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

feat(job-array-single-wal-record): make apply pump respect apply failures

Browse source 
persist_apply_pump_run() no longer discards apply_committed_entry()'s
return value. On a negative rc for any WAL type (not just the new
array type), the walk halts at that LSN — no last_applied_lsn advance,
no pending-apply hand-off — logs a loud error, and retries from the
same position on the next kick, mirroring the existing
apply_pump_read_entry failure branch's shape.

Investigated whether this newly turns the pre-existing job-fact
-ENOENT path into a permanent-wedge hazard: it does not, since
c->jobmgr never deletes entries and facts are only ever applied after
their causally-prior submit already succeeded, so a live -ENOENT there
can only mean genuine divergence — halting is the correct behavior.

Task 4.1 of job-array-single-wal-record (Requirement 9.4).
This commit is contained in:
Rongsong Shen 2026-07-15 03:24:28 +00:00
parent 107e3839d9
commit cc7e99c2f7
3 changed files with 236 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

197
src/controller/testsuite/test_apply_pump.c
View file

@ -571,6 +571,202 @@ static void test_apply_pump_run_applies_mixed_submit_and_fact_entries(void)
"PASS\n");
}
/* ── 2b. Task 4.1 (job-array-single-wal-record, design.md "Live Apply
* Resource Fence"): the walk must respect a negative apply outcome ─────── */
/* Encodes a (base_jobid, array_size, spec) JobSubmit payload -- the exact
* WAL_JOB_ARRAY_SUBMIT payload shape, mirroring test_job_array_apply.c's
* taj_encode_job_submit. Caller frees *out. */
static int tap_encode_job_submit(uint64_t base_jobid, uint64_t array_size,
job_submit_data_t* spec, uint8_t** out,
size_t* out_len)
{
struct capn c;
struct capn_segment* cs;
struct JobSubmit cjs;
JobSubmit_ptr jsp;
xce_job_submit_t s;
memset(&s, 0, sizeof(s));
s.jobid = base_jobid;
s.array_size = array_size;
s.submit = spec;
capn_init_malloc(&c);
cs = capn_root(&c).seg;
encode_JobSubmit(cs, &cjs, &s);
jsp = new_JobSubmit(cs);
write_JobSubmit(&cjs, jsp);
capn_setp(capn_root(&c), 0, jsp.p);
*out_len = capn_size(&c);
*out = malloc(*out_len);
if (!*out) {
capn_free(&c);
return -ENOMEM;
}
capn_write_mem(&c, *out, *out_len, 0);
capn_free(&c);
return 0;
}
/* Before this fix, persist_apply_pump_run() discarded
* apply_committed_entry()'s return value entirely
* ((void)apply_committed_entry(...)) and unconditionally advanced
* last_applied_lsn -- silently, permanently losing any apply failure
* (design.md "Live Apply Resource Fence", Req 9.4). This test forces a REAL
* negative return through the REAL WAL_JOB_ARRAY_SUBMIT dispatch path
* (task 3.1's scratch-build-phase fault-injection seam), rather than
* mocking apply_committed_entry() itself, and proves the walk now:
* (a) returns negative -- not silent 0/success;
* (b) does not advance last_applied_lsn past the failed position;
* (c) genuinely halts -- a LATER, already-committed entry in the same
* batch is NOT applied on this pass, proving this is a stop, not a
* skip-and-continue;
* (d) reaches the loud, operator-visible ERROR log branch: this is the
* ONLY source of a negative return from persist_apply_pump_run()'s
* WAL_JOB_ARRAY_SUBMIT dispatch in this scenario, and the ERROR()
* call is unconditionally on that exact return path (see persist.c) --
* confirmed structurally rather than by parsing log output, per this
* suite's convention (no log-capture mechanism exists in this
* fixture).
* A subsequent retry, with the fault cleared, then proves the walk resumes
* from the SAME stuck position (not a saved-forward offset) and completes
* both entries once unstuck -- mirroring the "entry stays committed and
* will be retried, from the same position, on the next kick" contract the
* pre-existing apply_pump_read_entry failure branch already established
* immediately above this one in the same function. */
static void test_apply_pump_run_halts_at_failed_lsn_without_advancing(void)
{
tap_setup();
#ifdef XCE_TESTING
job_array_apply_test_clear_force_fail();
#endif
const uint64_t base_jobid = 93000;
const uint64_t array_size = 3;
job_submit_data_t spec;
memset(&spec, 0, sizeof(spec));
spec.queue = (char*)"q";
spec.user = (char*)"tester";
spec.mintasks = 1;
spec.maxtasks = 1;
spec.job_name = (char*)"array-fail-test";
uint8_t* array_payload = NULL;
size_t array_len = 0;
int enc_rc = tap_encode_job_submit(base_jobid, array_size, &spec,
&array_payload, &array_len);
/* Fail at scratch-build index 1 (of 3) -- set BEFORE either entry below
* is appended, so no background fsync-driven kick (see file header) can
* ever observe an unfailed attempt at this LSN: the fault is
* deterministic and sticky until cleared, so every caller that reaches
* this LSN -- this test's own call below, or a racing background one --
* gets the identical negative rc without advancing anything. */
#ifdef XCE_TESTING
job_array_apply_test_set_force_fail_at(1);
#endif
int rc_array = persist_wal_async(&g_tap_c.persist, WAL_JOB_ARRAY_SUBMIT,
array_payload, (uint32_t)array_len);
free(array_payload);
uint64_t array_lsn = g_tap_c.persist.current_lsn - 1;
/* A second, later entry -- an ordinary single-job submit -- committed in
* the SAME batch as the array entry above. If the walk merely skipped
* the failed array record instead of halting at it, this job would end
* up materialized; a genuine halt must leave it untouched. */
memset(&g_tap_seed_submit, 0, sizeof(g_tap_seed_submit));
g_tap_seed_submit.queue = (char*)"q";
g_tap_seed_submit.user = (char*)"tester";
xce_job_t jdef;
memset(&jdef, 0, sizeof(jdef));
jdef.jobid = 94000;
jdef.state = JOB_STAT_PEND;
jdef.submit = &g_tap_seed_submit;
uint8_t* later_payload = NULL;
size_t later_len = 0;
int enc_rc2 = tap_encode_job(&jdef, &later_payload, &later_len);
int rc_later = persist_wal_async(&g_tap_c.persist, WAL_JOB_SUBMIT,
later_payload, (uint32_t)later_len);
free(later_payload);
uint64_t later_lsn = g_tap_c.persist.current_lsn - 1;
uint64_t baseline_applied = persist_last_applied_lsn(&g_tap_c.persist);
/* White-box: mark both entries committed directly (this test targets
* the walk's own return-value handling, not commit-advance itself --
* that is test 1's job). */
atomic_store(&g_tap_c.persist.committed_lsn, later_lsn);
int walk_rc = persist_apply_pump_run(&g_tap_c.persist);
uint64_t last_applied_after_failure =
persist_last_applied_lsn(&g_tap_c.persist);
job_t* array_job0_after_failure = tap_find_job(base_jobid + 0);
job_t* later_job_after_failure = tap_find_job(94000);
/* Clear the fault and retry: the walk must resume from the SAME stuck
* LSN (not have skipped it) and, this time, apply both entries. */
#ifdef XCE_TESTING
job_array_apply_test_clear_force_fail();
#endif
int walk_rc_retry = persist_apply_pump_run(&g_tap_c.persist);
uint64_t last_applied_after_retry =
persist_last_applied_lsn(&g_tap_c.persist);
job_t* array_job0_after_retry = tap_find_job(base_jobid + 0);
job_t* array_job1_after_retry = tap_find_job(base_jobid + 1);
job_t* array_job2_after_retry = tap_find_job(base_jobid + 2);
job_t* later_job_after_retry = tap_find_job(94000);
tap_teardown();
TEST_ASSERT_EQUAL_INT(0, enc_rc);
TEST_ASSERT_EQUAL_INT(0, rc_array);
TEST_ASSERT_EQUAL_INT(0, enc_rc2);
TEST_ASSERT_EQUAL_INT(0, rc_later);
TEST_ASSERT_EQUAL_UINT64(array_lsn + 1, later_lsn);
TEST_ASSERT_TRUE_MESSAGE(walk_rc < 0,
"the walk must return a negative value -- not silent 0/success -- "
"when apply_committed_entry fails");
TEST_ASSERT_EQUAL_UINT64_MESSAGE(baseline_applied,
last_applied_after_failure,
"last_applied_lsn must NOT advance past the failed position");
TEST_ASSERT_NULL_MESSAGE(array_job0_after_failure,
"no element of the failed array attempt may be visible -- "
"restore_job_array's own scratch-build atomicity plus this walk's "
"halt must together leave nothing materialized");
TEST_ASSERT_NULL_MESSAGE(later_job_after_failure,
"REGRESSION GUARD: the later, already-committed entry must NOT be "
"applied on this same pass -- the walk genuinely halted at the "
"failed position, it did not skip past it and continue");
TEST_ASSERT_TRUE_MESSAGE(walk_rc_retry >= 0,
"once the fault clears, the retry from the SAME stuck position "
"must succeed");
TEST_ASSERT_EQUAL_UINT64_MESSAGE(later_lsn, last_applied_after_retry,
"the retry must resume from the same stuck LSN and reach the "
"watermark -- proving the earlier failure did not skip the entry");
TEST_ASSERT_NOT_NULL_MESSAGE(array_job0_after_retry,
"array element 0 must exist once the walk is unstuck");
TEST_ASSERT_NOT_NULL_MESSAGE(array_job1_after_retry,
"array element 1 (the previously-forced index) must exist once the "
"walk is unstuck");
TEST_ASSERT_NOT_NULL_MESSAGE(array_job2_after_retry,
"array element 2 must exist once the walk is unstuck");
TEST_ASSERT_NOT_NULL_MESSAGE(later_job_after_retry,
"the later entry must apply too, once the walk is unstuck");
printf("test_apply_pump_run_halts_at_failed_lsn_without_advancing: "
"PASS\n");
}
/* ── 3. Hazard 1 guard precision: job_ctrl's own live append must survive ── */
static void test_apply_pump_guard_does_not_break_job_ctrl_live_append(void)
@ -1295,6 +1491,7 @@ void test_apply_pump(void)
UNITY_BEGIN();
RUN_TEST(test_apply_pump_kick_applies_committed_burst_in_ascending_lsn_order);
RUN_TEST(test_apply_pump_run_applies_mixed_submit_and_fact_entries);
RUN_TEST(test_apply_pump_run_halts_at_failed_lsn_without_advancing);
RUN_TEST(test_apply_pump_guard_does_not_break_job_ctrl_live_append);
RUN_TEST(test_apply_pump_fail_racing_finish_merges_against_current_state);
RUN_TEST(test_apply_pump_late_pending_apply_registration_self_heals);