lei.chen/myxce
1
0
Fork 1
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

test(raft-adapter-conformance): WAL catch-up reject reply-construction regression lock

Browse source 
Adds test_5_1_wal_catchup_reject_sends_nack_reply, driving a genuine
(term,lsn) conflict against a real persisted WAL entry through
ha_apply_term_entry_via_library and asserting
ha_send_wal_ack_reply_ex(success=0) fires via ha_wal_ack_send_hook.

Note: test_config_repl.c's test_bug1479_ae_reject_sends_nack_not_silence
already covers the same call site via a different (forward-gap)
stimulus, added in the original bug-1479 commit. design.md's own File
Structure Plan explicitly calls for this new test in this file
regardless, so this is disclosed, design-sanctioned defense-in-depth,
not accidental duplication -- both tests independently confirmed to
fail together when the reply call is removed.

1065 -> 1066 tests, 0 failures.
This commit is contained in:
Rongsong Shen 2026-07-29 16:11:47 +00:00
parent 87ce7be917
commit cb668adc7a
3 changed files with 116 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

112
src/controller/testsuite/test_ha_core_safety.c
View file

@ -2766,6 +2766,113 @@ static void test_4_2_dormant_sender_stays_uncalled_in_production(void)
printf("test_4_2_dormant_sender_stays_uncalled_in_production: PASS\n");
}
/* ═══════════════════════════════════════════════════════════════════════════
* TASK 5.1 (raft-adapter-conformance) — regression-lock: a WAL catch-up
* rejection actually sends the NACK reply on the wire.
*
* bug-1479 fixed ha_apply_term_entry_via_library's logOk-reject branch (ha.c
* ~3315-3327) to call ha_send_wal_ack_reply_ex(ha, ep, c, e->lsn, success=0)
* instead of silently dropping the reject — before that fix NOTHING was sent
* on reject, so the primary's NACK-handling (ha_raft_on_repl_nack) was correct
* but unreachable dead code. Downstream tests (ha_raft_on_repl_nack's own
* suite, catch-up-triggering tests) already prove the EFFECTS of a NACK once
* one arrives; this test closes the reply-CONSTRUCTION-boundary gap itself —
* that the reject branch actually invokes ha_send_wal_ack_reply_ex(success=0)
* — asserted here via the ha_wal_ack_send_hook seam (ha.h, XCE_TESTING),
* mirroring test_config_repl.c's test_bug1479_ae_reject_sends_nack_not_silence
* but built from THIS file's own hcs4_* fixture family (Requirement 2.1's
* _Boundary:_ is this file) so a future change to the reject branch is caught
* here too, independent of test_config_repl.c.
*
* Fixture: a STANDBY follower with a real persisted LSN1@STORED_TERM tip. A
* term-carrying single-entry AppendEntries claims prev=(1, CLAIMED_PREV_TERM)
* — a genuine (term,lsn) mismatch against the real on-disk term at LSN1 — so
* logOk fails and ha_apply_term_entry_via_library takes the reject branch.
* Driven through the REAL production ingest seam, ha_apply_wal_catchup_entry
* (the exact function every incoming WAL replication message is routed to),
* the same seam task 6.1 already established in this file.
* ═══════════════════════════════════════════════════════════════════════════ */
static uint64_t g_hcs51_hook_term;
static uint64_t g_hcs51_hook_lsn;
static int g_hcs51_hook_success;
static int g_hcs51_hook_called;
static void hcs51_wal_ack_capture(uint64_t term, uint64_t lsn, int success)
{
g_hcs51_hook_called = 1;
g_hcs51_hook_term = term;
g_hcs51_hook_lsn = lsn;
g_hcs51_hook_success = success;
}
static void test_5_1_wal_catchup_reject_sends_nack_reply(void)
{
cluster_t* c = hcs4_cluster_up("wal_nack");
TEST_ASSERT_NOT_NULL(c);
enum { FOLLOWER_TERM = 4, STORED_TERM = 2, CLAIMED_PREV_TERM = 3 };
hcs4_make_follower(c, /*term*/FOLLOWER_TERM, /*n_peers*/3);
/* Real persisted tip: LSN1 @ STORED_TERM, via the wired standby persist
* callback (real fs required for inline fdatasync — bug-924). */
uint8_t full[HCS_FULL_LEN];
hcs_fill_body(full);
uint8_t blob[sizeof(raft_entry_blob_t) + HCS_FULL_LEN];
size_t n = hcs4_pack_entry(blob, WAL_JOB_SUBMIT, full, HCS_FULL_LEN);
TEST_ASSERT_EQUAL_INT_MESSAGE(0,
ha_cb_persist_entry_for_test(&c->ha, 1, STORED_TERM, blob, n),
"seed write must persist (real fs required — bug-924)");
c->ha.raft.log_len = 1;
/* A term-carrying entry at LSN2 claims prev=(1, CLAIMED_PREV_TERM) — a
* genuine (term,lsn) mismatch against the real LSN1@STORED_TERM on disk
* (CLAIMED_PREV_TERM != STORED_TERM), so logOk MUST reject it. */
uint8_t lpay[1] = { 'z' };
wal_catchup_entry_t sub;
memset(&sub, 0, sizeof(sub));
sub.lsn = 2;
sub.entry_type = WAL_JOB_UPDATE;
sub.term = FOLLOWER_TERM;
sub.prev_log_index = 1;
sub.prev_log_term = CLAIMED_PREV_TERM;
sub.raw_payload = lpay;
sub.raw_payload_len = 1;
wal_catchup_entry_t* sub_arr[1] = { &sub };
wal_catchup_entry_t top;
memset(&top, 0, sizeof(top));
top.n_entries = 1;
top.entries = sub_arr;
g_hcs51_hook_called = 0;
ha_wal_ack_send_hook = hcs51_wal_ack_capture;
int rc = ha_apply_wal_catchup_entry(&c->ha, &c->persist, &top,
/*ep*/NULL, c);
ha_wal_ack_send_hook = NULL; /* uninstall before any assertion can fail */
TEST_ASSERT_EQUAL_INT(0, rc); /* reject, not a hard error */
/* Nothing was accepted at LSN2: the rejected entry never landed. */
hcs_probe_t pr;
TEST_ASSERT_EQUAL_INT(0, hcs4_probe(c, 2, &pr));
TEST_ASSERT_FALSE_MESSAGE(pr.present,
"a rejected entry must never be persisted at its LSN");
TEST_ASSERT_TRUE_MESSAGE(g_hcs51_hook_called,
"a WAL catch-up rejection must send a WalAckReply NACK "
"(ha_send_wal_ack_reply_ex success=0), not silence it -- the "
"reply-construction boundary bug-1479 fixed");
TEST_ASSERT_EQUAL_INT_MESSAGE(0, g_hcs51_hook_success,
"the reply for a rejected WAL catch-up entry must carry success=0");
TEST_ASSERT_EQUAL_UINT64((uint64_t)FOLLOWER_TERM, g_hcs51_hook_term);
TEST_ASSERT_EQUAL_UINT64(2, g_hcs51_hook_lsn);
hcs4_cluster_down(c);
printf("test_5_1_wal_catchup_reject_sends_nack_reply: PASS\n");
}
/* ── Suite entry point ─────────────────────────────────────────────────────*/
void test_ha_core_safety(void)
@ -2871,4 +2978,9 @@ void test_ha_core_safety(void)
* production senders) end-to-end and confirm the dormant stub's counter
* never moves off zero, while proving each real sender actually fired. */
RUN_TEST(test_4_2_dormant_sender_stays_uncalled_in_production);
/* Task 5.1 (raft-adapter-conformance): regression-lock the bug-1479
* reply-construction boundary — a WAL catch-up rejection must actually
* invoke ha_send_wal_ack_reply_ex(success=0) via ha_wal_ack_send_hook,
* not silently drop the reject. */
RUN_TEST(test_5_1_wal_catchup_reject_sends_nack_reply);
}