myxce/src/controller/testsuite/test_repl_majority.c

/*
 * test_repl_majority.c — RED-phase tests for majority-commit replication.
 *
 * Tests for:
 *   repl_wait_majority_ack(replicator_t *, uint32_t timeout_ms, uint8_t ack_op)
 *   repl_broadcast majority semantics (pending_ack_count, over-limit eviction)
 *
 * These functions/fields do not exist yet (task 7.2, 7.3).
 * This file will fail to link until they are implemented.
 *
 * Requirements: 5.1, 5.4, 5.5, 5.8, 8.2
 */
#include <errno.h>
#include <pthread.h>
#include <stdatomic.h>
#include <stdint.h>
#include <stdio.h>
#include <string.h>
#include <time.h>
#include <unity/unity.h>
#include "repl.h"
#include "config.h"
#include "controller.capnp.h"  /* OPCode_walAck, OPCode_upgradeConfigAck */

/* MAX_PENDING_ACKS: defined in repl.h after task 7.2; fallback for RED phase */
#ifndef MAX_PENDING_ACKS
#define MAX_PENDING_ACKS 16
#endif

/* ── Forward declarations of functions-under-test (not yet implemented) ───── */

/*
 * repl_wait_majority_ack: wait until majority of active standbys have ACKed
 * for the given ack_op. Returns 0 on quorum, -ETIMEDOUT on timeout.
 * Single-node (no active standbys) returns 0 immediately.
 */
extern int repl_wait_majority_ack(replicator_t *r, uint32_t timeout_ms,
                                   uint8_t ack_op);

/* ── Helpers ───────────────────────────────────────────────────────────────── */

/* Dummy endpoints — repl.c only compares pointers */
static int ep0, ep1, ep2;

/* ACK a standby from another thread */
struct ack_args {
    replicator_t *r;
    void         *ep;
    uint64_t      lsn;
    uint32_t      delay_ms;
};

static void *ack_thread(void *arg)
{
    struct ack_args *a = arg;
    if (a->delay_ms > 0) {
        struct timespec ts = { .tv_sec = 0,
                               .tv_nsec = (long)a->delay_ms * 1000000L };
        nanosleep(&ts, NULL);
    }
    repl_on_ack(a->r, a->ep, a->lsn);
    return NULL;
}

/* ── Test 1: 2/3 ACKs → majority, returns 0 ───────────────────────────────── */

/* Static so ack_args survive Unity longjmp if assert fires before join */
static replicator_t g_r1;
static struct ack_args g_a1_0, g_a1_1;

static void test_wait_majority_ack_two_of_three_returns_zero(void)
{
    repl_init(&g_r1);
    repl_add_standby(&g_r1, &ep0, "sb0", 7000);
    repl_add_standby(&g_r1, &ep1, "sb1", 7001);
    repl_add_standby(&g_r1, &ep2, "sb2", 7002);

    /* 2 standbys ACK — majority of 3 active standbys is ceil((3+1)/2) = 2 ACKs + self = quorum */
    pthread_t t0, t1;
    g_a1_0 = (struct ack_args){ &g_r1, &ep0, 1, 10 };
    g_a1_1 = (struct ack_args){ &g_r1, &ep1, 1, 20 };
    pthread_create(&t0, NULL, ack_thread, &g_a1_0);
    pthread_create(&t1, NULL, ack_thread, &g_a1_1);

    int rc = repl_wait_majority_ack(&g_r1, 2000, (uint8_t)OPCode_walAck);

    /* Join threads before asserting — prevents use-after-return if assert longjmps */
    pthread_join(t0, NULL);
    pthread_join(t1, NULL);

    TEST_ASSERT_EQUAL_INT(0, rc);

    repl_fini(&g_r1);
    printf("test_wait_majority_ack_two_of_three_returns_zero: PASS\n");
}

/* ── Test 2: timeout before majority ACKs → -ETIMEDOUT ────────────────────── */

static void test_wait_majority_ack_timeout_returns_etimedout(void)
{
    replicator_t r;
    repl_init(&r);
    repl_add_standby(&r, &ep0, "sb0", 7000);
    repl_add_standby(&r, &ep1, "sb1", 7001);
    repl_add_standby(&r, &ep2, "sb2", 7002);
    /* No ACKs arrive — should time out */

    int rc = repl_wait_majority_ack(&r, 50, (uint8_t)OPCode_walAck);
    TEST_ASSERT_EQUAL_INT(-ETIMEDOUT, rc);

    repl_fini(&r);
    printf("test_wait_majority_ack_timeout_returns_etimedout: PASS\n");
}

/* ── Test 3: single-node (no standbys) → returns 0 immediately ────────────── */

static void test_wait_majority_ack_no_standbys_returns_zero(void)
{
    replicator_t r;
    repl_init(&r);
    /* No standbys added — primary alone is majority */

    int rc = repl_wait_majority_ack(&r, 100, (uint8_t)OPCode_walAck);
    TEST_ASSERT_EQUAL_INT(0, rc);

    repl_fini(&r);
    printf("test_wait_majority_ack_no_standbys_returns_zero: PASS\n");
}

/* ── Test 4: in_catch_up standby excluded from quorum denominator ──────────── */

static replicator_t g_r4;
static struct ack_args g_a4_0;

static void test_wait_majority_ack_catchup_excluded_from_quorum(void)
{
    repl_init(&g_r4);
    repl_add_standby(&g_r4, &ep0, "sb0", 7000); /* active */
    repl_add_standby(&g_r4, &ep1, "sb1", 7001); /* will be put in catch-up */
    repl_add_standby(&g_r4, &ep2, "sb2", 7002); /* active */

    repl_start_catchup(&g_r4, &ep1, 0);

    pthread_t t0;
    g_a4_0 = (struct ack_args){ &g_r4, &ep0, 1, 10 };
    pthread_create(&t0, NULL, ack_thread, &g_a4_0);

    int rc = repl_wait_majority_ack(&g_r4, 2000, (uint8_t)OPCode_walAck);

    pthread_join(t0, NULL);
    TEST_ASSERT_EQUAL_INT(0, rc);

    repl_fini(&g_r4);
    printf("test_wait_majority_ack_catchup_excluded_from_quorum: PASS\n");
}

/* ── Test 5: OP_walAck vs OP_upgradeConfigAck dispatched independently ─────── */

static replicator_t g_r5;
static struct ack_args g_a5_0;

static void test_wait_majority_ack_ack_op_discriminates(void)
{
    repl_init(&g_r5);
    repl_add_standby(&g_r5, &ep0, "sb0", 7000);

    pthread_t t0;
    g_a5_0 = (struct ack_args){ &g_r5, &ep0, 1, 10 };
    pthread_create(&t0, NULL, ack_thread, &g_a5_0);

    int rc_wal = repl_wait_majority_ack(&g_r5, 2000, (uint8_t)OPCode_walAck);

    pthread_join(t0, NULL);
    TEST_ASSERT_EQUAL_INT(0, rc_wal);

    /* upgradeConfigAck with no pending ACKs → timeout */
    int rc_cfg = repl_wait_majority_ack(&g_r5, 50, (uint8_t)OPCode_upgradeConfigAck);
    TEST_ASSERT_EQUAL_INT(-ETIMEDOUT, rc_cfg);

    repl_fini(&g_r5);
    printf("test_wait_majority_ack_ack_op_discriminates: PASS\n");
}

/* ── Test 6: pending_ack_count > max removes standby from active set ──────── */

static void test_broadcast_over_limit_removes_standby(void)
{
    replicator_t r;
    repl_init(&r);
    repl_add_standby(&r, &ep0, "sb0", 7000);

    /* Artificially inflate pending_ack_count past the limit.
     * After overflow the standby should be evicted (in_catch_up=1 or removed). */
    for (int i = 0; i < r.standbys[0].ep != NULL ? 1 : 0; i++) {
        /* Access the pending_ack_count field — this will fail to compile if
         * the field does not exist on standby_conn_t */
        r.standbys[0].pending_ack_count = MAX_PENDING_ACKS + 1;
    }
    /* Also verify the field exists via a direct write */
    r.standbys[0].pending_ack_count = MAX_PENDING_ACKS + 1;

    /* Broadcast a wal entry — the over-limit standby should be evicted */
    wal_entry_hdr_t hdr = { .type = WAL_JOB_SUBMIT, .lsn = 1 };
    int rc = repl_broadcast(&r, &hdr, NULL, 0);
    /* repl_broadcast itself may return 0 even after eviction */
    (void)rc;

    /* After broadcast with pending_ack_count > max, standby should be in catch-up */
    int evicted = 0;
    for (int i = 0; i < MAX_STANDBYS; i++) {
        if (r.standbys[i].ep == &ep0) {
            if (atomic_load_explicit(&r.standbys[i].in_catch_up,
                                     memory_order_acquire))
                evicted = 1;
        }
    }
    /* Alternatively the standby may have been fully removed */
    if (!evicted) {
        evicted = (r.nstandbys == 0);
    }
    TEST_ASSERT_TRUE(evicted);

    repl_fini(&r);
    printf("test_broadcast_over_limit_removes_standby: PASS\n");
}

/* ── Test group entry point ────────────────────────────────────────────────── */

void test_repl_majority(void)
{
    UNITY_BEGIN();
    RUN_TEST(test_wait_majority_ack_two_of_three_returns_zero);
    RUN_TEST(test_wait_majority_ack_timeout_returns_etimedout);
    RUN_TEST(test_wait_majority_ack_no_standbys_returns_zero);
    RUN_TEST(test_wait_majority_ack_catchup_excluded_from_quorum);
    RUN_TEST(test_wait_majority_ack_ack_op_discriminates);
    RUN_TEST(test_broadcast_over_limit_removes_standby);
    UNITY_END();
}