0013 §5).
* reload_config(): reads connection.maxConcurrentDownloads /
maxActiveSegments + a daemon-local host-cap map, pushes caps to
the engine, updates the governor.
* Deps: injectable local-now clock and a post_to_loop marshaller
(engine callbacks arrive on engine threads; default runs inline
for tests).
Test veloxd.sched_scheduler (ASan+UBSan and TSan clean): admission +
ordering, a slot freeing on completion, queue-stop -> pause
(queue_stopped) then queue-restart -> resume (not a fresh start),
engine auto-pause -> pause_reason 'auto' + never auto-resumed,
reconcile_after_restart, reload_config caps push. 35 daemon/cli tests
green.
Co-Authored-By: Claude Sonnet 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01Upd9WhG9oppieig5nRDLig
192 lines
8.0 KiB
C++
192 lines
8.0 KiB
C++
// Scheduler against a FakeEnginePort and an in-memory store: admission, priority order,
|
|
// queue stop, restart reconciliation, and the engine-state -> store projection.
|
|
|
|
#include <string>
|
|
|
|
#include "check.hpp"
|
|
#include "sched/fake_engine_port.hpp"
|
|
#include "sched/governor.hpp"
|
|
#include "sched/scheduler.hpp"
|
|
#include "store/migrations.hpp"
|
|
#include "store/settings.hpp"
|
|
#include "store/sqlite.hpp"
|
|
#include "store/tasks.hpp"
|
|
|
|
using namespace velox::daemon;
|
|
using sched::FakeEnginePort;
|
|
using sched::Governor;
|
|
using sched::GovernorConfig;
|
|
using sched::Scheduler;
|
|
|
|
namespace {
|
|
|
|
store::TaskRow task(std::string id, std::string state, std::string created,
|
|
std::optional<std::string> queue = std::nullopt, std::int64_t pos = 0) {
|
|
store::TaskRow r;
|
|
r.task_id = std::move(id);
|
|
r.url = "https://cdn.example/" + r.task_id;
|
|
r.save_dir = "/tmp";
|
|
r.filename = r.task_id + ".bin";
|
|
r.state = std::move(state);
|
|
r.created_at = std::move(created);
|
|
r.queue_id = std::move(queue);
|
|
if (r.queue_id) r.queue_position = pos;
|
|
return r;
|
|
}
|
|
|
|
std::string task_state(store::Db& db, const std::string& id) {
|
|
store::Tasks t(db);
|
|
auto g = t.get(id);
|
|
return (g && *g) ? (*g)->state : std::string("<none>");
|
|
}
|
|
|
|
} // namespace
|
|
|
|
void run() {
|
|
auto db = store::Db::open(":memory:");
|
|
CHECK(db.has_value());
|
|
if (!db) return;
|
|
CHECK(store::migrate_to_head(*db).has_value());
|
|
store::Tasks tasks(*db);
|
|
|
|
// --- admission: 4 queued, cap 2 -> start the 2 oldest, in order -----------------
|
|
{
|
|
FakeEnginePort engine;
|
|
Scheduler sched(*db, engine,
|
|
Governor(GovernorConfig{.max_concurrent_downloads = 2,
|
|
.max_active_segments = 32}));
|
|
for (int i = 0; i < 4; ++i)
|
|
CHECK(tasks.insert(task("a" + std::to_string(i), "queued",
|
|
"2026-09-10T10:0" + std::to_string(i) + ":00Z"))
|
|
.has_value());
|
|
|
|
CHECK(sched.tick().has_value());
|
|
CHECK_EQ(engine.starts.size(), 2u);
|
|
CHECK_EQ(engine.starts[0].url, std::string("https://cdn.example/a0"));
|
|
CHECK_EQ(engine.starts[1].url, std::string("https://cdn.example/a1"));
|
|
CHECK_EQ(engine.starts[0].save_path, std::string("/tmp/a0.bin"));
|
|
CHECK_EQ(task_state(*db, "a0"), std::string("probing"));
|
|
CHECK_EQ(task_state(*db, "a2"), std::string("queued")); // not admitted
|
|
|
|
// set_task_order carries exactly the started tasks, oldest first.
|
|
CHECK_EQ(engine.last_order().size(), 2u);
|
|
CHECK(engine.last_order()[0] == engine.starts[0].id);
|
|
|
|
// A second tick with no free slots starts nothing new.
|
|
CHECK(sched.tick().has_value());
|
|
CHECK_EQ(engine.starts.size(), 2u);
|
|
}
|
|
|
|
// --- engine reports downloading, then one completes -> a slot frees ------------
|
|
{
|
|
for (const char* id : {"a0", "a1", "a2", "a3"}) tasks.remove(id);
|
|
FakeEnginePort engine;
|
|
Scheduler sched(*db, engine,
|
|
Governor(GovernorConfig{.max_concurrent_downloads = 1,
|
|
.max_active_segments = 32}));
|
|
CHECK(tasks.insert(task("b0", "queued", "2026-09-10T10:00:00Z")).has_value());
|
|
CHECK(tasks.insert(task("b1", "queued", "2026-09-10T10:01:00Z")).has_value());
|
|
|
|
CHECK(sched.tick().has_value());
|
|
CHECK_EQ(engine.starts.size(), 1u); // b0 only
|
|
CHECK_EQ(task_state(*db, "b0"), std::string("probing"));
|
|
|
|
sched.on_engine_state("b0", "downloading", std::nullopt);
|
|
CHECK_EQ(task_state(*db, "b0"), std::string("downloading"));
|
|
|
|
sched.on_engine_state("b0", "complete", std::nullopt);
|
|
CHECK_EQ(task_state(*db, "b0"), std::string("complete"));
|
|
|
|
CHECK(sched.tick().has_value()); // b0 terminal -> b1 admitted
|
|
CHECK_EQ(engine.starts.size(), 2u);
|
|
CHECK_EQ(engine.starts[1].url, std::string("https://cdn.example/b1"));
|
|
}
|
|
|
|
// --- a stopped queue: running tasks get paused with reason queue_stopped -------
|
|
{
|
|
for (const char* id : {"b0", "b1"}) tasks.remove(id);
|
|
CHECK(db->exec("UPDATE queues SET state='running' WHERE queue_id='main'").has_value());
|
|
FakeEnginePort engine;
|
|
Scheduler sched(*db, engine,
|
|
Governor(GovernorConfig{.max_concurrent_downloads = 10,
|
|
.max_active_segments = 32}));
|
|
CHECK(tasks.insert(task("q0", "queued", "2026-09-10T10:00:00Z", "main", 0)).has_value());
|
|
CHECK(sched.tick().has_value());
|
|
CHECK_EQ(engine.starts.size(), 1u);
|
|
sched.on_engine_state("q0", "downloading", std::nullopt);
|
|
|
|
CHECK(db->exec("UPDATE queues SET state='stopped' WHERE queue_id='main'").has_value());
|
|
CHECK(sched.tick().has_value());
|
|
CHECK_EQ(engine.paused.size(), 1u);
|
|
CHECK_EQ(task_state(*db, "q0"), std::string("paused"));
|
|
store::Tasks t(*db);
|
|
CHECK_EQ(t.get("q0").value().value().pause_reason.value_or(""), std::string("queue_stopped"));
|
|
|
|
// Restart the queue -> the task resumes (not a fresh start).
|
|
CHECK(db->exec("UPDATE queues SET state='running' WHERE queue_id='main'").has_value());
|
|
CHECK(sched.tick().has_value());
|
|
CHECK_EQ(engine.resumed.size(), 1u);
|
|
CHECK_EQ(engine.starts.size(), 1u); // no new start
|
|
}
|
|
|
|
// --- an engine auto-pause (error present) -> pause_reason 'auto', not touched --
|
|
{
|
|
for (const char* id : {"q0"}) tasks.remove(id);
|
|
FakeEnginePort engine;
|
|
Scheduler sched(*db, engine,
|
|
Governor(GovernorConfig{.max_concurrent_downloads = 10,
|
|
.max_active_segments = 32}));
|
|
CHECK(tasks.insert(task("auth", "queued", "2026-09-10T10:00:00Z")).has_value());
|
|
CHECK(sched.tick().has_value());
|
|
|
|
sched::TaskErrorFields ef;
|
|
ef.code = "auth_required";
|
|
ef.message = "401";
|
|
ef.http_status = 401;
|
|
sched.on_engine_state("auth", "paused", ef);
|
|
|
|
store::Tasks t(*db);
|
|
auto row = t.get("auth").value().value();
|
|
CHECK_EQ(row.state, std::string("paused"));
|
|
CHECK_EQ(row.pause_reason.value_or(""), std::string("auto"));
|
|
CHECK_EQ(row.error_code.value_or(""), std::string("auth_required"));
|
|
|
|
// A tick must NOT resume an auto-paused task.
|
|
engine.resumed.clear();
|
|
CHECK(sched.tick().has_value());
|
|
CHECK_EQ(engine.resumed.size(), 0u);
|
|
}
|
|
|
|
// --- reconcile_after_restart: CORE-owned states -> queued --------------------
|
|
{
|
|
for (const char* id : {"auth"}) tasks.remove(id);
|
|
CHECK(tasks.insert(task("r0", "downloading", "2026-09-10T10:00:00Z")).has_value());
|
|
CHECK(tasks.insert(task("r1", "verifying", "2026-09-10T10:01:00Z")).has_value());
|
|
CHECK(tasks.insert(task("r2", "paused", "2026-09-10T10:02:00Z")).has_value());
|
|
CHECK(db->exec("UPDATE tasks SET pause_reason='user' WHERE task_id='r2'").has_value());
|
|
|
|
FakeEnginePort engine;
|
|
Scheduler sched(*db, engine, Governor(GovernorConfig{}));
|
|
CHECK(sched.reconcile_after_restart().has_value());
|
|
CHECK_EQ(task_state(*db, "r0"), std::string("queued"));
|
|
CHECK_EQ(task_state(*db, "r1"), std::string("queued"));
|
|
CHECK_EQ(task_state(*db, "r2"), std::string("paused")); // paused survives
|
|
store::Tasks t(*db);
|
|
CHECK_EQ(t.get("r2").value().value().pause_reason.value_or(""), std::string("user"));
|
|
}
|
|
|
|
// --- reload_config pushes the caps to the engine ---------------------------
|
|
{
|
|
store::Settings settings(*db);
|
|
CHECK(settings.set_raw("connection.maxActiveSegments", "12").has_value());
|
|
FakeEnginePort engine;
|
|
Scheduler sched(*db, engine, Governor(GovernorConfig{}));
|
|
CHECK(sched.reload_config().has_value());
|
|
CHECK_EQ(engine.max_active_segments.size(), 1u);
|
|
CHECK_EQ(engine.max_active_segments.back(), 12u);
|
|
CHECK_EQ(sched.reload_config().has_value() ? 0 : 1, 0);
|
|
}
|
|
}
|
|
|
|
TEST_MAIN()
|