wdgzyjx/myxce
1
0
Fork 0
forked from lei.chen/myxce
Code Pull requests Activity

test(ha-commit-barrier-rollout): RED tests for mark_job_* guards (task 6.1)

Browse source 
3 RED carriers (duplicate FINISH on DONE appends a 2nd WAL entry +
overwrites state; START on terminal clobbers it; replay non-equivalent)
+ 2 preservation pins (forward postdone PDONE-merge, fail-after-finish
PERR-merge) that 6.2 must not break. Reviewer-confirmed: the
UPDATE-clears-terminal arm is production-unreachable (pinned, not
driven). 22 tests / 3 RED; census 508 distinct triples, only those 3
fail.
This commit is contained in:
Rongsong Shen 2026-06-13 04:20:05 +00:00
parent 5a2fae1d37
commit 2308389eb1
4 changed files with 365 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

355
src/controller/testsuite/test_commit_barrier_reply.c
View file

@ -1498,6 +1498,352 @@ static void test_fact_retention_across_quorum_loss(void)
printf("test_fact_retention_across_quorum_loss: PASS\n");
}
/* ════════════════════════════════════════════════════════════════════════
* Idempotency / ordering guards for mark_job_* (task 6.1, Req 5.1/5.2/5.3)
* ════════════════════════════════════════════════════════════════════════
*
* RED-phase tests for the transition guards that task 6.2 adds at the top
* of mark_job_start / mark_job_finish / mark_job_fail / mark_job_update
* (job.c:583/638/696/726 pre-task anchors). Design §Idempotency Guards:
* - duplicate (already-reflected transition) → INFO log, NO-OP: state
* unchanged, BEFORE/AFTER_EVENT hooks NOT fired → NO WAL entry appended
* (current_lsn unmoved), caller-visible rc treated as success-no-op (5.1)
* - backward (terminal current state, non-terminal requested: START on a
* finished job, UPDATE clearing terminal bits) → WARN log, REJECT,
* terminal state preserved (5.2)
* - replay: re-applying the same transition converges to single-
* application state — no second WAL entry, identical final state (5.3)
* - mark_job_fail's existing fail-after-finish PERR-merge (job.c:702-716)
* is forward-compatible and must be PRESERVED by the guard (pin)
*
* Drivers: the static mark_job_* are reached through their non-static
* callers on_job_start / on_job_finish / on_job_fail (job.c) — exactly the
* fact path used by test_fact_retention_across_quorum_loss, minus the
* opcode decode. These wrappers each return 0 unconditionally today, so the
* "success-no-op rc" observable (every caller treats a guarded-out
* transition as success) is asserted directly on the wrapper rc.
*
* Observability of state: the per-job WAL append count and the LAST
* recorded post-transition state come from cbrp_count_jobstate_entries
* (direct on-disk scan, defined above); the job's LIVE in-memory state is
* read via cbrp_job_live_state (key_find on g_hc.jobmgr). current_lsn is
* the "did a hook fire / WAL entry append" oracle (a guarded-out no-op runs
* no hooks → no persist_wal_async → current_lsn frozen).
*
* RED expectation against the UNGUARDED mark_job_* (no guard yet):
* - duplicate FINISH re-fires the AFTER_EVENT hook → a 2nd WAL_JOB_FINISH
* append, current_lsn advances → the "current_lsn unmoved / count==1"
* assertions FAIL.
* - START on a DONE job unconditionally sets state = JOB_STAT_RUN and
* appends WAL_JOB_START → the "state preserved DONE / no new append"
* assertions FAIL.
* - replay FINISH appends a duplicate entry → the "single append"
* assertion FAILS.
* The fail-after-finish PERR-merge pin and the success-no-op rc pins lock
* behavior that must hold both before and after the guard (preservation
* pins, like the task-3.1 validation pins); they ride this group so 6.2
* cannot silently regress the merge or the wrapper return contract.
*
* NOTE on the UPDATE-clears-terminal arm (5.2): mark_job_update is static
* with no public caller that produces a terminal→non-terminal state
* (on_job_postdone's update is forward — it OR's PDONE, preserving terminal;
* job_ctrl SIGCONT only clears suspend bits). mark_job_start IS the
* canonical "set state to the non-terminal JOB_STAT_RUN" overwrite, so the
* START-on-terminal case below is the faithful, publicly-reachable witness
* of the shared backward rule the design lists for START and UPDATE
* together. test_guard_forward_update_on_terminal_preserved additionally
* pins that a FORWARD update on a terminal job (on_job_postdone) is NOT
* over-rejected — the boundary the guard must respect.
*/
/* Read a job's live in-memory state from g_hc.jobmgr (post-transition).
* Returns the state flags, or -1 if the job is absent. */
static int cbrp_job_live_state(uint64_t jobid)
{
job_t *j = NULL;
int st = -1;
lock(g_hc.jobmgr, RTTI_LOCK_READ);
key_find(g_hc.jobmgr, (void *)jobid, (void **)&j);
if (j != NULL) {
reference(j);
}
unlock(g_hc.jobmgr);
if (j != NULL) {
lock(j, RTTI_LOCK_READ);
st = (int)j->job.state;
unlock(j);
dereference(j);
}
return st;
}
/* Drive a job to terminal DONE via start(jobid) → finish(jobid, exit 0).
* Returns current_lsn after the two forward facts (the watermark the
* duplicate/backward cases must NOT advance). */
static uint64_t cbrp_drive_to_done(uint64_t jobid)
{
static unsigned int gd_pids[1] = { 9999 };
job_pidinfo_t start;
xce_jobfinish_t fin;
uint64_t lsn;
memset(&start, 0, sizeof(start));
start.jobid = jobid;
start.npids = 1;
start.pids = &gd_pids[0];
TEST_ASSERT_EQUAL_INT(0, on_job_start(&g_hc, &start));
memset(&fin, 0, sizeof(fin));
fin.jobid = jobid;
fin.exit_code = 0; /* → JOB_STAT_DONE */
TEST_ASSERT_EQUAL_INT(0, on_job_finish(&g_hc, &fin));
TEST_ASSERT_EQUAL_INT_MESSAGE(JOB_STAT_DONE, cbrp_job_live_state(jobid),
"precondition: job must be DONE after start→finish(0)");
pthread_mutex_lock(&g_hc.persist.lock);
lsn = g_hc.persist.current_lsn;
pthread_mutex_unlock(&g_hc.persist.lock);
return lsn;
}
/* 5.1 — duplicate FINISH on a DONE job is a logged no-op: state unchanged,
* NO AFTER_EVENT hook fired (NO new WAL entry → current_lsn frozen), exactly
* one FINISH entry on disk, and on_job_finish returns success-no-op (0). */
static void test_guard_duplicate_finish_on_done_is_noop(void)
{
xce_jobfinish_t fin;
uint64_t lsn_after_done, lsn_after_dup;
uint32_t st_finish = 0;
int rc;
cbrp_setup(3000);
cbrp_make_job(70, &g_job_submit);
memset(&g_job_submit, 0, sizeof(g_job_submit));
lsn_after_done = cbrp_drive_to_done(70);
TEST_ASSERT_EQUAL_INT_MESSAGE(1,
cbrp_count_jobstate_entries(&g_hc.persist, WAL_JOB_FINISH, 70, NULL),
"exactly one FINISH entry must exist after the first finish");
/* Act: a duplicate FINISH on the already-DONE job (retransmit / replay) */
memset(&fin, 0, sizeof(fin));
fin.jobid = 70;
fin.exit_code = 0;
rc = on_job_finish(&g_hc, &fin);
pthread_mutex_lock(&g_hc.persist.lock);
lsn_after_dup = g_hc.persist.current_lsn;
pthread_mutex_unlock(&g_hc.persist.lock);
/* Assert: success-no-op rc; state unchanged; NO hook fired (no append) */
TEST_ASSERT_EQUAL_INT_MESSAGE(0, rc,
"a guarded-out duplicate FINISH must return success-no-op (5.1)");
TEST_ASSERT_EQUAL_INT_MESSAGE(JOB_STAT_DONE, cbrp_job_live_state(70),
"duplicate FINISH must leave the job's state unchanged (5.1)");
TEST_ASSERT_EQUAL_UINT64_MESSAGE(lsn_after_done, lsn_after_dup,
"duplicate FINISH must fire NO AFTER_EVENT hook → NO WAL entry "
"appended → current_lsn unmoved (5.1)");
TEST_ASSERT_EQUAL_INT_MESSAGE(1,
cbrp_count_jobstate_entries(&g_hc.persist, WAL_JOB_FINISH, 70,
&st_finish),
"duplicate FINISH must not append a second FINISH entry (5.1)");
TEST_ASSERT_EQUAL_UINT32(JOB_STAT_DONE, st_finish);
cbrp_teardown();
printf("test_guard_duplicate_finish_on_done_is_noop: PASS\n");
}
/* 5.2 — START on a finished (DONE) job is rejected: the terminal state is
* preserved (never overwritten with JOB_STAT_RUN), NO WAL_JOB_START entry is
* appended, and on_job_start returns a success-no-op code that the caller
* (do_notify) treats as success. mark_job_start is the canonical
* terminal→non-terminal overwrite, so this also witnesses the UPDATE-clears-
* terminal arm of the shared backward rule (5.2). */
static void test_guard_start_on_terminal_rejected_state_preserved(void)
{
static unsigned int rs_pids[1] = { 7001 };
job_pidinfo_t restart;
uint64_t lsn_after_done, lsn_after_start;
int rc;
cbrp_setup(3000);
cbrp_make_job(71, &g_job_submit);
memset(&g_job_submit, 0, sizeof(g_job_submit));
lsn_after_done = cbrp_drive_to_done(71);
/* Precondition: drive_to_done's start→finish appended exactly one
* WAL_JOB_START (the forward start). The rejected backward START below
* must not add a second one. */
TEST_ASSERT_EQUAL_INT_MESSAGE(1,
cbrp_count_jobstate_entries(&g_hc.persist, WAL_JOB_START, 71, NULL),
"precondition: exactly one START entry from the forward start");
/* Act: a stale/duplicate START arrives for the already-finished job */
memset(&restart, 0, sizeof(restart));
restart.jobid = 71;
restart.npids = 1;
restart.pids = &rs_pids[0];
rc = on_job_start(&g_hc, &restart);
pthread_mutex_lock(&g_hc.persist.lock);
lsn_after_start = g_hc.persist.current_lsn;
pthread_mutex_unlock(&g_hc.persist.lock);
/* Assert: terminal preserved, no append, success-no-op rc */
TEST_ASSERT_EQUAL_INT_MESSAGE(0, rc,
"a rejected backward START must return success-no-op to the caller "
"(5.2)");
TEST_ASSERT_EQUAL_INT_MESSAGE(JOB_STAT_DONE, cbrp_job_live_state(71),
"START on a DONE job must preserve the terminal state — never "
"overwrite it with JOB_STAT_RUN (5.2)");
TEST_ASSERT_EQUAL_UINT64_MESSAGE(lsn_after_done, lsn_after_start,
"a rejected backward START must append NO WAL entry (5.2)");
TEST_ASSERT_EQUAL_INT_MESSAGE(1,
cbrp_count_jobstate_entries(&g_hc.persist, WAL_JOB_START, 71, NULL),
"a rejected backward START must not append a second START entry "
"(5.2)");
cbrp_teardown();
printf("test_guard_start_on_terminal_rejected_state_preserved: PASS\n");
}
/* 5.3 — replay equivalence: applying the same FINISH transition twice yields
* state identical to a single application AND a single WAL entry. The second
* application is the guarded-out duplicate; the on-disk FINISH count staying
* at 1 with current_lsn frozen is the replay-once invariant. */
static void test_guard_replay_finish_equals_single_application(void)
{
xce_jobfinish_t fin;
uint64_t lsn_single, lsn_replay;
int state_single, state_replay;
uint32_t st_disk = 0;
cbrp_setup(3000);
cbrp_make_job(72, &g_job_submit);
memset(&g_job_submit, 0, sizeof(g_job_submit));
/* Single application baseline */
lsn_single = cbrp_drive_to_done(72);
state_single = cbrp_job_live_state(72);
TEST_ASSERT_EQUAL_INT(1,
cbrp_count_jobstate_entries(&g_hc.persist, WAL_JOB_FINISH, 72, NULL));
/* Replay the FINISH (retry / WAL replay re-application) */
memset(&fin, 0, sizeof(fin));
fin.jobid = 72;
fin.exit_code = 0;
TEST_ASSERT_EQUAL_INT_MESSAGE(0, on_job_finish(&g_hc, &fin),
"replayed FINISH must return success-no-op (5.3)");
pthread_mutex_lock(&g_hc.persist.lock);
lsn_replay = g_hc.persist.current_lsn;
pthread_mutex_unlock(&g_hc.persist.lock);
state_replay = cbrp_job_live_state(72);
/* Assert: state and the WAL log are identical to single application */
TEST_ASSERT_EQUAL_INT_MESSAGE(state_single, state_replay,
"replayed transition must converge to single-application state "
"(5.3)");
TEST_ASSERT_EQUAL_UINT64_MESSAGE(lsn_single, lsn_replay,
"replaying a committed transition must append no second WAL entry "
"(5.3)");
TEST_ASSERT_EQUAL_INT_MESSAGE(1,
cbrp_count_jobstate_entries(&g_hc.persist, WAL_JOB_FINISH, 72,
&st_disk),
"the FINISH fact must remain on disk exactly once after replay "
"(5.3)");
TEST_ASSERT_EQUAL_UINT32(JOB_STAT_DONE, st_disk);
cbrp_teardown();
printf("test_guard_replay_finish_equals_single_application: PASS\n");
}
/* 5.2 boundary pin — a FORWARD update on a terminal job must NOT be
* over-rejected by the guard. on_job_postdone is the reachable mark_job_update
* caller: on a DONE job it OR's JOB_STAT_PDONE (terminal preserved, strictly
* forward). This must still apply (state gains PDONE, an entry appends) after
* the guard lands — the guard rejects backward, never a forward merge.
* Preservation pin: green before and after task 6.2. */
static void test_guard_forward_update_on_terminal_preserved(void)
{
uint64_t lsn_after_done, lsn_after_pdone;
int st;
cbrp_setup(3000);
cbrp_make_job(73, &g_job_submit);
memset(&g_job_submit, 0, sizeof(g_job_submit));
lsn_after_done = cbrp_drive_to_done(73);
/* Act: post-done arrives — forward update merging PDONE onto DONE */
TEST_ASSERT_EQUAL_INT(0, on_job_postdone(&g_hc, &g_req_ep, 73));
pthread_mutex_lock(&g_hc.persist.lock);
lsn_after_pdone = g_hc.persist.current_lsn;
pthread_mutex_unlock(&g_hc.persist.lock);
st = cbrp_job_live_state(73);
/* Assert: terminal preserved, PDONE merged forward, the update appended */
TEST_ASSERT_TRUE_MESSAGE((st & JOB_STAT_DONE) != 0,
"a forward update on a terminal job must preserve the terminal bit");
TEST_ASSERT_TRUE_MESSAGE((st & JOB_STAT_PDONE) != 0,
"the forward update must merge JOB_STAT_PDONE (not be rejected)");
TEST_ASSERT_TRUE_MESSAGE(lsn_after_pdone > lsn_after_done,
"a forward update on a terminal job must still append its WAL entry "
"— the guard rejects backward transitions, never forward merges");
cbrp_teardown();
printf("test_guard_forward_update_on_terminal_preserved: PASS\n");
}
/* 5.2 pin — mark_job_fail's existing fail-after-finish PERR-merge
* (job.c:702-716) must be PRESERVED by the guard: a POST_EXEC-stage fail on a
* DONE job keeps DONE and OR's JOB_STAT_PERR (it does NOT reset the job to a
* bare JOB_STAT_EXIT). Forward-compatible terminal→terminal merge — the guard
* must not reject it. Preservation pin: green before and after task 6.2. */
static void test_guard_fail_after_finish_preserves_perr_merge(void)
{
job_failinfo_t failinfo;
uint64_t lsn_after_done, lsn_after_fail;
int st;
cbrp_setup(3000);
cbrp_make_job(74, &g_job_submit);
memset(&g_job_submit, 0, sizeof(g_job_submit));
lsn_after_done = cbrp_drive_to_done(74);
/* Act: a post-exec-stage failure for the already-finished job */
memset(&failinfo, 0, sizeof(failinfo));
failinfo.jobid = 74;
failinfo.stage = JOB_EXEC_STAGE_POST_EXEC;
failinfo.code = 1;
failinfo.detail = (char *)"post-exec fail after finish";
TEST_ASSERT_EQUAL_INT(0, on_job_fail(&g_hc, &failinfo));
pthread_mutex_lock(&g_hc.persist.lock);
lsn_after_fail = g_hc.persist.current_lsn;
pthread_mutex_unlock(&g_hc.persist.lock);
st = cbrp_job_live_state(74);
/* Assert: DONE preserved, PERR merged in — not reset to bare EXIT */
TEST_ASSERT_TRUE_MESSAGE((st & JOB_STAT_DONE) != 0,
"fail-after-finish must keep the DONE terminal bit (PERR-merge "
"behavior, job.c:702-716)");
TEST_ASSERT_TRUE_MESSAGE((st & JOB_STAT_PERR) != 0,
"fail-after-finish must OR JOB_STAT_PERR onto the existing terminal "
"state (PERR-merge behavior, job.c:702-716)");
TEST_ASSERT_TRUE_MESSAGE(lsn_after_fail > lsn_after_done,
"the PERR-merge fail must still append its WAL entry (forward "
"terminal→terminal merge — not a guarded-out no-op)");
cbrp_teardown();
printf("test_guard_fail_after_finish_preserves_perr_merge: PASS\n");
}
/* ── Test group entry point ──────────────────────────────────────────── */
void test_commit_barrier_reply(void)
@ -1534,5 +1880,14 @@ void test_commit_barrier_reply(void)
/* Fact retention across quorum loss (task 4.3, Req 3.1, 3.3, 3.4) —
* green on landing against tasks 1.2 + 4.2 output */
RUN_TEST(test_fact_retention_across_quorum_loss);
/* mark_job_* idempotency / ordering guards (task 6.1, Req 5.1/5.2/5.3)
* — the no-op / backward-reject / replay cases FAIL (red) against the
* unguarded mark_job_*; the forward-merge and PERR-merge cases are
* preservation pins (green before and after task 6.2) */
RUN_TEST(test_guard_duplicate_finish_on_done_is_noop);
RUN_TEST(test_guard_start_on_terminal_rejected_state_preserved);
RUN_TEST(test_guard_replay_finish_equals_single_application);
RUN_TEST(test_guard_forward_update_on_terminal_preserved);
RUN_TEST(test_guard_fail_after_finish_preserves_perr_merge);
UNITY_END();
}