myxce/src/controller/testsuite/test_commit_resolve.c

/*
 * test_commit_resolve.c — raft-apply-decoupling task 1.1.
 *
 * Keystone conversion, registration half: the commit engine gains
 * commit_submit_async(), a non-blocking sibling of
 * commit_submit(..., COMMIT_MODE_WAIT, ...) that registers a continuation
 * (callback + context) against an appended LSN instead of parking the
 * calling thread. This file covers ONLY the registration mechanism —
 * resolution (invoking the continuation on majority-ack / timeout /
 * demotion / truncation) is wired by a follow-up task (1.2) and is not
 * exercised here: a registered continuation is never invoked in these
 * tests, by design.
 *
 * Asserts:
 *   (1) commit_submit_async returns immediately (0), before the LSN
 *       commits, and does NOT invoke the continuation inline.
 *   (2) Bad-argument rejection: -EINVAL for NULL engine, LSN 0, NULL fn.
 *   (3) The SAME admission-cap discipline commit_submit's WAIT mode uses
 *       (wait_admit_locked / wait_cap / inflight_waits) governs
 *       registration: cap exhaustion fast-rejects with -XCE_ERR_NOT_READY,
 *       never blocks.
 *   (4) That admission budget is SHARED with COMMIT_MODE_WAIT — a parked
 *       blocking waiter and a pending async registration draw from the
 *       same inflight_waits pool.
 *   (5) Distinct concurrent registrations occupy distinct per-LSN slots.
 *
 * Requirements: 1.3, 1.4, 9.1, 9.2
 */
#include <errno.h>
#include <pthread.h>
#include <stdatomic.h>
#include <stdint.h>
#include <string.h>
#include <time.h>
#include <unistd.h>

#include <unity/unity.h>

#include "xce/errnox.h"

#include "commit.h"
#include "repl.h"

/* ── Fixture ──────────────────────────────────────────────────────────────
 * Static: persist_t embeds large path buffers, and statics survive Unity's
 * longjmp on assertion failure (pattern from test_commit_engine.c /
 * test_commit_admission_pool.c). */
static persist_t       g_p;
static commit_engine_t g_ce;
static int             g_eps[MAX_STANDBYS]; /* dummy endpoints — pointer-only */

/* Arrange a fresh engine over a stub persist_t + replicator_t, mirroring
 * test_commit_engine.c's engine_setup_vcpus. n_vcpus drives the local
 * admission cap: max(1, n_vcpus - COMMIT_WAIT_RESERVED). */
static void resolve_setup(int n_peers, int n_standbys, uint64_t appended_lsn,
                          int n_vcpus)
{
    char name[16];

    memset(&g_p, 0, sizeof(g_p));
    TEST_ASSERT_EQUAL_INT(0, repl_init(&g_p.repl));
    for (int i = 0; i < n_standbys; i++) {
        snprintf(name, sizeof(name), "sb%d", i);
        TEST_ASSERT_EQUAL_INT(
            i, repl_add_standby(&g_p.repl, &g_eps[i], name, 7000 + (uint32_t)i));
    }
    g_p.current_lsn = appended_lsn + 1;
    atomic_store(&g_p.committed_lsn, 0);
    atomic_store(&g_p.durable_lsn, appended_lsn);

    TEST_ASSERT_EQUAL_INT(0, commit_engine_init(&g_ce, &g_p, n_peers, n_vcpus));
}

static void resolve_teardown(void)
{
    commit_engine_fini(&g_ce);
    repl_fini(&g_p.repl);
}

/* Continuation recorder — proves (non-)invocation and captures the args a
 * future commit_resolve() would deliver. Not exercised as a real resolve
 * path in this file (task 1.2's job); only used to assert it stays quiet. */
typedef struct {
    _Atomic int      calls;
    uint64_t         last_lsn;
    commit_outcome_t last_outcome;
    int              last_rc;
    void*            last_ctx;
} continuation_recorder_t;

static void recorder_fn(void* ctx, uint64_t lsn, commit_outcome_t outcome,
                        int rc)
{
    continuation_recorder_t* r = (continuation_recorder_t*)ctx;

    r->last_lsn     = lsn;
    r->last_outcome = outcome;
    r->last_rc      = rc;
    r->last_ctx     = ctx;
    atomic_fetch_add(&r->calls, 1);
}

/* ------------------------------------------------------------------ *
 * (1) Registration returns immediately, before the LSN commits, and   *
 *     never invokes the continuation inline.                          *
 * ------------------------------------------------------------------ */
static void test_commit_submit_async_returns_immediately_before_commit(void)
{
    continuation_recorder_t rec = {0};

    /* n_peers=3, no standby ACKs delivered: LSN 1 can never commit on its
     * own (majority unreachable), so a blocking WAIT would park here. */
    resolve_setup(/*n_peers=*/3, /*n_standbys=*/2, /*appended_lsn=*/1,
                  /*n_vcpus=*/8);

    int rc = commit_submit_async(&g_ce, /*lsn=*/1, recorder_fn, &rec);

    TEST_ASSERT_EQUAL_INT_MESSAGE(
        0, rc, "registration must succeed and return without blocking");
    TEST_ASSERT_EQUAL_UINT64_MESSAGE(
        0, atomic_load(&g_p.committed_lsn),
        "the LSN must still be uncommitted at the point of registration");
    TEST_ASSERT_EQUAL_INT_MESSAGE(
        0, atomic_load(&rec.calls),
        "the continuation must NOT be invoked by registration alone");

    resolve_teardown();
    printf("test_commit_submit_async_returns_immediately_before_commit: "
           "PASS\n");
}

/* ------------------------------------------------------------------ *
 * (2) Bad-argument rejection.                                         *
 * ------------------------------------------------------------------ */
static void test_commit_submit_async_rejects_invalid_args(void)
{
    continuation_recorder_t rec = {0};

    resolve_setup(/*n_peers=*/1, /*n_standbys=*/0, /*appended_lsn=*/1,
                  /*n_vcpus=*/8);

    TEST_ASSERT_EQUAL_INT(-EINVAL,
                          commit_submit_async(NULL, 1, recorder_fn, &rec));
    TEST_ASSERT_EQUAL_INT(
        -EINVAL, commit_submit_async(&g_ce, /*lsn=*/0, recorder_fn, &rec));
    TEST_ASSERT_EQUAL_INT(-EINVAL,
                          commit_submit_async(&g_ce, /*lsn=*/1, NULL, &rec));
    TEST_ASSERT_EQUAL_INT_MESSAGE(
        0, atomic_load(&rec.calls),
        "no rejected registration may invoke the continuation");

    resolve_teardown();
    printf("test_commit_submit_async_rejects_invalid_args: PASS\n");
}

/* ------------------------------------------------------------------ *
 * (3) Admission cap governs registration exactly as it governs WAIT:  *
 *     n_vcpus=2, COMMIT_WAIT_RESERVED=2 -> local cap = max(1,0) = 1.   *
 * ------------------------------------------------------------------ */
static void test_commit_submit_async_respects_admission_cap(void)
{
    continuation_recorder_t rec1 = {0}, rec2 = {0};

    resolve_setup(/*n_peers=*/3, /*n_standbys=*/2, /*appended_lsn=*/2,
                  /*n_vcpus=*/2);

    TEST_ASSERT_EQUAL_INT(0, commit_submit_async(&g_ce, 1, recorder_fn, &rec1));
    TEST_ASSERT_EQUAL_INT_MESSAGE(1, g_ce.inflight_waits,
                                  "registration consumes an admission slot");

    int rc = commit_submit_async(&g_ce, 2, recorder_fn, &rec2);
    TEST_ASSERT_EQUAL_INT_MESSAGE(
        -XCE_ERR_NOT_READY, rc,
        "over-cap registration must fast-reject, never block");
    TEST_ASSERT_EQUAL_INT_MESSAGE(
        1, g_ce.inflight_waits,
        "a rejected registration must not consume a slot");
    TEST_ASSERT_EQUAL_INT(0, atomic_load(&rec1.calls));
    TEST_ASSERT_EQUAL_INT(0, atomic_load(&rec2.calls));

    resolve_teardown();
    printf("test_commit_submit_async_respects_admission_cap: PASS\n");
}

/* ------------------------------------------------------------------ *
 * (4) The admission budget is SHARED with COMMIT_MODE_WAIT: a parked   *
 *     blocking waiter occupies the same pool an async registration    *
 *     draws from, and releasing it frees the slot for either caller.  *
 * ------------------------------------------------------------------ */
typedef struct {
    uint64_t lsn;
    uint32_t timeout_ms;
    int      rc;
} waiter_arg_t;

static void* waiter_thread(void* a)
{
    waiter_arg_t* w = (waiter_arg_t*)a;
    w->rc           = commit_submit(&g_ce, w->lsn, COMMIT_MODE_WAIT,
                                    w->timeout_ms);
    return NULL;
}

static uint64_t mono_ms(void)
{
    struct timespec ts;
    clock_gettime(CLOCK_MONOTONIC, &ts);
    return (uint64_t)ts.tv_sec * 1000 + ts.tv_nsec / 1000000;
}

/* Poll ce->inflight_waits until it reaches `want` or the deadline elapses;
 * returns the last observed value (pattern from test_commit_admission_pool.c
 * poll_inflight — avoids a fixed sleep race against the background thread's
 * admission acquire). */
static int poll_inflight(int want, uint32_t deadline_ms)
{
    uint64_t t0 = mono_ms();
    int      v;

    for (;;) {
        pthread_mutex_lock(&g_ce.lock);
        v = g_ce.inflight_waits;
        pthread_mutex_unlock(&g_ce.lock);
        if (v >= want || mono_ms() - t0 >= deadline_ms) {
            return v;
        }
        usleep(500);
    }
}

static void test_commit_submit_async_shares_admission_budget_with_wait(void)
{
    continuation_recorder_t rec = {0};
    pthread_t               tid;
    waiter_arg_t            w = {.lsn = 1, .timeout_ms = 4000, .rc = -9999};

    /* n_vcpus=2 -> local cap = 1 (same sizing as test 3 above). */
    resolve_setup(/*n_peers=*/3, /*n_standbys=*/2, /*appended_lsn=*/2,
                  /*n_vcpus=*/2);

    TEST_ASSERT_EQUAL_INT(0, pthread_create(&tid, NULL, waiter_thread, &w));
    TEST_ASSERT_EQUAL_INT_MESSAGE(
        1, poll_inflight(1, 3000),
        "the blocking WAIT must occupy the sole admission slot");

    int rc = commit_submit_async(&g_ce, /*lsn=*/2, recorder_fn, &rec);
    TEST_ASSERT_EQUAL_INT_MESSAGE(
        -XCE_ERR_NOT_READY, rc,
        "async registration must fast-reject while a blocking WAIT holds "
        "the shared admission slot");

    /* Release the blocking waiter via a covering majority ACK (self + 1
     * standby = 2 > 3/2), freeing the slot for the pending registration. */
    repl_on_ack(&g_p.repl, &g_eps[0], 1);
    commit_on_ack(&g_ce, 0, 1);
    TEST_ASSERT_EQUAL_INT(0, pthread_join(tid, NULL));
    TEST_ASSERT_EQUAL_INT(0, w.rc);

    rc = commit_submit_async(&g_ce, /*lsn=*/2, recorder_fn, &rec);
    TEST_ASSERT_EQUAL_INT_MESSAGE(
        0, rc, "registration must succeed once the shared slot is freed");

    resolve_teardown();
    printf("test_commit_submit_async_shares_admission_budget_with_wait: "
           "PASS\n");
}

/* ------------------------------------------------------------------ *
 * (5) Distinct concurrent registrations occupy distinct per-LSN slots. *
 * ------------------------------------------------------------------ */
static void test_commit_submit_async_tracks_distinct_lsns(void)
{
    continuation_recorder_t rec1 = {0}, rec2 = {0};

    resolve_setup(/*n_peers=*/3, /*n_standbys=*/2, /*appended_lsn=*/2,
                  /*n_vcpus=*/8);

    TEST_ASSERT_EQUAL_INT(0, commit_submit_async(&g_ce, 1, recorder_fn, &rec1));
    TEST_ASSERT_EQUAL_INT(0, commit_submit_async(&g_ce, 2, recorder_fn, &rec2));
    TEST_ASSERT_EQUAL_INT(2, g_ce.inflight_waits);

    /* White-box: the two registrations must land in distinct slots, each
     * carrying its own lsn/fn/ctx (the per-LSN bookkeeping the task
     * requires, not a single-shot overwrite). */
    int found_lsn1 = 0, found_lsn2 = 0;
    for (int i = 0; i < g_ce.n_continuations; i++) {
        if (g_ce.continuations[i].lsn == 1) {
            found_lsn1 = 1;
            TEST_ASSERT_EQUAL_PTR(recorder_fn, g_ce.continuations[i].fn);
            TEST_ASSERT_EQUAL_PTR(&rec1, g_ce.continuations[i].ctx);
        } else if (g_ce.continuations[i].lsn == 2) {
            found_lsn2 = 1;
            TEST_ASSERT_EQUAL_PTR(recorder_fn, g_ce.continuations[i].fn);
            TEST_ASSERT_EQUAL_PTR(&rec2, g_ce.continuations[i].ctx);
        }
    }
    TEST_ASSERT_TRUE_MESSAGE(found_lsn1, "lsn=1 registration must be tracked");
    TEST_ASSERT_TRUE_MESSAGE(found_lsn2, "lsn=2 registration must be tracked");

    resolve_teardown();
    printf("test_commit_submit_async_tracks_distinct_lsns: PASS\n");
}

void test_commit_resolve(void)
{
    RUN_TEST(test_commit_submit_async_returns_immediately_before_commit);
    RUN_TEST(test_commit_submit_async_rejects_invalid_args);
    RUN_TEST(test_commit_submit_async_respects_admission_cap);
    RUN_TEST(test_commit_submit_async_shares_admission_budget_with_wait);
    RUN_TEST(test_commit_submit_async_tracks_distinct_lsns);
}