Complete M7.9b upgrade barrier and durability qualification

Schema v8 binds authority to builds (ADR-0068): acquisition names the
host build and only retained, unretired builds may hold a lease; no
commit may name a retired build; upgrade_barrier retires a build and
fences every holder in one transaction, while build-less pre-v8 hosts
keep working until the first barrier. Tests cover a writer surviving a
failed and then a real online migration, old-writer fencing on every
path, whole-history recovery by the new build, and the M7 qualification
fixture (19.6 s SIGKILL-to-ready under the production lease, no lost
acknowledgements).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
dingo
2026-09-29 07:31:04 -04:00
co-authored by Claude Opus 5.5
parent 703f67834f
commit f59cca2c3b
24 changed files with 893 additions and 52 deletions
+20 -20
View File
@@ -178,7 +178,7 @@ void runtime_cannot_bypass_the_guard() {
// A SECURITY DEFINER function ignores a hostile caller search_path.
CHECK(db->query("SET search_path = pg_temp, public", {}, 5s));
CHECK(db->query("CREATE TEMP TABLE region_leases(x int)", {}, 5s));
auto lease = acquire_region_lease(*db, key, 20000ms, 5s);
auto lease = acquire_region_lease(*db, key, build, 20000ms, 5s);
CHECK(lease && lease->epoch == 1 && lease->frame == 7);
CHECK(release_region_lease(*db, key, *lease, 5s));
}
@@ -187,13 +187,13 @@ void acquire_renew_release_and_publish() {
auto admin = owner();
const auto key = provision(*admin, 20);
auto db = runtime();
CHECK(
failed(acquire_region_lease(*db, {1, 999}, 20000ms, 5s), LeaseStoreError::not_provisioned));
CHECK(failed(acquire_region_lease(*db, key, 999ms, 5s), LeaseStoreError::invalid));
CHECK(failed(acquire_region_lease(*db, key, 60001ms, 5s), LeaseStoreError::invalid));
auto lease = acquire_region_lease(*db, key, 20000ms, 5s);
CHECK(failed(acquire_region_lease(*db, {1, 999}, build, 20000ms, 5s),
LeaseStoreError::not_provisioned));
CHECK(failed(acquire_region_lease(*db, key, build, 999ms, 5s), LeaseStoreError::invalid));
CHECK(failed(acquire_region_lease(*db, key, build, 60001ms, 5s), LeaseStoreError::invalid));
auto lease = acquire_region_lease(*db, key, build, 20000ms, 5s);
CHECK(lease && lease->epoch == 1 && lease->duration == 20000ms && lease->holder != Uuid{});
CHECK(failed(acquire_region_lease(*db, key, 20000ms, 5s), LeaseStoreError::busy));
CHECK(failed(acquire_region_lease(*db, key, build, 20000ms, 5s), LeaseStoreError::busy));
auto renewed = renew_region_lease(*db, key, *lease, 20000ms, 5s);
CHECK(renewed && *renewed == 20000ms);
auto forged = *lease;
@@ -244,7 +244,7 @@ void acquire_renew_release_and_publish() {
CHECK(failed(release_region_lease(*db, key, *lease, 5s), LeaseStoreError::fenced));
CHECK(failed(renew_region_lease(*db, key, *lease, 20000ms, 5s), LeaseStoreError::fenced));
CHECK(failed(publish(*db, link(*head, *lease, 22, 65)), LeaseStoreError::fenced));
auto next = acquire_region_lease(*db, key, 20000ms, 5s);
auto next = acquire_region_lease(*db, key, build, 20000ms, 5s);
CHECK(next && next->epoch == 2 && next->holder != lease->holder);
auto final_head = publish(*db, link(*head, *next, 22, 65));
CHECK(final_head && final_head->head.sequence == 2);
@@ -258,16 +258,16 @@ void database_time_expiry_and_paused_writer() {
const LeasePolicy fast{1000ms, 200ms, 100ms, 100ms, 300ms};
LeaseAuthority a{fast};
auto sent = LeaseClock::now();
auto lease_a = acquire_region_lease(*worker_a, key, fast.duration, 5s);
auto lease_a = acquire_region_lease(*worker_a, key, build, fast.duration, 5s);
CHECK(lease_a && a.acquired(*lease_a, sent, LeaseClock::now()));
CHECK(failed(acquire_region_lease(*worker_b, key, 20000ms, 5s), LeaseStoreError::busy));
CHECK(failed(acquire_region_lease(*worker_b, key, build, 20000ms, 5s), LeaseStoreError::busy));
const auto genesis = committed(*worker_a, key);
std::this_thread::sleep_for(1200ms); // Worker A is paused past its lease.
CHECK(a.state(LeaseClock::now()) == LeaseState::fenced);
// Expiry is decided by database time; the successor acquires a newer epoch.
wait_until_expired(*admin, key);
auto lease_b = acquire_region_lease(*worker_b, key, 20000ms, 5s);
auto lease_b = acquire_region_lease(*worker_b, key, build, 20000ms, 5s);
CHECK(lease_b && lease_b->epoch == lease_a->epoch + 1);
auto head_b = publish(*worker_b, link(genesis, *lease_b, 31, 3));
CHECK(head_b);
@@ -282,7 +282,7 @@ void database_time_expiry_and_paused_writer() {
// Expired renewal cannot revive a lease even without a successor.
CHECK(release_region_lease(*worker_b, key, *lease_b, 5s));
auto lease_c = acquire_region_lease(*worker_a, key, 1000ms, 5s);
auto lease_c = acquire_region_lease(*worker_a, key, build, 1000ms, 5s);
CHECK(lease_c && lease_c->epoch == lease_b->epoch + 1);
wait_until_expired(*admin, key);
CHECK(
@@ -295,7 +295,7 @@ void queued_writer_uses_post_lock_database_time() {
auto admin = owner();
const auto key = provision(*admin, 40);
auto worker = runtime();
auto lease = acquire_region_lease(*worker, key, 1000ms, 5s);
auto lease = acquire_region_lease(*worker, key, build, 1000ms, 5s);
CHECK(lease);
const auto genesis = committed(*worker, key);
auto blocker = owner();
@@ -325,7 +325,7 @@ void partitioned_renewal_fences_locally() {
const LeasePolicy fast{1000ms, 200ms, 100ms, 100ms, 300ms};
LeaseAuthority authority{fast};
const auto sent = LeaseClock::now();
auto lease = acquire_region_lease(*worker, key, fast.duration, 5s);
auto lease = acquire_region_lease(*worker, key, build, fast.duration, 5s);
CHECK(lease && authority.acquired(*lease, sent, LeaseClock::now()));
auto blocker = owner();
const std::array<std::string, 1> region{"50"};
@@ -346,7 +346,7 @@ void partitioned_renewal_fences_locally() {
CHECK(blocker->query("ROLLBACK", {}, 5s));
// The orphaned renewal reached the row only after database expiry: rejected.
auto successor = runtime();
auto next = acquire_region_lease(*successor, key, 20000ms, 5s);
auto next = acquire_region_lease(*successor, key, build, 20000ms, 5s);
CHECK(next && next->epoch == lease->epoch + 1);
}
@@ -365,7 +365,7 @@ void contenders_serialize_on_the_database() {
for (std::size_t i = 0; i < 2; ++i)
threads.emplace_back([&, i] {
start.arrive_and_wait();
results[i] = acquire_region_lease(*workers[i], key, 20000ms, 5s);
results[i] = acquire_region_lease(*workers[i], key, build, 20000ms, 5s);
});
for (auto& t : threads)
t.join();
@@ -380,7 +380,7 @@ void contenders_serialize_on_the_database() {
}
// The same holder racing two commits from the same predecessor: exactly one wins.
auto lease = acquire_region_lease(*workers[0], key, 20000ms, 5s);
auto lease = acquire_region_lease(*workers[0], key, build, 20000ms, 5s);
CHECK(lease);
auto head = committed(*workers[0], key);
for (std::uint8_t round = 0; round < 32; ++round) {
@@ -413,9 +413,9 @@ void exhaustion_fails_closed() {
"WHERE world_id = 1 AND region_id = 70",
{}, 5s));
auto db = runtime();
CHECK(failed(acquire_region_lease(*db, key, 20000ms, 5s), LeaseStoreError::exhausted));
CHECK(failed(acquire_region_lease(*db, key, build, 20000ms, 5s), LeaseStoreError::exhausted));
const auto other = provision(*admin, 71);
auto lease = acquire_region_lease(*db, other, 20000ms, 5s);
auto lease = acquire_region_lease(*db, other, build, 20000ms, 5s);
CHECK(lease);
// Owner-only fixture: a chain link at the last sequence (the head FK requires it).
CHECK(admin->query(
@@ -493,7 +493,7 @@ void measure_round_trips() {
for (int i = 0; i < n; ++i) {
std::expected<LeaseGrant, LeaseStoreFailure> lease = std::unexpected{LeaseStoreFailure{}};
acquire.samples.push_back(
timed([&] { lease = acquire_region_lease(*db, key, 20000ms, 5s); }));
timed([&] { lease = acquire_region_lease(*db, key, build, 20000ms, 5s); }));
CHECK(lease);
renew.samples.push_back(
timed([&] { CHECK(renew_region_lease(*db, key, *lease, 20000ms, 5s)); }));