myxce/src/scheduler/testsuite/test_sim_startup.c

/*
 * test_sim_startup.c - contract test for simulation-mode startup
 * (scheduler-core spec, task 11.1, Req 5 AC 13).
 *
 * Observable under test (task 11.1's own text):
 *   - starting simulation against a valid fixture file reaches a
 *     ready-to-run state with the virtual clock reporting the snapshot's
 *     timestamp.
 *   - starting against a file missing its initial snapshot entry fails with
 *     a clear error before any event is processed.
 *
 * Fixture strategy: rather than hand-constructing capnp bytes, this file
 * builds REAL, valid `.replay` fixtures via the SAME production code path
 * normal-mode recording already uses (sched_record_start()/
 * sched_record_stop(), task 9.2) against a small real xce_scheduler_t
 * fixture -- same technique test_record_lifecycle.c already establishes.
 * The "missing initial snapshot entry" fixture is then derived from a valid
 * one by truncating it to exactly its first message (the ReplayHeader),
 * discovered by decoding that one message and reading the resulting file
 * offset -- no hand-rolled capnp byte construction needed for that case
 * either. The "first message is not a valid ReplayHeader" and "first data
 * message is not a SnapshotEntry" fixtures DO hand-construct one wrong-
 * shaped message directly (same technique test_e2e_capnp.c/
 * test_record_lifecycle.c already use for building capnp messages by hand),
 * since there is no production code path that ever writes a malformed
 * stream to reuse.
 *
 * White-box #include of ../src/core.c, ../src/core_clock.c (task 11.1's own
 * code under test, sim.c, needs both -- xce_sched_core_init/fini and
 * xce_core_now()) PLUS ../src/snapshot.c, ../src/snapshot_wire.c,
 * ../src/snapshot_load.c (task 8.1's real save/load, needed both to BUILD
 * the fixture via sched_record_start() and to exercise sim.c's own
 * xce_sched_core_load_snapshot() call) PLUS ../src/recording.c (real
 * sched_record_start()/sched_record_stop(), used ONLY to build fixtures --
 * this file never asserts anything about recording.c's own behavior, that
 * is test_record_lifecycle.c's job) PLUS ../src/sim.c (the code under
 * test). No driver.c/plugin.c/core_events.c/core_session.c/decision.c: this
 * file never drives a real scheduling session (task 11.1 stops at
 * "ready-to-run", not the event loop), so none of those are needed.
 *
 * Stubs below mirror the exact same link-satisfying set
 * test_record_lifecycle.c/test_driver_session_ordering.c already establish
 * for this core.c/core_clock.c/snapshot.c/snapshot_wire.c/snapshot_load.c/
 * recording.c combination (kill_sched_*, sched_resolve_job_picker's real
 * reimplementation -- schedobj.c is not linked).
 */
#include <errno.h>
#include <limits.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>

#include <unity/unity.h>

#include "controller.capnp.h"
#include "kvmgr.h"
#include "scheduler.h"
#include "xstring.h"

/* Pull in the real functions under test into this TU (white-box #include,
 * same convention as test_record_lifecycle.c). */
#include "../src/core.c"
#include "../src/core_clock.c"
#include "../src/recording.c"
#include "../src/sim.c"
#include "../src/snapshot.c"
#include "../src/snapshot_load.c"
#include "../src/snapshot_wire.c"

void kill_sched_job(void* arg) { (void)arg; }
void kill_sched_queue(void* arg) { (void)arg; }
void kill_sched_worker(void* arg) { (void)arg; }
void kill_sched_user(void* arg) { (void)arg; }
void kill_sched_project(void* arg) { (void)arg; }
void kill_sched_resval(xce_val_t* val) { (void)val; }

/* plugin.c is not linked into this TU (no session is ever driven, so no
 * real plugin unregistration ever happens) -- same stub every other
 * core.c-including test file in this directory establishes for
 * xce_sched_core_init()'s kvmgr datakiller. */
void plugin_unregister(void* arg) { (void)arg; }

/* Real reimplementation of schedobj.c's sched_resolve_job_picker -- same
 * rationale/algorithm as test_record_lifecycle.c's own copy (schedobj.c is
 * not linked). Both the FIXTURE core (built via a real xce_scheduler_t,
 * needs a resolvable picker for sched_record_start()'s own snapshot to be
 * well-formed) and sim.c's own core (which never registers a picker, per
 * sim.h's documented scope boundary -- this will legitimately return
 * -EINVAL/-ENOENT for that core, which xce_sched_core_load_snapshot()
 * gracefully WARNs and skips) share this one implementation. */
int sched_resolve_job_picker(xce_sched_core_t* core, xce_sched_plugin_t** out)
{
    xce_sched_plugin_t* plugin = NULL;
    int                 rc     = 0;

    if ((core == NULL) || (out == NULL)) {
        return -EINVAL;
    }

    *out = NULL;

    if (core->job_pick_plugin == NULL) {
        return -EINVAL;
    }

    lock(core->plugins, RTTI_LOCK_READ);
    rc = key_find(core->plugins, core->job_pick_plugin, (void**)&plugin);
    unlock(core->plugins);

    if (rc <= 0) {
        return (rc < 0) ? rc : -ENOENT;
    }

    if ((plugin == NULL) || (plugin->picker_iface == NULL)
        || (plugin->picker_iface->next_job == NULL)
        || (plugin->picker_iface->begin_session == NULL)
        || (plugin->picker_iface->end_session == NULL)
        || (plugin->picker_iface->on_dispatch == NULL)
        || (plugin->picker_iface->on_pend == NULL)) {
        return -EINVAL;
    }

    *out = plugin;

    return 0;
}

void setUp(void) { return; }
void tearDown(void) { return; }

/* ---------------------------------------------------------------------- */
/* Fixture helpers                                                         */
/* ---------------------------------------------------------------------- */

static void make_tmp_dir(char* out, size_t out_len, const char* suffix)
{
    char tmpl[PATH_MAX];

    snprintf(tmpl, sizeof(tmpl), "/tmp/sched_simstart%s_XXXXXX", suffix);
    TEST_ASSERT_NOT_NULL(mkdtemp(tmpl));
    TEST_ASSERT_TRUE(strlen(tmpl) < out_len);
    strcpy(out, tmpl);
}

static int stub_picker_begin_session(void* picker)
{
    (void)picker;
    return 0;
}

static xce_sched_job_t* stub_picker_next_job(void* picker)
{
    (void)picker;
    return NULL;
}

static int stub_picker_end_session(void* picker)
{
    (void)picker;
    return 0;
}

static int stub_picker_jobid_noop(void* picker, uint64_t jobid)
{
    (void)picker;
    (void)jobid;
    return 0;
}

static int stub_picker_queue_update_noop(void* picker, xce_sched_queue_t* q)
{
    (void)picker;
    (void)q;
    return 0;
}

static int stub_picker_job_noop(void* picker, xce_sched_job_t* job)
{
    (void)picker;
    (void)job;
    return 0;
}

static int stub_picker_job_state_change_noop(void* picker, xce_sched_job_t* job,
                                             uint32_t state)
{
    (void)picker;
    (void)job;
    (void)state;
    return 0;
}

static xce_job_picker_iface_t g_stub_picker_iface
    = { .init                = NULL,
        .fini                = NULL,
        .begin_session       = stub_picker_begin_session,
        .next_job            = stub_picker_next_job,
        .end_session         = stub_picker_end_session,
        .on_dispatch         = stub_picker_jobid_noop,
        .on_pend             = stub_picker_jobid_noop,
        .on_queue_update     = stub_picker_queue_update_noop,
        .on_job_push         = stub_picker_job_noop,
        .on_job_state_change = stub_picker_job_state_change_noop,
        .on_job_update       = stub_picker_job_noop,
        .on_config           = NULL,
        .on_job_rusage       = NULL };

static xce_sched_plugin_t g_stub_picker_plugin
    = { .name         = "test_sim_startup_picker",
        .picker_iface = &g_stub_picker_iface };

/* Builds a small, real xce_scheduler_t fixture (same pattern
 * test_record_lifecycle.c's fixture_init() establishes) purely to drive
 * sched_record_start()/sched_record_stop() and produce a REAL, valid
 * `.replay` file this test's OWN code under test (sim.c) then consumes. */
static void build_fixture_scheduler(xce_scheduler_t* sched, char* record_dir)
{
    int rc;

    memset(sched, 0, sizeof(*sched));
    mylock_init(&(sched->record_lock));

    rc = xce_sched_core_init(&(sched->core));
    TEST_ASSERT_EQUAL_INT(0, rc);

    lock(sched->core.plugins, RTTI_LOCK_WRITE);
    rc = key_add(sched->core.plugins, (void*)g_stub_picker_plugin.name,
                 (void*)&g_stub_picker_plugin);
    TEST_ASSERT_GREATER_OR_EQUAL(0, rc);
    unlock(sched->core.plugins);

    sched->core.job_pick_plugin = g_stub_picker_plugin.name;
    sched->record_dir           = record_dir;
}

/* Produces a valid `.replay` fixture (ReplayHeader + initial SnapshotEntry)
 * at `out_path` via the real sched_record_start()/sched_record_stop(); the
 * chosen snapshot timestamp is returned via `out_ts`. */
static void write_valid_fixture(char* out_path, size_t out_path_len,
                                uint64_t* out_ts, const char* suffix)
{
    char            record_dir[PATH_MAX];
    xce_scheduler_t sched;
    int             rc;

    make_tmp_dir(record_dir, sizeof(record_dir), suffix);
    build_fixture_scheduler(&sched, record_dir);

    rc = sched_record_start(&sched, "fixture.replay");
    TEST_ASSERT_EQUAL_INT(0, rc);
    TEST_ASSERT_TRUE(strlen(sched.record_file_path) < out_path_len);
    strcpy(out_path, sched.record_file_path);
    *out_ts = sched.record_start_ts;

    rc = sched_record_stop(&sched);
    TEST_ASSERT_EQUAL_INT(0, rc);
}

/* Truncates `src_path` down to just its first capnp message (the
 * ReplayHeader) and writes the result to `dst_path` -- simulates a replay
 * file whose stream ends immediately after the header, i.e. "missing
 * initial snapshot entry". */
static void truncate_to_header_only(const char* src_path, const char* dst_path)
{
    FILE*       src;
    FILE*       dst;
    struct capn c;
    long        header_end;
    char*       buf;
    size_t      n;

    src = fopen(src_path, "r");
    TEST_ASSERT_NOT_NULL(src);
    TEST_ASSERT_EQUAL_INT(0, capn_init_fp(&c, src, 0));
    capn_free(&c);
    header_end = ftell(src);
    TEST_ASSERT_TRUE(header_end > 0);
    rewind(src);

    buf = (char*)malloc((size_t)header_end);
    TEST_ASSERT_NOT_NULL(buf);
    n = fread(buf, 1, (size_t)header_end, src);
    TEST_ASSERT_EQUAL_UINT((size_t)header_end, n);
    fclose(src);

    dst = fopen(dst_path, "w");
    TEST_ASSERT_NOT_NULL(dst);
    TEST_ASSERT_EQUAL_UINT((size_t)header_end,
                           fwrite(buf, 1, (size_t)header_end, dst));
    fclose(dst);
    free(buf);
}

/* Hand-builds a single capnp message shaped like `SnapshotEntry`
 * (word_count=1, pointer_count=1) but with all-default/empty field
 * contents, and writes it standalone to `path` -- used to simulate a
 * malformed "first message is not ReplayHeader" fixture (ReplayHeader is
 * shaped (1,5); a lone (1,1)-shaped message can never be mistaken for one
 * by sim.c's shape check). */
static void write_lone_snapshotentry_message(const char* path)
{
    struct capn          c;
    struct capn_segment* cs;
    SnapshotData_ptr     sdata;
    SnapshotEntry_ptr    snap;
    FILE*                f;
    int                  rc;

    capn_init_malloc(&c);
    cs = capn_root(&c).seg;

    sdata = new_SnapshotData(cs);
    snap  = new_SnapshotEntry(cs);
    SnapshotEntry_set_ts(snap, 42ULL);
    SnapshotEntry_set_data(snap, sdata);
    capn_setp(capn_root(&c), 0, snap.p);

    f = fopen(path, "w");
    TEST_ASSERT_NOT_NULL(f);
    rc = write_capnp_message(f, &c);
    TEST_ASSERT_EQUAL_INT(0, rc);
    fclose(f);
    capn_free(&c);
}

/* ---------------------------------------------------------------------- */
/* Test 1: starting simulation against a valid fixture file reaches a      */
/* ready-to-run state with the virtual clock reporting the snapshot's      */
/* timestamp -- this task's own primary Observable.                        */
/* ---------------------------------------------------------------------- */

static void
test_valid_fixture_reaches_ready_state_with_frozen_virtual_clock(void)
{
    char                   path[PATH_MAX];
    uint64_t               snapshot_ts = 0;
    sched_sim_args_t       args;
    xce_sched_sim_driver_t sim;
    int                    rc;

    write_valid_fixture(path, sizeof(path), &snapshot_ts, "_valid");
    TEST_ASSERT_TRUE(snapshot_ts > 0);

    memset(&args, 0, sizeof(args));
    args.replay_path  = path;
    args.sim_start_ts = SCHED_SIM_START_TS_LATEST;
    args.sim_speed    = 0; /* fast/frozen -- xce_core_now() stays pinned to
                            * virtual_clock_base regardless of real elapsed
                            * time, giving this test a deterministic,
                            * non-flaky assertion. */

    rc = sched_sim_driver_start(&sim, &args);
    TEST_ASSERT_EQUAL_INT(0, rc);

    /* Step 4's Observable: the virtual clock reports the snapshot's own
     * timestamp, exactly (frozen -- speed_num=0). */
    TEST_ASSERT_EQUAL_UINT64(snapshot_ts, xce_core_now(&(sim.core)));

    /* Direct inspection of the anchors Step 4 documents setting. */
    TEST_ASSERT_EQUAL_UINT64(
        snapshot_ts, atomic_load_explicit(&(sim.core.virtual_clock_base),
                                          memory_order_acquire));
    TEST_ASSERT_EQUAL_UINT64(0ULL, atomic_load_explicit(&(sim.core.speed_num),
                                                        memory_order_acquire));
    TEST_ASSERT_EQUAL_UINT64(1ULL, atomic_load_explicit(&(sim.core.speed_den),
                                                        memory_order_acquire));
    TEST_ASSERT_EQUAL_UINT64(0ULL, sim.sim_speed_num);
    TEST_ASSERT_EQUAL_UINT64(1ULL, sim.sim_speed_den);

    /* "Ready-to-run" -- no session is active, load_snapshot()'s own
     * precondition would otherwise have been violated. */
    TEST_ASSERT_EQUAL_INT(0, atomic_load(&(sim.core.session_active)));

    TEST_ASSERT_NOT_NULL(sim.replay_file);

    printf("test_valid_fixture_reaches_ready_state_with_frozen_virtual_clock:"
           " PASS\n");
}

/* ---------------------------------------------------------------------- */
/* Test 1b (design review follow-up, Req 5 AC 3): sched_sim_driver_start()  */
/* must activate the core's virtual clock for tlog logging -- otherwise    */
/* every log line emitted during a --sim/--interactive run shows real      */
/* wall-clock time instead of the frozen/virtual replay timestamp,         */
/* defeating the whole point of debugging against a replay's own timeline. */
/* g_active_core_for_logging is core_clock.c's module-static (white-box    */
/* #include above puts it in this TU) -- direct inspection is simpler and  */
/* more precise than round-tripping through tlog's own formatter, which    */
/* test_clock.c already covers at the unit level.                          */
/* ---------------------------------------------------------------------- */

static void test_valid_fixture_activates_virtual_clock_for_tlog_logging(void)
{
    char                   path[PATH_MAX];
    uint64_t               snapshot_ts = 0;
    sched_sim_args_t       args;
    xce_sched_sim_driver_t sim;
    int                    rc;

    /* Defensive reset -- other tests in this same process may have left
     * g_active_core_for_logging pointing at a since-destroyed core. */
    xce_core_set_active_for_logging(NULL);

    write_valid_fixture(path, sizeof(path), &snapshot_ts, "_tlogactivate");

    memset(&args, 0, sizeof(args));
    args.replay_path  = path;
    args.sim_start_ts = SCHED_SIM_START_TS_LATEST;
    args.sim_speed    = 0;

    rc = sched_sim_driver_start(&sim, &args);
    TEST_ASSERT_EQUAL_INT(0, rc);

    TEST_ASSERT_EQUAL_PTR(&(sim.core), g_active_core_for_logging);

    xce_core_set_active_for_logging(NULL); /* leave clean for later tests */

    printf("test_valid_fixture_activates_virtual_clock_for_tlog_logging:"
           " PASS\n");
}

/* ---------------------------------------------------------------------- */
/* Test 2: starting against a file missing its initial snapshot entry      */
/* fails with a clear error before any event is processed -- this task's   */
/* own second Observable.                                                  */
/* ---------------------------------------------------------------------- */

static void test_missing_initial_snapshot_entry_fails_cleanly(void)
{
    char                   valid_path[PATH_MAX];
    char                   header_only_path[PATH_MAX + 32];
    uint64_t               snapshot_ts = 0;
    sched_sim_args_t       args;
    xce_sched_sim_driver_t sim;
    int                    rc;

    write_valid_fixture(valid_path, sizeof(valid_path), &snapshot_ts,
                        "_hdronly_src");
    snprintf(header_only_path, sizeof(header_only_path),
             "%s.header_only.replay", valid_path);
    truncate_to_header_only(valid_path, header_only_path);

    memset(&args, 0, sizeof(args));
    args.replay_path  = header_only_path;
    args.sim_start_ts = SCHED_SIM_START_TS_LATEST;
    args.sim_speed    = 1;

    rc = sched_sim_driver_start(&sim, &args);
    TEST_ASSERT_TRUE(rc < 0);

    printf("test_missing_initial_snapshot_entry_fails_cleanly: PASS\n");
}

/* ---------------------------------------------------------------------- */
/* Test 3: a replay file whose FIRST message is not a valid ReplayHeader   */
/* is rejected (Req 5 AC 13 step 1) -- distinct code path from test 2.     */
/* ---------------------------------------------------------------------- */

static void test_first_message_not_replayheader_fails_cleanly(void)
{
    char                   dir[PATH_MAX];
    char                   path[PATH_MAX + 32];
    sched_sim_args_t       args;
    xce_sched_sim_driver_t sim;
    int                    rc;

    make_tmp_dir(dir, sizeof(dir), "_badhdr");
    snprintf(path, sizeof(path), "%s/bad_header.replay", dir);
    write_lone_snapshotentry_message(path);

    memset(&args, 0, sizeof(args));
    args.replay_path  = path;
    args.sim_start_ts = SCHED_SIM_START_TS_LATEST;
    args.sim_speed    = 1;

    rc = sched_sim_driver_start(&sim, &args);
    TEST_ASSERT_TRUE(rc < 0);

    printf("test_first_message_not_replayheader_fails_cleanly: PASS\n");
}

/* ---------------------------------------------------------------------- */
/* Test 4: a missing replay file fails with a clear error (Req 5 AC 13     */
/* step 1, "the file is missing, unreadable").                            */
/* ---------------------------------------------------------------------- */

static void test_missing_replay_file_fails_cleanly(void)
{
    sched_sim_args_t       args;
    xce_sched_sim_driver_t sim;
    int                    rc;

    memset(&args, 0, sizeof(args));
    args.replay_path  = "/nonexistent/path/does_not_exist.replay";
    args.sim_start_ts = SCHED_SIM_START_TS_LATEST;
    args.sim_speed    = 1;

    rc = sched_sim_driver_start(&sim, &args);
    TEST_ASSERT_TRUE(rc < 0);

    printf("test_missing_replay_file_fails_cleanly: PASS\n");
}

/* ---------------------------------------------------------------------- */
/* Test 5: NULL argument guards.                                           */
/* ---------------------------------------------------------------------- */

static void test_null_arguments_return_einval(void)
{
    xce_sched_sim_driver_t sim;
    sched_sim_args_t       args;

    memset(&args, 0, sizeof(args));
    args.replay_path = "/tmp/does-not-matter.replay";

    TEST_ASSERT_EQUAL_INT(-EINVAL, sched_sim_driver_start(NULL, &args));
    TEST_ASSERT_EQUAL_INT(-EINVAL, sched_sim_driver_start(&sim, NULL));

    memset(&args, 0, sizeof(args));
    args.replay_path = NULL;
    TEST_ASSERT_EQUAL_INT(-EINVAL, sched_sim_driver_start(&sim, &args));

    printf("test_null_arguments_return_einval: PASS\n");
}

/* Test 6 (sched_sim_driver_run() -- design.md's literal entry point --
 * calling start() then failing loudly with -ENOSYS pending the event loop)
 * was removed here: the event loop now exists (scheduler-core spec, task
 * 11.2), and sched_sim_driver_run() itself moved to sim_loop.c (a much
 * heavier white-box dependency set this file's own header comment
 * deliberately stays without -- "this task stops at 'ready-to-run'"). Its
 * successor lives in test_sim_event_loop.c, alongside every other
 * sched_sim_driver_run()-level test. */

int main(void)
{
    UNITY_BEGIN();

    RUN_TEST(test_valid_fixture_reaches_ready_state_with_frozen_virtual_clock);
    RUN_TEST(test_valid_fixture_activates_virtual_clock_for_tlog_logging);
    RUN_TEST(test_missing_initial_snapshot_entry_fails_cleanly);
    RUN_TEST(test_first_message_not_replayheader_fails_cleanly);
    RUN_TEST(test_missing_replay_file_fails_cleanly);
    RUN_TEST(test_null_arguments_return_einval);

    return UNITY_END();
}