myxce/src/scheduler/testsuite/test_sim_alt_events.c

/*
 * test_sim_alt_events.c - contract test for what-if event-source branching
 * (scheduler-core spec, task 11.5, Req 5 AC 16).
 *
 * Observable under test (task 11.5's own text, task text's Observable (a)):
 *   - running with an alternate-events file produces decisions driven by
 *     the alternate events, not the base file's original events.
 *
 * Two tests:
 *   - a baseline run against the base .replay file ALONE (no
 *     --sim-alt-events) confirms its own event stream drives a PEND
 *     decision for the BASE job, and NOT the alt job.
 *   - a what-if run against the SAME base file's snapshot, but with
 *     --sim-alt-events pointed at a separate events-only stream, confirms
 *     the opposite: a PEND decision for the ALT job, and NOT the base job.
 * Together these prove the switch is real (not merely "some decision
 * appears"): the DRIVING SOURCE genuinely changed.
 *
 * Fixture strategy: the SAME real QUEUE_UPDATE+JOBS_PUSH-driving-the-real-
 * builtin_fcfs-picker technique test_sim_verify.c's own integration-level
 * fixture helpers establish (build_fixture_scheduler() records
 * schedPolicy="builtin_fcfs" so sim_register_default_picker() resolves the
 * real plugin) -- since core.c's own sched_job_is_ready()/
 * sched_queue_is_ready() are unconditional `return 1` stubs (task 2.4's own
 * documented, still-live scope note), any queue/job pair immediately
 * becomes a next_job() candidate, so each run deterministically produces
 * exactly one live PEND decision via make_pendreason() for whichever jobid
 * that run's own event stream pushed. Decisions are observed by
 * redirecting STDOUT_FILENO around sched_sim_driver_run(), the same
 * dup()/dup2() capture technique test_sim_verify.c's own
 * run_sim_and_capture_stdout() establishes (sim_print_decision()'s
 * "[sim] PEND jobid=%llu" line, sim_loop.c).
 *
 * The alt-events file itself is a BARE sequence of ReplayEvent/ReplaySession
 * messages (no ReplayHeader, no SnapshotEntry) -- Req 5 AC 16's own text:
 * "the driver loads the snapshot from the base file, then replays events
 * from the alt-events file (same .replay capnp stream format)". Once
 * --sim-alt-events is set, sched_sim_driver_run()'s main loop reads
 * EXCLUSIVELY from it from message 1 onward -- the same shape-based
 * message dispatch (msg_root_has_shape(), never position-based beyond the
 * base file's own first two messages) that already governs every message
 * after a SnapshotEntry in a full `.replay` stream, so an alt-events file
 * that is simply "the tail of a .replay stream" needs no header/snapshot
 * prefix of its own.
 *
 * White-box #include of the same TU set test_sim_verify.c uses (see that
 * file's own header comment) -- core.c/core_clock.c/core_events.c/
 * core_session.c/decision.c/plugin.c/plugins/builtin_fcfs.c/recording.c/
 * recording_session.c/repl.c/sim.c/sim_loop.c/sim_record.c/sim_verify.c/
 * snapshot.c/snapshot_load.c/snapshot_wire.c. sim_verify.c AND
 * recording_session.c/sim_record.c/repl.c are all required at link time
 * (sched_sim_driver_run() externs sim_decision_eq()/sim_log_mismatch() and
 * sched_record_session_ctx_new()/_finalize()/sim_record_write_header_and_
 * snapshot()/sim_record_write_event() unconditionally, and repl.h's task
 * 12.1 inline wrappers -- pulled in transitively by sim_loop.c's own
 * `#include "repl.h"` -- reference xce_repl_start()/
 * xce_repl_post_session_check() unconditionally too) even though this file
 * never sets --sim-verify/--sim-output/--interactive, same reason
 * test_sim_event_loop.c's own header comment documents.
 */
#include <errno.h>
#include <limits.h>
#include <stdatomic.h>
#include <stdbool.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.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_sim_verify.c). */
#include "../src/core.c"
#include "../src/core_clock.c"
#include "../src/core_events.c"
#include "../src/core_session.c"
#include "../src/decision.c"
#include "../src/plugin.c"
#include "../src/plugins/builtin_fcfs.c"
#include "../src/recording.c"
#include "../src/recording_session.c"
#include "../src/repl.c"
#include "../src/repl_fmt.c"
#include "../src/repl_rollup.c"
#include "../src/repl_break.c"
#include "../src/repl_info.c"
#include "../src/repl_params.c"
#include "../src/sim.c"
#include "../src/sim_loop.c"
#include "../src/sim_picker.c" /* bug-1567: sched_sim_driver_run() now calls sim_bootstrap_picker() (sim_loop.c-cap sibling) as an extern -- undefined reference at link time otherwise */
#include "../src/sim_limit.c" /* bug-1825: sched_sim_driver_run() now also calls sim_bootstrap_limit_plugin() (sim_loop.c-cap sibling, sim_picker.c's own bug-1567 precedent) as an extern -- undefined reference at link time otherwise */
#include "../src/sim_record.c"
#include "../src/sim_verify.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; }

/* repl_info.c (scheduler-sim-diagnostics spec, task 2.1) now calls
 * limit_get_configured_limits() (plugins/limit.c, not part of this TU) to
 * resolve `info limit`'s name/all argument -- link-satisfying stub only,
 * same rationale as kill_sched_job()/kill_sched_resval() above; this
 * file's own fixtures never register the limit plugin, so NULL
 * (limit_get_configured_limits()'s own documented "plugin absent" return)
 * is also the behaviorally correct answer here, not just a link
 * placeholder. repl_info_limit() itself is not yet wired into
 * repl_cmd_info() (task 4), so no test in this file can reach it anyway. */
var limit_get_configured_limits(xce_sched_core_t* core)
{
    (void)core;
    return NULL;
}

/* scheduler-sim-diagnostics spec, task 3.1: repl_info.c now also calls
 * limit_get_usage_instances() (plugins/limit.c, not part of this TU) to
 * read a limit's live usage instances -- identical link-satisfying stub,
 * same rationale as limit_get_configured_limits() immediately above; this
 * file's own fixtures never register the limit plugin, so NULL
 * (limit_get_usage_instances()'s own documented "plugin absent" return) is
 * also the behaviorally correct answer here, not just a link placeholder. */
var limit_get_usage_instances(xce_sched_core_t* core)
{
    (void)core;
    return NULL;
}

/* scheduler-sim-diagnostics spec, task 6 (bug-1825): sim_loop.c's
 * sched_sim_driver_run() now also calls sim_bootstrap_limit_plugin()
 * (sim_limit.c, pulled into this TU via the #include above), which in
 * turn calls limit_new_plugin() (plugins/limit.c, not part of this TU) --
 * identical link-satisfying stub rationale as limit_get_configured_
 * limits()/limit_get_usage_instances() immediately above. Returning NULL
 * here is also the behaviorally correct answer, not just a link
 * placeholder: sim_bootstrap_limit_plugin() already handles a NULL
 * limit_new_plugin() return gracefully (logs an ERROR, registers nothing,
 * returns) -- the exact same "out of memory" path sim_bootstrap_picker()
 * (sim_picker.c) takes for a NULL builtin_fcfs_new_plugin() -- so this
 * file's fixtures simply end up with no limit plugin registered, same
 * observable state as before this task. */
xce_sched_plugin_t* limit_new_plugin(void)
{
    return NULL;
}

/* limit_seed_config() (plugins/limit.c, not part of this TU) -- bug-1825
 * remediation round 2's new honestly-typed config-seed entry point.
 * sim_bootstrap_limit_plugin() (sim_limit.c) only calls it after
 * plugin_register_core() has already succeeded against a real, non-NULL
 * limit_new_plugin() plugin -- unreachable in this file since the
 * limit_new_plugin() stub immediately above always returns NULL, but the
 * symbol must still resolve at link time. Same link-satisfying-stub
 * rationale as limit_new_plugin() immediately above. */
int limit_seed_config(xce_sched_plugin_t* plugin, xce_sched_core_t* core,
                      xce_conf4sched_t* config)
{
    (void)plugin;
    (void)core;
    (void)config;
    return 0;
}

void sched_worker_release_host_ctx(xce_sched_worker_t* w) { (void)w; }

/* resource-accounting.md's reconciliation (resource.c, not linked here --
 * this file only #includes core_events.c). core_events.c's
 * XCE_CORE_EVENT_JOB_RUSAGE handler calls this whenever job->accounts !=
 * NULL; this fixture never populates job->accounts, so the real body is
 * never reached -- link-satisfying stub only, same rationale as every
 * other stub in this block (see test_job_update.c's identical stub). */
int sched_reconcile_job_resource_usage(xce_sched_core_t*  c,
                                       xce_job_account_t* a,
                                       xce_job_rusages_t* r)
{
    (void)c; (void)a; (void)r; return 0;
}

int sched_fill_limit_requests(xce_sched_alloc_req_t* alloc_req,
                              xlist_t* limits, xlist_t* rusages, int nhosts,
                              int nslots)
{
    (void)alloc_req;
    (void)limits;
    (void)rusages;
    (void)nhosts;
    (void)nslots;
    return 0;
}

/* sched_sim_driver_run()'s (sim_loop.c, scheduler-sim-decision-parity task
 * 2.1) new round-boundary call to the relocated sched_account_jobs()
 * (core.h) -- a no-op stand-in here since this file does not link
 * scheduler.c/resource.c, same rationale test_sim_equivalence.c's own copy
 * documents. */
int sched_account_jobs(xce_sched_core_t* core)
{
    (void)core;
    return 0;
}

/* Real reimplementation of schedobj.c's sched_resolve_job_picker -- same
 * copy test_sim_verify.c/test_sim_event_loop.c/test_sim_startup.c each
 * carry (schedobj.c is not linked here: it would need plugin_register(),
 * which requires a genuine xce_scheduler_t* neither this file's fixtures
 * nor sim_loop.c's own core-scoped registration path have, Req 5 AC 17). */
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 -- same techniques test_sim_verify.c already            */
/* establishes for its own integration-level tests.                       */
/* ---------------------------------------------------------------------- */

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

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

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);

    sched->core.job_pick_plugin = (char*)"builtin_fcfs";
    sched->record_dir           = record_dir;
}

static FILE* write_header_and_snapshot(char* out_path, size_t out_path_len,
                                       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);

    return sched.record_file;
}

static void append_queue_update_event(FILE* f, uint64_t ts,
                                      const char* queue_name)
{
    xce_queue_t          queue;
    replay_event_t       src;
    struct capn          c;
    struct capn_segment* cs;
    ReplayEvent_ptr      p;

    memset(&queue, 0, sizeof(queue));
    queue.queue    = (char*)queue_name;
    queue.status   = QUEUE_STAT_OPEN;
    queue.priority = 1;

    memset(&src, 0, sizeof(src));
    src.ts                = ts;
    src.body_which        = ReplayEvent_body_queueUpdate;
    src.body.queue_update = &queue;

    capn_init_malloc(&c);
    cs = capn_root(&c).seg;
    encode_ReplayEvent_ptr(cs, &p, &src);
    capn_setp(capn_root(&c), 0, p.p);

    TEST_ASSERT_EQUAL_INT(0, write_capnp_message(f, &c));
    capn_free(&c);
}

static void append_jobs_push_event(FILE* f, uint64_t ts, uint64_t jobid,
                                   const char* queue_name)
{
    job_submit_data_t    submit;
    xce_job_t            job;
    xce_job_t*           jobs[1];
    xce_jobs_data_t      jobs_data;
    replay_event_t       src;
    struct capn          c;
    struct capn_segment* cs;
    ReplayEvent_ptr      p;

    memset(&submit, 0, sizeof(submit));
    submit.queue    = (char*)queue_name;
    submit.user     = (char*)"alice";
    submit.mintasks = 1;
    submit.maxtasks = 1;

    memset(&job, 0, sizeof(job));
    job.jobid  = jobid;
    job.state  = JOB_STAT_PEND;
    job.submit = &submit;

    jobs[0] = &job;

    memset(&jobs_data, 0, sizeof(jobs_data));
    jobs_data.n_total = 1;
    jobs_data.count   = 1;
    jobs_data.jobs    = jobs;

    memset(&src, 0, sizeof(src));
    src.ts             = ts;
    src.body_which     = ReplayEvent_body_jobsPush;
    src.body.jobs_push = &jobs_data;

    capn_init_malloc(&c);
    cs = capn_root(&c).seg;
    encode_ReplayEvent_ptr(cs, &p, &src);
    capn_setp(capn_root(&c), 0, p.p);

    TEST_ASSERT_EQUAL_INT(0, write_capnp_message(f, &c));
    capn_free(&c);
}

static void append_replay_session(FILE* f, uint64_t begin_round)
{
    struct capn          c;
    struct capn_segment* cs;
    ReplaySession_ptr    sp;

    capn_init_malloc(&c);
    cs = capn_root(&c).seg;
    sp = new_ReplaySession(cs);
    ReplaySession_set_beginRound(sp, begin_round);
    capn_setp(capn_root(&c), 0, sp.p);

    TEST_ASSERT_EQUAL_INT(0, write_capnp_message(f, &c));
    capn_free(&c);
}

static void append_end_of_stream_marker(FILE* f)
{
    replay_event_t       src;
    struct capn          c;
    struct capn_segment* cs;
    ReplayEvent_ptr      p;

    memset(&src, 0, sizeof(src));
    src.body_which = ReplayEvent_body_endSession;

    capn_init_malloc(&c);
    cs = capn_root(&c).seg;
    encode_ReplayEvent_ptr(cs, &p, &src);
    capn_setp(capn_root(&c), 0, p.p);

    TEST_ASSERT_EQUAL_INT(0, write_capnp_message(f, &c));
    capn_free(&c);
}

/* Runs sched_sim_driver_run() with optional --sim-alt-events, capturing
 * everything written to stdout during the call -- same dup()/dup2()
 * technique test_sim_verify.c's own run_sim_and_capture_stdout()
 * establishes, extended with an `alt_path` parameter (NULL to omit
 * --sim-alt-events entirely). */
static char* run_sim_and_capture_stdout(const char* base_path,
                                        const char* alt_path, int* out_rc)
{
    sched_sim_args_t       args;
    xce_sched_sim_driver_t sim;
    char                   tmp[] = "/tmp/xce_altevents_run_XXXXXX";
    int                    fd    = mkstemp(tmp);
    int                    saved_stdout;
    off_t                  len;
    char*                  buf;

    TEST_ASSERT_TRUE_MESSAGE(fd >= 0, "mkstemp for stdout capture must "
                                      "succeed");

    fflush(stdout);
    saved_stdout = dup(STDOUT_FILENO);
    TEST_ASSERT_TRUE_MESSAGE(saved_stdout >= 0, "dup(STDOUT_FILENO) must "
                                                "succeed");
    TEST_ASSERT_TRUE_MESSAGE(dup2(fd, STDOUT_FILENO) >= 0,
                             "dup2 redirect of STDOUT_FILENO must succeed");

    memset(&args, 0, sizeof(args));
    args.replay_path     = base_path;
    args.sim_start_ts    = SCHED_SIM_START_TS_LATEST;
    args.sim_speed       = 0; /* frozen -- deterministic, no wall-clock wait */
    args.alt_events_path = alt_path;

    *out_rc = sched_sim_driver_run(&sim, &args);

    fflush(stdout);
    dup2(saved_stdout, STDOUT_FILENO);
    close(saved_stdout);

    len = lseek(fd, 0, SEEK_CUR);
    TEST_ASSERT_TRUE(len >= 0);

    buf = (char*)calloc(1, (size_t)len + 1);
    TEST_ASSERT_NOT_NULL(buf);
    TEST_ASSERT_TRUE(lseek(fd, 0, SEEK_SET) == 0);
    if (len > 0) {
        ssize_t nread = read(fd, buf, (size_t)len);
        TEST_ASSERT_TRUE(nread == len);
    }
    close(fd);
    unlink(tmp);

    return buf;
}

#define BASE_JOBID 777ULL
#define ALT_JOBID  888ULL

/* ---------------------------------------------------------------------- */
/* Test 1: baseline -- no --sim-alt-events, the base file's OWN events     */
/* drive scheduling.                                                       */
/* ---------------------------------------------------------------------- */

static void test_baseline_run_uses_base_file_events(void)
{
    char  base_jobid_marker[80];
    char  alt_jobid_marker[80];
    char  jobid_buf[64];
    char  path[PATH_MAX];
    FILE* f;
    int   rc;
    char* captured;

    /* bug-1591: sim_print_decision() (sim_loop.c) now renders jobids via
     * fmt_jobid(), not raw %llu -- these markers must match that same
     * human-readable form, computed the same way, not hardcoded. */
    fmt_jobid(jobid_buf, sizeof(jobid_buf), BASE_JOBID);
    snprintf(base_jobid_marker, sizeof(base_jobid_marker), "jobid=%s",
             jobid_buf);
    fmt_jobid(jobid_buf, sizeof(jobid_buf), ALT_JOBID);
    snprintf(alt_jobid_marker, sizeof(alt_jobid_marker), "jobid=%s",
             jobid_buf);

    f = write_header_and_snapshot(path, sizeof(path), "_baseline");
    TEST_ASSERT_NOT_NULL(f);

    append_queue_update_event(f, 1000ULL, "normal");
    append_jobs_push_event(f, 1500ULL, BASE_JOBID, "normal");
    append_replay_session(f, 2000ULL);
    append_end_of_stream_marker(f);
    fclose(f);

    captured = run_sim_and_capture_stdout(path, NULL, &rc);

    TEST_ASSERT_EQUAL_INT(0, rc);
    TEST_ASSERT_NOT_NULL_MESSAGE(
        strstr(captured, base_jobid_marker),
        "baseline run (no --sim-alt-events) must produce a decision for "
        "the base file's own jobid");
    TEST_ASSERT_NULL_MESSAGE(
        strstr(captured, alt_jobid_marker),
        "baseline run must never produce a decision for a jobid it never "
        "saw");

    free(captured);
    printf("test_baseline_run_uses_base_file_events: PASS\n");
}

/* ---------------------------------------------------------------------- */
/* Test 2: what-if -- --sim-alt-events set, the ALTERNATE file's events    */
/* drive scheduling instead (Req 5 AC 16's own Observable).                */
/* ---------------------------------------------------------------------- */

static void test_alt_events_run_uses_alt_file_events_not_base(void)
{
    char  base_jobid_marker[80];
    char  alt_jobid_marker[80];
    char  jobid_buf[64];
    char  base_path[PATH_MAX];
    char  alt_path[PATH_MAX];
    FILE* base_f;
    FILE* alt_f;
    int   rc;
    char* captured;

    /* bug-1591: see test_baseline_run_uses_base_file_events()'s identical
     * fmt_jobid() comment. */
    fmt_jobid(jobid_buf, sizeof(jobid_buf), BASE_JOBID);
    snprintf(base_jobid_marker, sizeof(base_jobid_marker), "jobid=%s",
             jobid_buf);
    fmt_jobid(jobid_buf, sizeof(jobid_buf), ALT_JOBID);
    snprintf(alt_jobid_marker, sizeof(alt_jobid_marker), "jobid=%s",
             jobid_buf);

    /* Base file: header + empty snapshot, then its OWN (never-to-be-read,
     * once --sim-alt-events is set) events for BASE_JOBID -- present to
     * prove the switch is real: if alt-events were silently ignored, this
     * run would fall back to seeing BASE_JOBID here too. */
    base_f = write_header_and_snapshot(base_path, sizeof(base_path),
                                       "_whatif_base");
    TEST_ASSERT_NOT_NULL(base_f);
    append_queue_update_event(base_f, 1000ULL, "normal");
    append_jobs_push_event(base_f, 1500ULL, BASE_JOBID, "normal");
    append_replay_session(base_f, 2000ULL);
    append_end_of_stream_marker(base_f);
    fclose(base_f);

    /* Alt-events file: a BARE ReplayEvent/ReplaySession stream (no
     * ReplayHeader, no SnapshotEntry -- this file's own header comment) for
     * a DIFFERENT job, ALT_JOBID, on a queue the alt stream creates for
     * itself (the loaded snapshot has zero queues). */
    TEST_ASSERT_TRUE(snprintf(alt_path, sizeof(alt_path), "%s.alt", base_path)
                     < (int)sizeof(alt_path));
    alt_f = fopen(alt_path, "w");
    TEST_ASSERT_NOT_NULL(alt_f);
    append_queue_update_event(alt_f, 3000ULL, "altqueue");
    append_jobs_push_event(alt_f, 3500ULL, ALT_JOBID, "altqueue");
    append_replay_session(alt_f, 4000ULL);
    append_end_of_stream_marker(alt_f);
    fclose(alt_f);

    captured = run_sim_and_capture_stdout(base_path, alt_path, &rc);

    TEST_ASSERT_EQUAL_INT(0, rc);
    TEST_ASSERT_NOT_NULL_MESSAGE(
        strstr(captured, alt_jobid_marker),
        "--sim-alt-events run must produce a decision for the ALTERNATE "
        "file's own jobid");
    TEST_ASSERT_NULL_MESSAGE(
        strstr(captured, base_jobid_marker),
        "--sim-alt-events run must NOT produce a decision for the base "
        "file's original jobid -- the base file's own events must never "
        "be read once --sim-alt-events is set");

    free(captured);
    printf("test_alt_events_run_uses_alt_file_events_not_base: PASS\n");
}

int main(void)
{
    UNITY_BEGIN();

    RUN_TEST(test_baseline_run_uses_base_file_events);
    RUN_TEST(test_alt_events_run_uses_alt_file_events_not_base);

    return UNITY_END();
}