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

test(ha-commit-barrier-rollout): receipt-ACK verdict pins (task 3.3)

Browse source 
4 green pins: handle_jobdispatch replies receipt-only with zero WAL
appends through a real 2-alloc dispatch cycle (notify outcomes intact,
reply-precedes-processing); set/clr_preason and do_update_op rusage
stay receipt-style with RETAIN-pending fact appends ACK-committed.
Umbrella Reply-Ordering Contract cited per pin. DISCOVERY bug-451
(reviewer-verified): RUSAGE hook va_list type confusion — 4-byte OOB
read + garbage state in WAL_JOB_RUSAGE payloads; fix deferred to 7.1.
Census 488; zero failures.
This commit is contained in:
Rongsong Shen 2026-06-12 11:16:51 +00:00
parent facdb90917
commit 7103fa643d
6 changed files with 865 additions and 327 deletions
Download patch file Download diff file Expand all files Collapse all files

1
src/controller/meson.build
View file

@ -127,6 +127,7 @@ controller_unit_test_src = [
'job.c',
'queue.c',
'join.c',
'opupd.c',
'startup_validation.c',
'worker.c',
'persist.c',

517
src/controller/testsuite/test_commit_barrier_reply.c
View file

@ -5,6 +5,14 @@
* timeout → -ETIMEDOUT error reply), 1.3 (barrier rejection → error reply,
* never success), 1.4 (no success-interpretable reply pre-commit).
*
* ALSO HOSTS (task 3.3, Req 2.3): the receipt-ACK verdict pins for
* handle_jobdispatch, do_set_preason / do_clr_preason, and the
* do_update_op rusage path — see the "Receipt-ACK verdict pins" section.
* These land GREEN by design (pins of current correct behavior, like the
* 3.1 validation pins); they live here, not in a new file, because they
* reuse this file's entire harness: cluster + real persist + wired engine
* + stub standby registry + reply-capture endpoint + the job.c link.
*
* Drives the four request-shaped handlers DIRECTLY on a worker pthread
* (vtask-context stand-in; production dispatch: cluster.c:325-363) against
* a real tmpdir persist_t embedded in a test cluster_t with registered
@ -83,21 +91,66 @@
#include "typemap.h"
#include "wal_types.h"
#include "wobj.h"
#include "xcealloc.h"
#include "xstring.h"
#include "zarray.h"
/* ── Link stubs ──────────────────────────────────────────────────────────
* job.c / join.c reference these cross-module functions (opupd.c, sched.c,
* apiserver.c — not part of the unit-test link). None of them sits on the
* four code paths under test (jobctrl not-started branch, queue/host ctrl,
* worker join); stubbed so the binary links, same precedent as
* test_worker_join.c's collect_confvars stub. */
* job.c / join.c / opupd.c reference these cross-module functions (dataex.c,
* misc.c, sched.c, apiserver.c — not part of the unit-test link). For the
* 3.1 paths (jobctrl not-started branch, queue/host ctrl, worker join) all
* stubs are inert; for the 3.3 verdict pins two of them gained test
* controls with NULL/no-op defaults that preserve the 3.1 behavior:
* notify() — captures dispatch-outcome notifications (jobdispatch
* verdict pin observes notify_dispatch through it)
* get_ep_worker() — returns g_stub_ep_worker (rusage verdict pin needs a
* reporting worker; production impl is misc.c:49) */
static endpoint_t g_req_ep; /* requester endpoint (capture; set up below) */
/* notify() capture — records each xce_notify_data_t delivery. For
* jobDispatchFail events (the shared ok/fail event of notify_dispatch,
* job.c) jobid + code are unpacked; reply_already_enqueued snapshots
* whether the receipt ACK was already sitting on the requester outq when
* the outcome notification fired (single-threaded handler call → exact
* ordering observation, no race). */
#define CBRP_MAX_NOTIFY 8
static int g_notify_count;
static int g_notify_events[CBRP_MAX_NOTIFY];
static uint64_t g_notify_jobids[CBRP_MAX_NOTIFY];
static int g_notify_codes[CBRP_MAX_NOTIFY];
static int g_notify_reply_already_enqueued[CBRP_MAX_NOTIFY];
static void cbrp_notify_capture_reset(void)
{
g_notify_count = 0;
memset(g_notify_events, 0, sizeof(g_notify_events));
memset(g_notify_jobids, 0, sizeof(g_notify_jobids));
memset(g_notify_codes, 0, sizeof(g_notify_codes));
memset(g_notify_reply_already_enqueued, 0,
sizeof(g_notify_reply_already_enqueued));
}
static worker_t *g_stub_ep_worker; /* NULL by default (3.1 behavior) */
/* clang-format off */
int notify(cluster_t *c, endpoint_t *e, xce_notify_data_t *d)
{ (void)c; (void)e; (void)d; return 0; }
{
(void)c; (void)e;
if (g_notify_count < CBRP_MAX_NOTIFY) {
g_notify_events[g_notify_count] = d->event;
if (d->event == NotifyData_data_jobDispatchFail) {
g_notify_jobids[g_notify_count] = d->data.dispatchfail->jobid;
g_notify_codes[g_notify_count] = d->data.dispatchfail->code;
}
g_notify_reply_already_enqueued[g_notify_count] =
!DATAQ_EMPTY(&g_req_ep.outq);
}
g_notify_count++;
return 0;
}
worker_t *get_ep_worker(cluster_t *c, endpoint_t *e)
{ (void)c; (void)e; return NULL; }
{ (void)c; (void)e; return g_stub_ep_worker; }
int update_host_runusage(xce_job_runusage_t **r, char *h, int n,
xce_rusage_t **u)
{ (void)r; (void)h; (void)n; (void)u; return 0; }
@ -277,6 +330,8 @@ static void cbrp_setup(uint32_t sync_timeout_ms)
memset(&g_req_ep, 0, sizeof(g_req_ep));
memset(&g_req_priv, 0, sizeof(g_req_priv));
memset(&g_req_from, 0, sizeof(g_req_from));
cbrp_notify_capture_reset();
g_stub_ep_worker = NULL;
/* Requester endpoint: zeroed, no iomgr — xce_reply packets stay on
* ep->outq (see file header). */
@ -385,21 +440,30 @@ static xce_jobctrl_t g_jobctrl;
static xce_request_t g_jobctrl_req;
static job_submit_data_t g_job_submit; /* job_init requires submit != NULL */
static int g_jobobj_ready; /* jobj module tables — once per process */
/* Create a pending (never-started) job in g_hc.jobmgr. submit may carry
* queue/user/start_info (deep-copied by makeJob via makeJobsub). */
static void cbrp_make_job(uint64_t jobid, job_submit_data_t *submit)
{
xce_job_t jdef;
if (!g_jobobj_ready) {
TEST_ASSERT_EQUAL_INT(0, job_obj_init(64, 64));
g_jobobj_ready = 1;
}
memset(&jdef, 0, sizeof(jdef));
jdef.jobid = jobid;
jdef.state = JOB_STAT_PEND;
jdef.submit = submit;
TEST_ASSERT_NOT_NULL(makeJob(g_hc.jobmgr, &jdef));
}
static void cbrp_arrange_jobctrl(uint64_t jobid, int create_job)
{
if (create_job) {
xce_job_t jdef;
static int jobobj_ready; /* jobj module tables — once per process */
if (!jobobj_ready) {
TEST_ASSERT_EQUAL_INT(0, job_obj_init(64, 64));
jobobj_ready = 1;
}
memset(&g_job_submit, 0, sizeof(g_job_submit));
memset(&jdef, 0, sizeof(jdef));
jdef.jobid = jobid;
jdef.state = JOB_STAT_PEND;
jdef.submit = &g_job_submit;
TEST_ASSERT_NOT_NULL(makeJob(g_hc.jobmgr, &jdef));
cbrp_make_job(jobid, &g_job_submit);
}
memset(&g_jobctrl, 0, sizeof(g_jobctrl));
g_jobctrl.action = JobControl_u_siginfo;
@ -768,6 +832,418 @@ static void test_worker_join_no_hostconfig_error_reply_immediate(void)
printf("test_worker_join_no_hostconfig_error_reply_immediate: PASS\n");
}
/* ════════════════════════════════════════════════════════════════════════
* Receipt-ACK verdict pins (ha-commit-barrier-rollout task 3.3, Req 2.3)
*
* Umbrella Reply-Ordering Contract reference (ha-consistency-invariants
* design.md §Write-Path Classification ▸ Reply-Ordering Contract):
* handle_jobdispatch's early reply is an ACK-of-receipt and MAY STAND,
* because dispatch outcomes are fact-shaped — per-job results are
* delivered via notify_dispatch, and the resulting job-state changes
* arrive later as worker-reported facts. The same verdict covers
* do_set_preason / do_clr_preason (scheduler-origin WAL_JOB_PREASON
* facts, RETAIN) and the do_update_op rusage path (worker-origin
* WAL_JOB_UPDATE + WAL_JOB_RUSAGE facts, RETAIN): their replies
* acknowledge RECEIPT of the report, never commitment of any
* state-changing log entry.
*
* These are PINS of current correct behavior — green on landing, no RED
* phase exists (task-stated design, like the 3.1 validation pins). They
* run with ACKs withheld throughout, so any future regression that makes
* one of these handlers wait on the commit barrier trips the latency
* bound, and any future WAL append from dispatch processing trips either
* the unchanged-LSN pin or (for an unclassified type) the XCE_TESTING
* abort in wal_classify — the classification guard stays silent through
* a clean dispatch cycle.
* ════════════════════════════════════════════════════════════════════════ */
/* ── handle_jobdispatch fixture ──────────────────────────────────────── */
static endpoint_t g_wkr_disp_ep; /* dispatch worker endpoint */
static job_submit_data_t g_disp_submit;
static job_startinfo_t g_disp_startinfo;
static xce_job_dispatch_t g_dispatchmsg;
static xce_job_alloc_t *g_dispatch_allocs[2];
static xce_request_t g_dispatch_req;
#define CBRP_DISP_JOBID 60u
/* Full dispatch fixture: queue (get_queue_exec), pending job with a real
* submit (dispatch_a_job_ reads submit->queue and submit->start_info),
* worker with a live no-iomgr endpoint (the startjob request must be
* enqueueable), and a 2-job dispatch message exercising BOTH outcomes:
* allocs[0] — dispatchable to wkr-disp → notify_dispatch(ok, code 0)
* allocs[1] — nhosts == 0 → notify_dispatch(fail, -EINVAL)
* The allocs are heap-built via xcealloc helpers because the handler
* takes ownership (MOVE_PTR + free_JobAlloc_ptr per job). */
static void cbrp_arrange_jobdispatch(void)
{
xce_queue_t qdef;
xce_worker_t wdef;
hostattrs_t *attrs = NULL;
worker_t *w = NULL;
memset(&qdef, 0, sizeof(qdef));
qdef.queue = (char *)"qd";
TEST_ASSERT_NOT_NULL(makeQueue(g_hc.qmgr, &qdef));
memset(&g_disp_startinfo, 0, sizeof(g_disp_startinfo));
g_disp_startinfo.cmdline = (char *)"/bin/true";
memset(&g_disp_submit, 0, sizeof(g_disp_submit));
g_disp_submit.queue = (char *)"qd";
g_disp_submit.user = (char *)"tester";
g_disp_submit.start_info = &g_disp_startinfo;
cbrp_make_job(CBRP_DISP_JOBID, &g_disp_submit);
attrs = calloc(1, sizeof(*attrs));
TEST_ASSERT_NOT_NULL(attrs);
attrs->hosttype = makeString("LINUX");
attrs->hostmodel = makeString("x86");
attrs->cpufactor = 1.0f;
attrs->maxcpus = 4;
memset(&wdef, 0, sizeof(wdef));
wdef.name = (char *)"wkr-disp";
wdef.attrs = attrs;
TEST_ASSERT_NOT_NULL(makeWorker(g_hc.workermgr, &wdef));
/* dispatch gate: worker must have an endpoint and status 0 */
memset(&g_wkr_disp_ep, 0, sizeof(g_wkr_disp_ep));
g_wkr_disp_ep.fd = -1;
lock(g_hc.workermgr, RTTI_LOCK_READ);
key_find(g_hc.workermgr, (void *)"wkr-disp", (void **)&w);
unlock(g_hc.workermgr);
TEST_ASSERT_NOT_NULL(w);
w->ep = &g_wkr_disp_ep;
g_dispatch_allocs[0] = make_job_alloc(
CBRP_DISP_JOBID, 1,
make_host_allocs(1,
make_host_alloc((char *)"wkr-disp", 1,
make_allocs(1,
make_alloc((char *)"slots", NULL, 0, 1.0f, 0)))));
TEST_ASSERT_NOT_NULL(g_dispatch_allocs[0]);
g_dispatch_allocs[1] = make_job_alloc(CBRP_DISP_JOBID, 0, NULL);
TEST_ASSERT_NOT_NULL(g_dispatch_allocs[1]);
memset(&g_dispatchmsg, 0, sizeof(g_dispatchmsg));
g_dispatchmsg.njobs = 2;
g_dispatchmsg.allocs = g_dispatch_allocs;
memset(&g_dispatch_req, 0, sizeof(g_dispatch_req));
g_dispatch_req.opcode = OPCode_jobdispatch;
g_dispatch_req.seq = 15;
g_dispatch_req.from = &g_req_from;
g_dispatch_req.body_which = Request_body_dispatchmsg;
g_dispatch_req.body.dispatchmsg = &g_dispatchmsg;
}
/* VERDICT PIN (Req 2.3): handle_jobdispatch (job.c:468-500, re-verified
* 2026-06-12) replies status=0 IMMEDIATELY — an ACK-of-receipt per the
* umbrella Reply-Ordering Contract (see section header) — and a full
* dispatch cycle (one successful + one failed allocation) appends NO WAL
* entries: allocation results return via notify_dispatch and job-state
* changes arrive later as worker facts. ACKs are withheld for the whole
* test, so a regression that adds a barrier wait trips the latency bound
* and any WAL append from dispatch processing trips the unchanged-LSN
* assert (an unclassified type would abort in wal_classify first). */
static void test_jobdispatch_receipt_ack_no_wal_append(void)
{
cbrp_reply_obs_t obs = { 0 };
uint64_t lsn_before, lsn_after, t0, elapsed_ms;
int rc;
cbrp_setup(3000);
cbrp_arrange_jobdispatch();
cbrp_notify_capture_reset(); /* drop any arrange-time noise */
pthread_mutex_lock(&g_hc.persist.lock);
lsn_before = g_hc.persist.current_lsn;
pthread_mutex_unlock(&g_hc.persist.lock);
/* Act: synchronous — the receipt ACK must never block on commit */
t0 = cbrp_mono_ms();
rc = handle_jobdispatch(&g_hc, &g_req_ep, &g_dispatch_req);
elapsed_ms = cbrp_mono_ms() - t0;
pthread_mutex_lock(&g_hc.persist.lock);
lsn_after = g_hc.persist.current_lsn;
pthread_mutex_unlock(&g_hc.persist.lock);
cbrp_scan_replies(&g_req_ep, &obs);
TEST_ASSERT_EQUAL_INT_MESSAGE(0, rc, "handle_jobdispatch rc");
TEST_ASSERT_TRUE_MESSAGE(elapsed_ms < 1000,
"receipt ACK must be latency-bounded — no commit barrier wait "
"(Req 2.3: the dispatch reply confirms receipt only)");
TEST_ASSERT_EQUAL_INT_MESSAGE(1, obs.n_replies,
"scheduler must receive exactly the one receipt ACK");
TEST_ASSERT_EQUAL_INT_MESSAGE(0, obs.last_status,
"the receipt ACK reports acceptance of the message (status 0)");
/* THE classification pin: dispatch processing appends no WAL entries,
* so there is nothing the receipt ACK could have falsely confirmed */
TEST_ASSERT_EQUAL_UINT64_MESSAGE(lsn_before, lsn_after,
"a dispatch cycle must append NO WAL entries (Req 2.3 — any "
"future append from dispatch processing must move behind the "
"barrier or be re-classified; the wal_classify XCE_TESTING "
"guard backstops unclassified types)");
/* notify_dispatch outcomes unaffected: one ok + one fail, in order */
TEST_ASSERT_EQUAL_INT_MESSAGE(2, g_notify_count,
"both allocations must produce their per-job outcome notification");
TEST_ASSERT_EQUAL_INT(NotifyData_data_jobDispatchFail,
g_notify_events[0]);
TEST_ASSERT_EQUAL_INT(NotifyData_data_jobDispatchFail,
g_notify_events[1]);
TEST_ASSERT_EQUAL_UINT64(CBRP_DISP_JOBID, g_notify_jobids[0]);
TEST_ASSERT_EQUAL_INT_MESSAGE(0, g_notify_codes[0],
"allocs[0] dispatch to the live worker must succeed (code 0)");
TEST_ASSERT_EQUAL_UINT64(CBRP_DISP_JOBID, g_notify_jobids[1]);
TEST_ASSERT_EQUAL_INT_MESSAGE(-EINVAL, g_notify_codes[1],
"allocs[1] (nhosts == 0) must fail with -EINVAL");
/* Ordering: the receipt ACK was already enqueued when the FIRST
* dispatch outcome fired — reply precedes processing (ACK-of-receipt,
* not ACK-of-outcome) */
TEST_ASSERT_TRUE_MESSAGE(g_notify_reply_already_enqueued[0],
"the receipt ACK must be enqueued before any dispatch outcome "
"notification (reply-before-processing is the verdict)");
/* drain the startjob request enqueued on the worker endpoint */
{
cbrp_reply_obs_t wdrain = { 0 };
cbrp_scan_replies(&g_wkr_disp_ep, &wdrain);
}
cbrp_teardown();
printf("test_jobdispatch_receipt_ack_no_wal_append: PASS\n");
}
/* ── do_set_preason / do_clr_preason fixtures ────────────────────────── */
static xce_pendreason_t g_pendreason;
static xce_pendreason_t *g_pendreasons[1];
static xce_preason_set_t g_preason_set;
static xce_request_t g_preason_req;
static uint64_t g_clr_jobs[1];
static xce_clear_reason_t g_clrreason;
static xce_request_t g_clrpreason_req;
/* set_preason MOVEs the inner xce_job_preason_t into the job (job.c
* MOVE_PTR(job->pend_reasons, ...)) and the job/do_clr_preason frees it
* later — so it must be heap-allocated; the carrier structs stay static. */
static void cbrp_arrange_set_preason(uint64_t jobid)
{
xce_job_preason_t *jpr = calloc(1, sizeof(*jpr));
TEST_ASSERT_NOT_NULL(jpr);
jpr->main_reason = 7; /* arbitrary scheduler pend reason */
memset(&g_pendreason, 0, sizeof(g_pendreason));
g_pendreason.jobid = jobid;
g_pendreason.reasons = jpr;
g_pendreasons[0] = &g_pendreason;
memset(&g_preason_set, 0, sizeof(g_preason_set));
g_preason_set.nreasons = 1;
g_preason_set.reasons = g_pendreasons;
memset(&g_preason_req, 0, sizeof(g_preason_req));
g_preason_req.opcode = OPCode_setpreason;
g_preason_req.seq = 16;
g_preason_req.from = &g_req_from;
g_preason_req.body_which = Request_body_preasonmsg;
g_preason_req.body.preasonmsg = &g_preason_set;
}
static void cbrp_arrange_clr_preason(uint64_t jobid)
{
g_clr_jobs[0] = jobid;
memset(&g_clrreason, 0, sizeof(g_clrreason));
g_clrreason.njobs = 1;
g_clrreason.jobs = g_clr_jobs;
memset(&g_clrpreason_req, 0, sizeof(g_clrpreason_req));
g_clrpreason_req.opcode = OPCode_clrpreason;
g_clrpreason_req.seq = 17;
g_clrpreason_req.from = &g_req_from;
g_clrpreason_req.body_which = Request_body_clrpreasonmsg;
g_clrpreason_req.body.clrpreasonmsg = &g_clrreason;
}
/* Shared receipt-style fact-handler driver: with ACKs withheld the
* handler must (a) reply status 0 latency-bounded — receipt only, no
* barrier wait — (b) append exactly expect_appends fact entries that
* remain PENDING (lsn > committed_lsn: the reply confirmed nothing about
* commitment), and (c) once a covering ACK arrives the retained suffix
* commits with no redelivery (the RETAIN contract observable per spec
* Implementation Notes 1.1: registration-free, pending purely by
* lsn > committed_lsn, ACK-driven advance). */
static void cbrp_drive_receipt_fact(cbrp_op_fn_t fn, xce_request_t *req,
uint64_t expect_appends)
{
cbrp_reply_obs_t obs = { 0 };
uint64_t lsn_before, lsn_after, watermark, t0, elapsed_ms;
uint64_t deadline;
int rc;
pthread_mutex_lock(&g_hc.persist.lock);
lsn_before = g_hc.persist.current_lsn;
pthread_mutex_unlock(&g_hc.persist.lock);
/* Act: synchronous — receipt-style handlers must never block */
t0 = cbrp_mono_ms();
rc = fn(&g_hc, &g_req_ep, req);
elapsed_ms = cbrp_mono_ms() - t0;
pthread_mutex_lock(&g_hc.persist.lock);
lsn_after = g_hc.persist.current_lsn;
pthread_mutex_unlock(&g_hc.persist.lock);
watermark = lsn_after - 1; /* last appended entry */
cbrp_scan_replies(&g_req_ep, &obs);
TEST_ASSERT_EQUAL_INT_MESSAGE(0, rc, "fact handler rc");
TEST_ASSERT_TRUE_MESSAGE(elapsed_ms < 1000,
"receipt-style reply must be latency-bounded — no commit barrier "
"wait with ACKs withheld (facts have no commit timeout, Req 2.3)");
TEST_ASSERT_EQUAL_INT_MESSAGE(1, obs.n_replies,
"the reporter must receive exactly one receipt reply");
TEST_ASSERT_EQUAL_INT_MESSAGE(0, obs.last_status,
"the receipt reply reports acceptance (status 0)");
/* the fact appends happened ... */
TEST_ASSERT_EQUAL_UINT64_MESSAGE(lsn_before + expect_appends, lsn_after,
"the handler must append exactly its fact entries");
/* ... and are RETAIN-pending: the receipt reply coexists with the
* uncommitted suffix, proving it confirmed receipt, not commitment */
TEST_ASSERT_TRUE_MESSAGE(
atomic_load(&g_hc.persist.committed_lsn) < watermark,
"fact entries must remain pending (lsn > committed_lsn) — the "
"receipt reply must not imply commitment (Req 2.3)");
TEST_ASSERT_TRUE_MESSAGE(obs.committed_at_obs < watermark,
"the receipt reply was observable while the fact entries were "
"still uncommitted — receipt-only semantics pinned");
/* RETAIN completion: a covering ACK (self + 1 standby = majority of
* n_peers=3) advances committed_lsn over the retained suffix with no
* redelivery from the reporter */
repl_on_ack(&g_hc.persist.repl, &g_hep_a, watermark);
deadline = cbrp_mono_ms() + 2000;
while (atomic_load(&g_hc.persist.committed_lsn) < watermark
&& cbrp_mono_ms() < deadline)
cbrp_sleep_ms(5);
TEST_ASSERT_TRUE_MESSAGE(
atomic_load(&g_hc.persist.committed_lsn) >= watermark,
"a covering ACK must commit the retained fact entries "
"(RETAIN registration contract)");
}
/* VERDICT PIN (Req 2.3): do_set_preason (job.c:1062) replies status=0
* receipt-style BEFORE applying the scheduler-reported pend reasons; the
* subsequent WAL_JOB_PREASON fact append (HOOK_DETAIL_SETPREASON →
* persist_job_hook_fun, RETAIN per wal_classify) stays pending until
* ACK-covered. Umbrella Reply-Ordering Contract: receipt-only ACK for a
* fact-shaped delivery (see section header). */
static void test_set_preason_receipt_reply_fact_retained(void)
{
cbrp_setup(3000);
cbrp_arrange_jobctrl(70, 1); /* job 70 exists; jobctrl req unused */
cbrp_arrange_set_preason(70);
cbrp_drive_receipt_fact(do_set_preason, &g_preason_req, 1);
cbrp_teardown();
printf("test_set_preason_receipt_reply_fact_retained: PASS\n");
}
/* VERDICT PIN (Req 2.3): do_clr_preason (job.c:1090) — same receipt-style
* verdict as do_set_preason; the clear is also a scheduler-origin
* WAL_JOB_PREASON fact (HOOK_DETAIL_CLRPREASON, RETAIN). */
static void test_clr_preason_receipt_reply_fact_retained(void)
{
cbrp_reply_obs_t drain = { 0 };
cbrp_setup(3000);
cbrp_arrange_jobctrl(71, 1);
/* seed pend reasons so the clear exercises the real erase path */
cbrp_arrange_set_preason(71);
TEST_ASSERT_EQUAL_INT(0, do_set_preason(&g_hc, &g_req_ep,
&g_preason_req));
cbrp_scan_replies(&g_req_ep, &drain); /* drop the seeding reply */
cbrp_arrange_clr_preason(71);
cbrp_drive_receipt_fact(do_clr_preason, &g_clrpreason_req, 1);
cbrp_teardown();
printf("test_clr_preason_receipt_reply_fact_retained: PASS\n");
}
/* ── do_update_op rusage path fixture ────────────────────────────────── */
/* KNOWN PRE-EXISTING MISMATCH (discovered while pinning, reported in the
* task evidence — NOT fixed here, production is out of boundary):
* update_job_rusages fires the AFTER_EVENT HOOK_DETAIL_JOB_RUSAGE_UPDATE
* hook with (cluster_t*, xce_job_rusages_t*) [job.c:1015-1016], but
* persist_job_hook_fun's default arm reads the second vararg as a job_t*
* [persist.c:1354-1359] and dereferences j->job.state at offset 56 —
* exactly sizeof(xce_job_rusages_t) — an out-of-bounds read on an
* exactly-sized allocation (the WAL_JOB_RUSAGE payload's state field is
* garbage). The padded box below keeps THIS pin's read in-bounds under
* ASAN without masking the report; the jobid field (offset 0 in both
* types) lines up by accident. */
static union {
xce_job_rusages_t r;
unsigned char pad[sizeof(xce_job_rusages_t) + 64];
} g_rusages_box;
static xce_update_data_t g_updatemsg;
static xce_request_t g_update_req;
static void cbrp_arrange_update_rusage(uint64_t jobid)
{
xce_worker_t wdef;
hostattrs_t *attrs = NULL;
worker_t *w = NULL;
/* reporting worker — get_ep_worker (stubbed) must return it */
attrs = calloc(1, sizeof(*attrs));
TEST_ASSERT_NOT_NULL(attrs);
attrs->hosttype = makeString("LINUX");
attrs->hostmodel = makeString("x86");
attrs->cpufactor = 1.0f;
attrs->maxcpus = 4;
memset(&wdef, 0, sizeof(wdef));
wdef.name = (char *)"wkr-rus";
wdef.attrs = attrs;
TEST_ASSERT_NOT_NULL(makeWorker(g_hc.workermgr, &wdef));
lock(g_hc.workermgr, RTTI_LOCK_READ);
key_find(g_hc.workermgr, (void *)"wkr-rus", (void **)&w);
unlock(g_hc.workermgr);
TEST_ASSERT_NOT_NULL(w);
g_stub_ep_worker = w;
memset(&g_rusages_box, 0, sizeof(g_rusages_box));
g_rusages_box.r.jobid = jobid; /* count/npids/npgids 0 — stubs no-op */
memset(&g_updatemsg, 0, sizeof(g_updatemsg));
g_updatemsg.table = Update_data_jobrusages;
g_updatemsg.data.jobrusages = &g_rusages_box.r;
memset(&g_update_req, 0, sizeof(g_update_req));
g_update_req.opcode = OPCode_update;
g_update_req.seq = 18;
g_update_req.from = &g_req_from;
g_update_req.body_which = Request_body_updatemsg;
g_update_req.body.updatemsg = &g_updatemsg;
}
/* VERDICT PIN (Req 2.3): the do_update_op rusage path (opupd.c:69 →
* do_update_jobrusage → update_job_rusages) replies receipt-style — the
* reply carries the LOCAL application result, never a commit barrier
* result — and its two fact appends (HOOK_DETAIL_JOB_UPDATE →
* WAL_JOB_UPDATE, HOOK_DETAIL_JOB_RUSAGE_UPDATE → WAL_JOB_RUSAGE, both
* RETAIN per wal_classify) stay pending until ACK-covered. Umbrella
* Reply-Ordering Contract: receipt-only ACK for fact-shaped delivery. */
static void test_update_op_rusage_receipt_reply_facts_retained(void)
{
cbrp_setup(3000);
cbrp_arrange_jobctrl(72, 1); /* job 72 exists; jobctrl req unused */
cbrp_arrange_update_rusage(72);
cbrp_drive_receipt_fact(do_update_op, &g_update_req, 2);
g_stub_ep_worker = NULL;
cbrp_teardown();
printf("test_update_op_rusage_receipt_reply_facts_retained: PASS\n");
}
/* ── Test group entry point ──────────────────────────────────────────── */
void test_commit_barrier_reply(void)
@ -796,5 +1272,10 @@ void test_commit_barrier_reply(void)
RUN_TEST(test_worker_join_withheld_acks_replies_error);
RUN_TEST(test_worker_join_success_reply_only_after_commit);
RUN_TEST(test_worker_join_no_hostconfig_error_reply_immediate);
/* Receipt-ACK verdict pins (task 3.3, Req 2.3) — green on landing */
RUN_TEST(test_jobdispatch_receipt_ack_no_wal_append);
RUN_TEST(test_set_preason_receipt_reply_fact_retained);
RUN_TEST(test_clr_preason_receipt_reply_fact_retained);
RUN_TEST(test_update_op_rusage_receipt_reply_facts_retained);
UNITY_END();
}