myxce/src/esd/testsuite/test_esd_core.c

/* test_esd_core.c -- external-license-resources Phase 1, step 6 TDD: the
 * xceesd skeleton's pure core -- esd.yaml parsing and the script
 * collector's output parsing -- white-box #include of the sources under
 * test (same pattern as the worker's resource_sync_test /
 * controller_connector_test). The join/reconnect wiring lives in esd.c
 * against the live client library and is exercised by the t1 E2E, not
 * here; everything this file drives must be deterministic. */
#include <errno.h>
#include <math.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/stat.h>
#include <unistd.h>

#include <unity/unity.h>

#include "esd.h"

/* White-box: reach the config schema/parse internals. */
#include "../src/esd_config.c"
/* White-box: the script collector's parse half (esd_parse_script_output);
 * the spawn half (esd_script_collect) is exercised by the t1 E2E with a
 * real fake-license script, not here. */
#include "../src/esd_script.c"
/* White-box: the stale predicate and the status-file writer (Phase 2,
 * design.md 3.5 "运维面"). */
#include "../src/esd_status.c"
/* White-box: the reconnect-flag contract (bug-1978). esd.c's main loop
 * drives the live client library, but the reconnect handler's flag contract
 * -- set BOTH rejoin and full-push, and the loop consuming rejoin first --
 * is unit-testable here without a controller: esd_run() itself is not
 * linked (its join sequence would need a live primary); we drive
 * esd_on_reconnect and read the loop's guard statics directly. */
#include "../src/esd.c"

static char g_tmpdir[256];

void setUp(void)
{
    snprintf(g_tmpdir, sizeof(g_tmpdir), "/tmp/xce_esd_testXXXXXX");
    TEST_ASSERT_NOT_NULL(mkdtemp(g_tmpdir));
}

void tearDown(void)
{
    if (g_tmpdir[0] != '\0') {
        char path[300];

        /* tests only write flat files inside g_tmpdir */
        snprintf(path, sizeof(path), "rm -rf %s", g_tmpdir);
        if (system(path) != 0) {
            /* best effort */
        }
        g_tmpdir[0] = '\0';
    }
}

static void write_file(const char* dir, const char* name, const char* content)
{
    char path[512];
    FILE* f;

    snprintf(path, sizeof(path), "%s/%s", dir, name);
    f = fopen(path, "w");
    TEST_ASSERT_NOT_NULL(f);
    fputs(content, f);
    fclose(f);
}

static char* slurp(const char* path)
{
    FILE*  f;
    long   len;
    char*  buf;

    f = fopen(path, "r");
    if (f == NULL) {
        return NULL;
    }
    fseek(f, 0, SEEK_END);
    len = ftell(f);
    fseek(f, 0, SEEK_SET);
    buf = (char*)malloc((size_t)len + 1);
    if (buf == NULL) {
        fclose(f);
        return NULL;
    }
    if (fread(buf, 1, (size_t)len, f) != (size_t)len) {
        fclose(f);
        free(buf);
        return NULL;
    }
    buf[len] = '\0';
    fclose(f);

    return buf;
}

/* ── esd_config_load ─────────────────────────────────────────────────── */

static void test_config_load_full_file(void)
{
    esd_config_t cfg;
    int          rc;

    memset(&cfg, 0, sizeof(cfg));

    write_file(g_tmpdir, "esd.yaml",
               "controller: 172.31.1.30:9990\n"
               "poll_interval: 30\n"
               "resources:\n"
               "  - name: Verilog_XL\n"
               "    collector: script\n"
               "    command: /etc/xce/lic-report.sh\n"
               "    interval: 15\n"
               "  - name: cloud_gpu_quota\n"
               "    collector: script\n"
               "    command: /etc/xce/quota-report.sh\n");

    rc = esd_config_load_path(g_tmpdir, "esd.yaml", &cfg);
    TEST_ASSERT_EQUAL_INT(0, rc);
    TEST_ASSERT_EQUAL_STRING("172.31.1.30", cfg.controller_host);
    TEST_ASSERT_EQUAL_INT(9990, cfg.controller_port);
    TEST_ASSERT_EQUAL_INT(30, cfg.poll_interval);
    TEST_ASSERT_EQUAL_INT(2, cfg.nsrc);

    TEST_ASSERT_NOT_NULL(cfg.src);
    TEST_ASSERT_EQUAL_STRING("Verilog_XL", cfg.src[0].name);
    TEST_ASSERT_EQUAL_STRING("/etc/xce/lic-report.sh", cfg.src[0].command);
    TEST_ASSERT_EQUAL_INT(15, cfg.src[0].interval);
    TEST_ASSERT_EQUAL_STRING("cloud_gpu_quota", cfg.src[1].name);
    TEST_ASSERT_EQUAL_STRING("/etc/xce/quota-report.sh", cfg.src[1].command);
    TEST_ASSERT_EQUAL_INT(0, cfg.src[1].interval); /* no override */

    esd_config_fini(&cfg);
}

static void test_config_load_missing_file_is_enoent(void)
{
    esd_config_t cfg;
    int          rc;

    memset(&cfg, 0, sizeof(cfg));

    rc = esd_config_load_path(g_tmpdir, "no-such-file.yaml", &cfg);
    TEST_ASSERT_EQUAL_INT(-ENOENT, rc);
}

static void test_config_load_bad_shape_is_einval(void)
{
    esd_config_t cfg;
    int          rc;

    memset(&cfg, 0, sizeof(cfg));

    /* a source without a name is structurally invalid -- the controller
     * would refuse the push and the operator would have no idea which
     * entry died; fail loudly at load. */
    write_file(g_tmpdir, "esd.yaml",
               "controller: 172.31.1.30:9990\n"
               "resources:\n"
               "  - collector: script\n"
               "    command: /bin/true\n");

    rc = esd_config_load_path(g_tmpdir, "esd.yaml", &cfg);
    TEST_ASSERT_EQUAL_INT(-EINVAL, rc);

    /* a source without a command can never report -- same rule. */
    memset(&cfg, 0, sizeof(cfg));
    write_file(g_tmpdir, "esd.yaml",
               "controller: 172.31.1.30:9990\n"
               "resources:\n"
               "  - name: lic\n"
               "    collector: script\n");

    rc = esd_config_load_path(g_tmpdir, "esd.yaml", &cfg);
    TEST_ASSERT_EQUAL_INT(-EINVAL, rc);
}

/* ── script collector output parsing (parse contract, not the spawn) ── */

static void test_parse_output_bare_number(void)
{
    double v = esd_parse_script_output("4\n");

    TEST_ASSERT_FALSE(isnan(v));
    TEST_ASSERT_EQUAL_FLOAT((float)4.0, (float)v);
}

static void test_parse_output_name_value(void)
{
    /* elim-style "<name> <value>" -- name may mismatch; the source it is
     * configured for is authoritative, the name is decorative. */
    double v = esd_parse_script_output("Verilog_XL 7\n");

    TEST_ASSERT_FALSE(isnan(v));
    TEST_ASSERT_EQUAL_FLOAT((float)7.0, (float)v);
}

static void test_parse_output_whitespace_and_negative(void)
{
    double v = esd_parse_script_output("  \t 3.5  \n");

    TEST_ASSERT_FALSE(isnan(v));
    TEST_ASSERT_EQUAL_FLOAT((float)3.5, (float)v);

    v = esd_parse_script_output("lic -1\n");
    TEST_ASSERT_FALSE(isnan(v));
    TEST_ASSERT_EQUAL_FLOAT((float)-1.0, (float)v);
}

static void test_parse_output_garbage_is_nan(void)
{
    double v;

    v = esd_parse_script_output("");
    TEST_ASSERT_TRUE(isnan(v));
    v = esd_parse_script_output("\n");
    TEST_ASSERT_TRUE(isnan(v));
    v = esd_parse_script_output("no digits here\n");
    TEST_ASSERT_TRUE(isnan(v));
    v = esd_parse_script_output(NULL);
    TEST_ASSERT_TRUE(isnan(v));
}

/* ── Phase 2: stale_limit config parsing ────────────────────────────── */

static void test_config_stale_limit_parse(void)
{
    esd_config_t cfg;
    int          rc;

    memset(&cfg, 0, sizeof(cfg));

    /* per-source override wins; a source without one takes the daemon
     * default; the daemon default itself is optional with a sane built-in
     * (design.md 3.4: stale_limit in esd.yaml, fail-open keep-old-value). */
    write_file(g_tmpdir, "esd.yaml",
               "controller: 172.31.1.30:9990\n"
               "poll_interval: 10\n"
               "stale_limit: 200\n"
               "resources:\n"
               "  - name: lic_a\n"
               "    collector: script\n"
               "    command: /bin/a.sh\n"
               "    stale_limit: 60\n"
               "  - name: lic_b\n"
               "    collector: script\n"
               "    command: /bin/b.sh\n");

    rc = esd_config_load_path(g_tmpdir, "esd.yaml", &cfg);
    TEST_ASSERT_EQUAL_INT(0, rc);
    TEST_ASSERT_EQUAL_INT(200, cfg.stale_limit);
    TEST_ASSERT_EQUAL_INT(60, cfg.src[0].stale_limit);
    TEST_ASSERT_EQUAL_INT(0, cfg.src[1].stale_limit); /* 0 = use default */

    esd_config_fini(&cfg);
}

/* ── Phase 2: stale predicate ───────────────────────────────────────── */

static void test_stale_predicate(void)
{
    esd_source_t src;

    memset(&src, 0, sizeof(src));
    src.name       = (char*)"lic";
    src.have_value = true;
    src.last_value = 3.0;

    /* Never report a value -> nothing to call stale; admission treats the
     * pool as 0 through the normal NO_RESOURCE path. */
    src.last_ok_time = 0;
    TEST_ASSERT_FALSE(esd_source_is_stale(&src, 100, 60));

    /* Fresh success (10s ago, limit 60) -> not stale. */
    src.last_ok_time = 90;
    TEST_ASSERT_FALSE(esd_source_is_stale(&src, 100, 60));

    /* Exactly at the limit -> not stale (strictly-greater rule, so an
     * interval == stale_limit config never flaps). */
    src.last_ok_time = 40;
    TEST_ASSERT_FALSE(esd_source_is_stale(&src, 100, 60));

    /* Past the limit -> stale. */
    src.last_ok_time = 39;
    TEST_ASSERT_TRUE(esd_source_is_stale(&src, 100, 60));

    /* A source whose own stale_limit override is set uses it. */
    src.stale_limit = 10;
    TEST_ASSERT_TRUE(esd_source_is_stale(&src, 100, 60));
    src.last_ok_time = 95;
    TEST_ASSERT_FALSE(esd_source_is_stale(&src, 100, 60));

    /* last_ok_time newer than `now` (clock skew between test harness and
     * caller) must not read as stale. */
    src.last_ok_time = 105;
    TEST_ASSERT_FALSE(esd_source_is_stale(&src, 100, 60));
}

/* ── Phase 2: status file ───────────────────────────────────────────── */

static void test_status_write_basic(void)
{
    esd_config_t cfg;
    esd_stats_t  stats;
    char         path[512];
    char*        text;
    time_t       now = time(NULL);
    char         expect_lvt[128];

    memset(&cfg, 0, sizeof(cfg));
    cfg.nsrc = 1;
    cfg.src  = (esd_source_t*)calloc(1, sizeof(esd_source_t));
    TEST_ASSERT_NOT_NULL(cfg.src);
    cfg.src[0].name       = (char*)"extlic";
    cfg.src[0].have_value = true;
    cfg.src[0].last_value = 3.0;
    /* fresh success: last good value 5s ago, limit default 150 -> not
     * stale (the marks-stale test below covers the other side) */
    cfg.src[0].last_ok_time = now - 5;
    cfg.stale_limit         = ESD_STALE_LIMIT_DEFAULT;

    memset(&stats, 0, sizeof(stats));
    stats.started_at  = 1000;
    stats.pushes_ok   = 7;
    stats.pushes_fail = 1;

    snprintf(path, sizeof(path), "%s/status.json", g_tmpdir);
    TEST_ASSERT_EQUAL_INT(0, esd_status_write(path, &cfg, &stats));

    text = slurp(path);
    TEST_ASSERT_NOT_NULL(text);

    /* The fields xceadmin extres status reads, and the stale flag driven
     * by the same predicate the tests above pin. */
    TEST_ASSERT_TRUE(strstr(text, "\"daemon\": \"xceesd\"") != NULL);
    TEST_ASSERT_TRUE(strstr(text, "\"name\": \"extlic\"") != NULL);
    snprintf(expect_lvt, sizeof(expect_lvt), "\"last_value\": %.17g", 3.0);
    TEST_ASSERT_TRUE(strstr(text, expect_lvt) != NULL);
    TEST_ASSERT_TRUE(strstr(text, "\"last_ok_time\": ") != NULL);
    TEST_ASSERT_TRUE(strstr(text, "\"stale\": false") != NULL);
    TEST_ASSERT_TRUE(strstr(text, "\"pushes_ok\": 7") != NULL);
    TEST_ASSERT_TRUE(strstr(text, "\"pushes_fail\": 1") != NULL);

    free(text);
    free(cfg.src);
}

static void test_status_write_marks_stale(void)
{
    esd_config_t cfg;
    esd_stats_t  stats;
    char         path[512];
    char*        text;
    time_t       now = time(NULL);

    memset(&cfg, 0, sizeof(cfg));
    cfg.nsrc = 1;
    cfg.src  = (esd_source_t*)calloc(1, sizeof(esd_source_t));
    TEST_ASSERT_NOT_NULL(cfg.src);
    cfg.src[0].name       = (char*)"extlic";
    cfg.src[0].have_value = true;
    cfg.src[0].last_value = 2.0;
    /* last success 1 hour ago, limit 150s -> stale. */
    cfg.src[0].last_ok_time = now - 3600;
    cfg.src[0].stale_limit  = 150;

    memset(&stats, 0, sizeof(stats));

    snprintf(path, sizeof(path), "%s/status.json", g_tmpdir);
    TEST_ASSERT_EQUAL_INT(0, esd_status_write(path, &cfg, &stats));

    text = slurp(path);
    TEST_ASSERT_NOT_NULL(text);
    TEST_ASSERT_TRUE(strstr(text, "\"stale\": true") != NULL);

    free(text);
    free(cfg.src);
}

/* ── bug-1978: the reconnect-flag contract ───────────────────────────── */

static void test_reconnect_sets_both_rejoin_and_full_push(void)
{
    g_needs_rejoin    = 0;
    g_needs_full_push = 0;

    TEST_ASSERT_EQUAL_INT(0, esd_on_reconnect((xcecli_ctx_t)0x1, NULL));

    /* BOTH flags: the re-join must happen before any re-push (an un-joined
     * push is refused -EPERM on the fresh endpoint), and the re-push must
     * still happen (the fresh controller knows no values). The bug-1978
     * defect cleared only g_needs_full_push -- a daemon that re-pushed onto
     * an un-joined HostRole_client endpoint, every push -EPERM forever. */
    TEST_ASSERT_EQUAL_INT(1, g_needs_rejoin);
    TEST_ASSERT_EQUAL_INT(1, g_needs_full_push);
}

static void test_reconnect_flags_recover_from_any_previous_state(void)
{
    /* The handler is level-set, not level-toggle: regardless of what a
     * previous (already consumed) reconnect left behind, a new callback
     * invocation re-arms both flags. */
    g_needs_rejoin    = 0;
    g_needs_full_push = 1; /* stale leftover from an unconsumed cycle */

    TEST_ASSERT_EQUAL_INT(0, esd_on_reconnect((xcecli_ctx_t)0x2, NULL));

    TEST_ASSERT_EQUAL_INT(1, g_needs_rejoin);
    TEST_ASSERT_EQUAL_INT(1, g_needs_full_push);
}

int main(void)
{
    UNITY_BEGIN();

    RUN_TEST(test_config_load_full_file);
    RUN_TEST(test_config_load_missing_file_is_enoent);
    RUN_TEST(test_config_load_bad_shape_is_einval);
    RUN_TEST(test_parse_output_bare_number);
    RUN_TEST(test_parse_output_name_value);
    RUN_TEST(test_parse_output_whitespace_and_negative);
    RUN_TEST(test_parse_output_garbage_is_nan);
    RUN_TEST(test_config_stale_limit_parse);
    RUN_TEST(test_stale_predicate);
    RUN_TEST(test_status_write_basic);
    RUN_TEST(test_status_write_marks_stale);
    RUN_TEST(test_reconnect_sets_both_rejoin_and_full_push);
    RUN_TEST(test_reconnect_flags_recover_from_any_previous_state);

    return UNITY_END();
}