Rongsong Shen
d2830ce514
With the dispatch flags flipped ON in-test, prove the three receiver-side liveness properties (production defaults stay OFF): - P1: while a snapshot (and config-push) transfer is parked in flight on the slow lane, another endpoint's peer-control message is still processed promptly on the vtask pool (different thread), with the transfer still parked — the offloaded transfer does not block the drive path. - P2: a peer-control ack (classified VTASK_LIVENESS) runs promptly even while the pool is saturated to the LivenessAdmission reservation boundary with REQ_BLOCK tasks (one more REQ_BLOCK fast-rejects with -E_XCE_NOT_READY, proving real saturation). Narrowed to the liveness-dispatch-under-saturation assertion; commit-advance itself is covered by the commit-engine tests. - P3: while one endpoint's peer-control body is parked (holding a worker + that ep busy), another endpoint's body runs concurrently on a different worker — per-endpoint FIFO does not serialize across endpoints. All deterministic (cond-var gates, bounded polls). Fixed a flaky teardown-race hang (bug-1224): the tests released a parked vtask body then immediately called the cancel-based vtaskmgr_fini while the just-released body was still unwinding (P2's REQ_BLOCK bodies racing blk_lock teardown the worst). Fix adds end-of-body completion counters polled to the full expected count before fini, so every pool body has fully returned (worker idle) before the cancel. slowlane_fini is graceful (join) so the lane side was already safe. Verified: 5/5 deterministic isolated runs; full controller suite EXIT=0; ASan-clean. Completes task 3.4 (3.4a UAF fix + 3.4b tests); the production flag-flip remains deferred to after the 4.1 partition soak + 4.2 regression sweep. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01S6fDCtXkkEgupu7rUah1y2
194 lines
5.2 KiB
Meson
194 lines
5.2 KiB
Meson
controller_src = [
|
|
'cluster.c',
|
|
'commit.c',
|
|
'config_repl.c',
|
|
'ctrlstatus.c',
|
|
'dataex.c',
|
|
'egress.c',
|
|
'ha.c',
|
|
'ha_convergence.c',
|
|
'job.c',
|
|
'join.c',
|
|
'main.c',
|
|
'misc.c',
|
|
'myapp.c',
|
|
'opget.c',
|
|
'opupd.c',
|
|
'queue.c',
|
|
'reply.c',
|
|
'resources.c',
|
|
'sched.c',
|
|
'startup_validation.c',
|
|
'task.c',
|
|
'worker.c',
|
|
'apiserver.c',
|
|
'myconf.c',
|
|
'persist.c',
|
|
'repl.c',
|
|
'ctrl_metrics.c',
|
|
'slowlane.c',
|
|
]
|
|
|
|
incdir = include_directories('.', '../include', '../lib',
|
|
'include')
|
|
|
|
# cc = meson.get_compiler('c')
|
|
# math_dep = cc.find_library('m', required : false)
|
|
|
|
zlib_dep = dependency('zlib')
|
|
|
|
controller_deps = [
|
|
libxce_dep,
|
|
librtti_dep,
|
|
c_capnproto_dep,
|
|
math_dep,
|
|
tinylog_dep,
|
|
thread_dep,
|
|
zlib_dep,
|
|
]
|
|
|
|
controller = executable('xce_controller',
|
|
controller_src,
|
|
include_directories: incdir,
|
|
dependencies: controller_deps,
|
|
link_args: wrap_link_args,
|
|
install: true)
|
|
|
|
xce_test_src = [ 'testsuite/test.c', 'testsuite/waldump.c', 'testsuite/walcompare.c']
|
|
|
|
readline_dep = dependency('readline')
|
|
ncurses_dep = dependency('ncurses')
|
|
history_dep = dependency('history')
|
|
|
|
xce_test_deps = [
|
|
libxce_dep,
|
|
librtti_dep,
|
|
struct2json_dep,
|
|
readline_dep,
|
|
history_dep,
|
|
ncurses_dep,
|
|
tinylog_dep,
|
|
zlib_dep, # waldump: crc32 WAL validation
|
|
c_capnproto_dep, # waldump: decode JOB_SUBMIT jobid
|
|
]
|
|
xce_test = executable('xce_test',
|
|
xce_test_src,
|
|
include_directories: [incdir],
|
|
dependencies: xce_test_deps,
|
|
install: true)
|
|
|
|
# Controller Unity test suite (persist types and future controller unit tests)
|
|
controller_unit_test_src = [
|
|
'testsuite/controller_test.c',
|
|
'testsuite/test_persist_types.c',
|
|
'testsuite/test_persist_wal.c',
|
|
'testsuite/test_persist_schema.c',
|
|
'testsuite/test_persist_checkpoint.c',
|
|
'testsuite/test_persist_recovery.c',
|
|
'testsuite/test_hooks.c',
|
|
'testsuite/test_persist_hooks.c',
|
|
'testsuite/test_gc_retention.c',
|
|
'testsuite/test_cluster_persist.c',
|
|
'testsuite/test_e2e_wal.c',
|
|
'testsuite/test_e2e_checkpoint.c',
|
|
'testsuite/test_e2e_hooks.c',
|
|
'testsuite/test_e2e_gc.c',
|
|
'testsuite/test_e2e_capnp.c',
|
|
'testsuite/test_ha_role.c',
|
|
'testsuite/test_ha_role_lifecycle.c',
|
|
'testsuite/test_ha_cluster.c',
|
|
'testsuite/test_ha_redirect.c',
|
|
'testsuite/test_join_redirect.c',
|
|
'testsuite/test_p1_integration.c',
|
|
'testsuite/test_repl_unit.c',
|
|
'testsuite/test_repl_apply.c',
|
|
'testsuite/test_persist_repl.c',
|
|
'testsuite/test_repl_catchup.c',
|
|
'testsuite/test_p2_integration.c',
|
|
'testsuite/test_p3_hardening.c',
|
|
'testsuite/test_p3_manual_failover.c',
|
|
'testsuite/test_ctrl_metrics.c',
|
|
'testsuite/test_config_repl.c',
|
|
'testsuite/test_worker_join.c',
|
|
'testsuite/test_ha_startup.c',
|
|
'testsuite/test_ha_election.c',
|
|
'testsuite/test_ha_bootstrap.c',
|
|
'testsuite/test_ha_bootstrap_support.c',
|
|
'testsuite/test_ha_durability.c',
|
|
'testsuite/test_repl_majority.c',
|
|
'testsuite/test_persist_truncate.c',
|
|
'testsuite/test_ha_ctrlhello.c',
|
|
'testsuite/test_ha_failover.c',
|
|
'testsuite/test_ha_vote_send.c',
|
|
'testsuite/test_ha_start_election_async.c',
|
|
'testsuite/test_ha_vote_gate.c',
|
|
'testsuite/test_ha_repl_push.c',
|
|
'testsuite/test_ha_connection_reuse.c',
|
|
'testsuite/test_ha_rdhup_integration.c',
|
|
'testsuite/test_ha_liveness.c',
|
|
'testsuite/test_ha_prevote.c',
|
|
'testsuite/test_ha_failover_prevote.c',
|
|
'testsuite/test_commit_engine.c',
|
|
'testsuite/test_commit_barrier_rollout.c',
|
|
'testsuite/test_commit_barrier_reply.c',
|
|
'testsuite/test_egress_filter.c',
|
|
'testsuite/test_demotion_convergence.c',
|
|
'testsuite/test_convergence_verification.c',
|
|
'testsuite/test_coldstart_lsn0.c',
|
|
'testsuite/test_commit_durability.c',
|
|
'testsuite/test_ctrlstatus.c',
|
|
'testsuite/test_ha_heartbeat_committed.c',
|
|
'testsuite/test_ha_vote_floor_heartbeat.c',
|
|
'testsuite/test_term_safety_adapter.c',
|
|
'testsuite/test_drive_async_config.c',
|
|
'testsuite/test_slowlane.c',
|
|
'testsuite/test_commit_admission_pool.c',
|
|
'testsuite/test_ha_vep_teardown.c',
|
|
'testsuite/test_ha_dispatch_integration.c',
|
|
'testsuite/test_waldump.c',
|
|
'testsuite/waldump.c',
|
|
'testsuite/test_walcompare.c',
|
|
'testsuite/walcompare.c',
|
|
'ctrlstatus.c',
|
|
'commit.c',
|
|
'job.c',
|
|
'egress.c',
|
|
'ha_convergence.c',
|
|
'queue.c',
|
|
'join.c',
|
|
'opupd.c',
|
|
'startup_validation.c',
|
|
'worker.c',
|
|
'persist.c',
|
|
'ha.c',
|
|
'repl.c',
|
|
'ctrl_metrics.c',
|
|
'config_repl.c',
|
|
'slowlane.c',
|
|
]
|
|
|
|
ssl_dep = dependency('openssl')
|
|
|
|
controller_unit_test_deps = [
|
|
libxce_dep,
|
|
librtti_dep,
|
|
unity_dep,
|
|
tinylog_dep,
|
|
thread_dep,
|
|
zlib_dep,
|
|
c_capnproto_dep,
|
|
ssl_dep,
|
|
]
|
|
|
|
controller_unit_test = executable('controller_unit_test',
|
|
controller_unit_test_src,
|
|
include_directories: [incdir],
|
|
dependencies: controller_unit_test_deps,
|
|
c_args: ['-DXCE_TESTING'],
|
|
install: false)
|
|
|
|
test('controller test', controller_unit_test,
|
|
suite: 'controller',
|
|
timeout: 300,
|
|
env: ['ASAN_OPTIONS=detect_leaks=0'])
|
|
|