forked from lei.chen/myxce
Rongsong Shen
1da26b043e
Adds an explicit case WAL_CONFIG_MARKER to apply_committed_entry, replacing its no-op treatment, that forces a checkpoint at exactly the marker's own (term, lsn) via two new helpers: persist_checkpoint_write_locked(p, checkpoint_lsn) -- the checkpoint core (pin lsn, scan config ref, write_snapshot, trim, rotate) taking an explicit LSN and never acquiring apply_pump_lock itself persist_checkpoint_marker_triggered(p, lsn) -- shares the existing checkpoint_in_progress CAS guard, calls the above with the marker's own lsn This fixes two hazards design.md's "call persist_checkpoint() directly" text didn't account for: (1) apply_committed_entry's live-pump caller (persist_apply_pump_run, used by both primary and standby online-apply) already holds apply_pump_lock across the dispatch call -- a direct persist_checkpoint() call would self-deadlock on that mutex; (2) last_applied_lsn/replay position only advance AFTER apply_committed_entry returns at both call sites, so pinning checkpoint_lsn from last_applied_lsn inside the marker case would label the checkpoint with the previous entry's LSN, not the marker's own -- fixed by threading the marker's own lsn parameter through explicitly. A -EBUSY outcome (a concurrent periodic checkpoint mid-flight) is logged at TRACE and treated as expected/self-resolving, never retried. The new case has no effect on entity interpretation/re-homing (Req 1.8). New test_upgrade_snapshot_apply.c drives WAL_CONFIG_MARKER through the REAL production call paths (persist_apply_pump_run and boot replay via persist_recover), not a bare apply_committed_entry() call, so the fix is actually proven against the lock-holding context rather than assumed. Also fixes a genuine regression in test_config_repl.c surfaced by WAL_CONFIG_MARKER apply having a real side effect for the first time (bug-1466): an fsync-worker-thread race (t42_wait_applied polling helper, mirrors test_apply_pump.c's tap_wait_applied) and one test call site trusting an unreliable raft-derived LSN. Surfaces (but does not fix, out of this spec's boundary) a pre-existing ha-term-safety/raft-log-replication gap: persist_write_checkpoint_marker bypasses ha_primary_log_append, breaking its documented current_lsn==log_len+1 invariant once a checkpoint interleaves with primary appends -- log_len feeds real RequestVote freshness comparisons, not advisory-only as first assumed; severity corrected in bug-1466. Task 5 of 19. Requirements: 1.1, 1.5, 1.8, 4.4, 5.2, 5.3
274 lines
8.8 KiB
Meson
274 lines
8.8 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', 'testsuite/snapverify.c', 'testsuite/snapdiff.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_elect_ctx_lifecycle.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_commit_resolve.c',
|
|
'testsuite/test_ha_vep_teardown.c',
|
|
'testsuite/test_ha_dispatch_integration.c',
|
|
'testsuite/test_ha_core_safety.c',
|
|
'testsuite/test_ha_partition.c',
|
|
'testsuite/test_waldump.c',
|
|
'testsuite/waldump.c',
|
|
'testsuite/test_walcompare.c',
|
|
'testsuite/walcompare.c',
|
|
'testsuite/test_snapverify.c',
|
|
'testsuite/snapverify.c',
|
|
'testsuite/test_snapdiff.c',
|
|
'testsuite/snapdiff.c',
|
|
'testsuite/test_persist_snapshot_entities.c',
|
|
'testsuite/test_apply_seam.c',
|
|
'testsuite/test_apply_committed_entry.c',
|
|
'testsuite/test_replay_apply_seam.c',
|
|
'testsuite/test_apply_reapply_idempotency.c',
|
|
'testsuite/test_apply_correctness_verification.c',
|
|
'testsuite/test_apply_pump.c',
|
|
'testsuite/test_apply_pump_integration.c',
|
|
'testsuite/test_job_array_apply.c',
|
|
'testsuite/test_job_array_fence.c',
|
|
'testsuite/test_job_array_replay_fence.c',
|
|
'testsuite/test_upgrade_snapshot_restore.c',
|
|
'testsuite/test_upgrade_snapshot_apply.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'])
|
|
|
|
# job-array-single-wal-record task 5.1: sched.c's push logic (sched_job_new_fun /
|
|
# xcesched_push_jobarray) is exercised by a small, STANDALONE test binary rather
|
|
# than being folded into controller_unit_test_src above. sched.c/dataex.c are not
|
|
# part of that binary today -- several existing files there (test_commit_barrier_
|
|
# reply.c, test_worker_join.c) already provide their OWN local fake definitions
|
|
# of on_scheduler_join()/notify()/collect_confvars(), precisely because the real
|
|
# sched.c/dataex.c were never linked in. Linking the real ones alongside those
|
|
# fakes collides at link time (multiple definition). This binary links the real
|
|
# sched.c + its real dataex.c/egress.c dependencies, isolated from that
|
|
# collision; only opget.c's one-line check_worker_() is stubbed locally in the
|
|
# test file (linking all of opget.c would pull in its own further dependencies
|
|
# this test does not need).
|
|
sched_push_unit_test_src = [
|
|
'testsuite/test_job_array_sched_push.c',
|
|
'sched.c',
|
|
'dataex.c',
|
|
'egress.c',
|
|
]
|
|
|
|
sched_push_unit_test = executable('sched_push_unit_test',
|
|
sched_push_unit_test_src,
|
|
include_directories: [incdir],
|
|
dependencies: controller_unit_test_deps,
|
|
c_args: ['-DXCE_TESTING'],
|
|
install: false)
|
|
|
|
test('sched push test', sched_push_unit_test,
|
|
suite: 'controller',
|
|
timeout: 60,
|
|
env: ['ASAN_OPTIONS=detect_leaks=0'])
|
|
|
|
# job-array-single-wal-record task 5.2: apiserver.c's push logic
|
|
# (apiserver_job_new_fun / apiserver_push_jobarray) faces the identical
|
|
# real-vs-fake link collision task 5.1 hit for sched.c (test_commit_barrier_
|
|
# reply.c / test_worker_join.c already define their OWN fake notify()/
|
|
# on_scheduler_join(), so linking the real dataex.c into controller_unit_test
|
|
# collides at link time) -- so this is its own standalone binary too,
|
|
# mirroring sched_push_unit_test's strategy. UNLIKE sched.c, apiserver.c
|
|
# never calls job_submit_committed()/collect_jobs_committed() (egress.c), so
|
|
# this binary does NOT need egress.c -- verified by grep, not assumed
|
|
# identical to sched.c's dependency set.
|
|
apiserver_push_unit_test_src = [
|
|
'testsuite/test_job_array_apiserver_push.c',
|
|
'apiserver.c',
|
|
'dataex.c',
|
|
]
|
|
|
|
apiserver_push_unit_test = executable('apiserver_push_unit_test',
|
|
apiserver_push_unit_test_src,
|
|
include_directories: [incdir],
|
|
dependencies: controller_unit_test_deps,
|
|
c_args: ['-DXCE_TESTING'],
|
|
install: false)
|
|
|
|
test('apiserver push test', apiserver_push_unit_test,
|
|
suite: 'controller',
|
|
timeout: 60,
|
|
env: ['ASAN_OPTIONS=detect_leaks=0'])
|
|
|