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

feat(ha-commit-durability): gate standby ACK on fdatasync success + persist-before-ACK regression test (task 2.3)

Browse source
This commit is contained in:
Rongsong Shen 2026-06-18 06:45:21 +00:00
parent c41edc515e
commit e4c4968331
4 changed files with 155 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

31
src/controller/persist.c
View file

@ -730,8 +730,27 @@ int persist_wal_write_replicated(persist_t* p, uint64_t lsn, uint32_t type,
* persist_wal_async defers fsync to the background thread / persist_flush;
* here we sync inline because the entry feeds the primary's commit
* majority and must survive a standby restart. fdatasync is sufficient
* (entry bytes + segment metadata are pre-allocated by open_new_segment). */
fdatasync(p->wal_fd);
* (entry bytes + segment metadata are pre-allocated by open_new_segment).
*
* Fail-loud rc-gate (ha-commit-durability Req 1.3, symmetric with the
* append-path gate at task 2.1): the ACK is sent by the caller ONLY when
* this returns success, and the ACK claims the entry is durable. So if
* the fdatasync FAILS (EIO/ENOSPC, or the forced-fail test seam), we must
* NOT return success — we log loudly and return -EIO so the caller's
* existing error path (ha_apply_single_entry) does NOT apply or ACK. */
int fsrc = fdatasync(p->wal_fd);
#ifdef XCE_TESTING
atomic_fetch_add_explicit(&p->test_replicated_fdatasync_count, 1,
memory_order_relaxed);
#endif
if (fsrc != 0 || flusher_fsync_forced_fail(p)) {
int e = (fsrc != 0) ? errno : EIO;
ERROR("persist: persist_wal_write_replicated fdatasync FAILED for "
"lsn=%" PRIu64 " (errno=%d %s) — entry NOT durable; returning "
"error so the standby does NOT ACK", lsn, e, strerror(e));
pthread_mutex_unlock(&p->lock);
return -EIO;
}
/* Rotate segment when full (same threshold as the primary append). */
if (p->seg_offset >= WAL_SEGMENT_SIZE_BYTES) {
@ -799,6 +818,14 @@ void persist_test_set_force_fsync_fail(persist_t* p, int fail)
memory_order_release);
}
unsigned persist_test_replicated_fdatasync_count(persist_t* p)
{
if (!p)
return 0;
return atomic_load_explicit(&p->test_replicated_fdatasync_count,
memory_order_relaxed);
}
/* ------------------------------------------------------------------ *
* Durability-verification test seam (ha-commit-durability Req 3.2/3.3)*
* *