Send the HA heartbeat as OP_nop + the existing HeartbeatMsg body carrying
{term, committed_lsn, committed_config_tag} (senderPriority unused). Generic
xce_nop_req untouched; C-side body support pre-existed (no typemap edit). Req 1.1
producer half. Round-trip test proves the 3 fields survive the wire; lib suite
0 failures under ASAN.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Append-only UInt64 epoch-millis field for the responder snapshot timestamp
(Req 11.1, wire-format setup). Hand-authored xce_ctrlstatus_t typemap gains a
matching responder_time_ms member; codec round-trips it. Controller suite 1/1 OK.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
On the standby replicated-apply path, ha_apply_single_entry wrote the entry via
persist_wal_write_replicated (which correctly set the self-computed CRC chain
link p->last_crc), then called apply_wal_entry with a SYNTHETIC header whose
crc=0. apply_wal_entry's `p->last_crc = hdr->crc` clobbered the chain link with
0, so every subsequent replicated write stamped prev_crc=0 on disk. The on-disk
CRC chain broke at the second replicated entry — invisible while live (standbys
serve in-memory state) but fatal on COLD RESTART: replay hit the break, returned
RECOVER_TRUNCATED, recovered only the config prefix, and lost all committed jobs
(joblist=0). The sticky truncated verdict then drove a promotion-fence
availability wedge (bug-777) when every survivor was truncated.
Fix — single ownership of the WAL header + CRC chain:
- apply_wal_entry is now LOGICAL entity-restore only: signature
(p, type, lsn, payload, payload_len); no header. It advances the current_lsn
high-water (monotonic) but NEVER touches p->last_crc.
- The physical layer is the sole owner of the CRC chain: persist_wal_write_-
replicated on the live path, replay_wal/persist_recover on recovery.
- ha_apply_single_entry drops the fabricated header and passes entry fields
directly. The persist_recover replay caller is updated to the new signature.
Verified: new RED->GREEN test test_replicated_apply_chain_survives_cold_restart
(drives the real ha_apply_wal_catchup_entry path, cold-replays -> RECOVER_CLEAN,
all N recovered); controller suite 0 failures; 3-node rolling-SIGKILL soak on a
real ext2/3 fs now passes 5/5 (was wedge+loss at round 3); full cold restart
recovers all 6 committed jobs (was 0) with CLEAN verdicts and a normal election.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Per design invariant (a controller exits only on crash or admin kill), replace the
self-abort recovery terminal (tasks 3.3/4.3/4.4) with a loud, permanent, non-promotable
fence that stays alive and keeps retrying catch-up (self-heals on peer return; no manual
admin recovery). Records the never-self-terminate invariant as project-wide guidance in
src/controller/CLAUDE.md + .kiro/steering/ha-async-io.md.
xce_failover_rotate reconnected with endpoint_fini+endpoint_init+endpoint_connect
but never re-bound ep->iomgr (reset by endpoint_init) nor re-armed the owner/
msg/err handlers + iomgr_monitor. endpoint_connect then dereferenced a NULL
iomgr (->ssl_ctx) → SEGV at netio.c:672 during live master failover. Added
xce_ctx_reconnect() in xcectx.c that mirrors xcecli_start's establishment
(without restarting iomgr/vtaskmgr or touching ctx->state); rotate delegates to
it. Found via live 3-node E2E. bug-610.
fsync_worker slept the full wal_sync_ms in one uninterruptible nanosleep()
before re-checking fsync_stop. persist_stop sets the flag and immediately
pthread_join()s, so the join blocked until the in-flight sleep returned —
up to a full wal_sync_ms per teardown. Tests set wal_sync_ms=5000 ("slow
fsync — no races"), so each persist_stop cost ~5s; across the ~7 suites
that use it the cumulative teardown time blew past the 300s controller-test
meson cap, killing the suite with SIGTERM.
Replace the nanosleep with pthread_cond_timedwait on a new fsync_mutex/
fsync_cond (added to persist_t, init in persist_init, destroyed in
persist_fini). persist_stop now sets fsync_stop and signals fsync_cond
under fsync_mutex before joining, so the worker wakes immediately. fdatasync
still runs under p->lock, released before re-acquiring fsync_mutex — no lock
nesting. The "commit: WAIT deadline expired" log lines were unrelated
intentional negative tests (50-300ms), not the cause.
Full controller suite now completes in ~10s (was >300s TIMEOUT); 0 failures.
Logged as bug-604.
Live symptom: jobsub intermittently failed with 'Connection timed out' even
though the cluster had quorum. Root cause: the synchronous commit barrier waits
only DEFAULT_SYNC_TIMEOUT_MS=50ms for durable majority replication, and that was
not configurable. 50ms is too tight for durable sync majority replication —
especially since standbys now fdatasync each replicated entry before ACK — so a
multi-entry jobsub's later WAL entry intermittently misses the window:
commit: WAIT deadline expired without commit (lsn=3 committed_lsn=2 timeout_ms=50)
-> persist hook returns -ETIMEDOUT -> handle_jobsubmit rejects -> client ETIMEDOUT.
Fix:
- Raise DEFAULT_SYNC_TIMEOUT_MS 50 -> 500 (config.h) — realistic for durable sync
majority replication, still bounded for failure detection.
- Add a --sync-timeout-ms controller flag threaded arguments -> myconf ->
persist pcfg (override applied before persist_init); 0 = use default, positive
overrides — so operators can tune per environment.
TDD: literal-pinned persist_config_defaults().sync_timeout_ms == 500. All
timeout-sensitive tests already pass an explicit timeout_ms (none rely on the
default), so none are slowed; full controller suite green under ASAN. No
commit-engine/barrier/replication/wire change beyond the default value + plumbing.
bug-561.
A standby applied replicated WAL entries via apply_wal_entry (the replay/
in-memory path) which restores entities + advances applied_lsn but NEVER writes
the entry to the standby's WAL segment. The standby then ACKed (feeding the
primary's commit majority) without persisting — a Raft durability violation:
entries counted toward a commit could be lost on standby restart, and standby
WAL files stayed empty (contradicting steering: log[i] = WAL segments for every
node). This is why ctrl-2/ctrl-3 received + acked the streamed own-term NOOP yet
kept empty seg-*.wal.
Fix: new persist_wal_write_replicated(p, lsn, type, payload, len) writes the
entry to the local WAL at the PRIMARY's lsn (no lsn-reassignment), with a
self-consistent intra-segment CRC chain (the streamed entry carries no term/crc;
each node chains independently and recovery validates intra-segment), fdatasyncs
for durability, advances current_lsn = max(current_lsn, lsn+1), rotates segments,
and does NOT re-broadcast. Wired into ha_apply_single_entry as
persist(durable) -> apply(in-memory) -> ACK; on persist failure: no apply, no ACK
(a standby never ACKs an entry it didn't persist). Covers single + batch
catch-up; OPCode_replEntry has no separate apply path (allow-list only), so all
live WAL apply now persists. Dedup guard (lsn+1<=current_lsn) makes re-streams
idempotent while still ACKing.
TDD: standby write -> drop persist_t -> reopen + persist_recover replays it
(single, 3-entry crc chain, post-dedup); checkpoint/oversized rejected. Full
controller suite green under ASAN; persist_wal_async / recovery / truncation /
streamer / wire untouched.
configAck branch: per-push majority (acked_config_lsn >= push_tag,
1+count > n_peers/2 over r->ce->n_peers, n_peers<=1 immediate,
ce==NULL -EINVAL); legacy >0 counting and n_active==0 shortcut dead.
push_config_to_standbys returns the barrier result; upgrade failure ->
send_upgrade_error (rc forwarded), no success ACK, no restart,
committed_config_tag success-only.
Remediation r1 (two CRITICAL review findings):
- F1: wire production config-ACK ingestion — replconfigpushreplymsg
decode branch in repl_ack_decode_and_dispatch -> repl_on_config_ack
on the promoted-vote ep; + defensive cluster.c OPCode_reply case.
Closes the unlanded half of ha-config-bootstrap 8.1; without this the
barrier would brick every multi-member config upgrade. No schema change.
- F2: keep the barrier off the iomgr thread — export
push_config_transport_only (non-blocking) for the 5 ha.c + join.c
streaming sites; barrier path now vtask-only (do_upgrade_config).
Wire-path test drives real capnp ACK bytes through the production decode
branch. 30/30 rollout, 6/6 repl_majority, 46/46 config_repl; census 0
FAIL; pre-existing fixture leak only (less than baseline).
7 cases: two covered short-circuits, timeout with committed_lsn
unmoved, covering-ACK release, sync_timeout_ms fallback (bounded both
directions), n_peers=1 standalone, NOT_READY passthrough via cap
saturation. Watermark resolved to current_lsn - 1 (design's literal
phrasing unsatisfiable per persist.h:71 invariant) with off-by-one
killing power both ways. 15 tests / 7 RED; suite baseline zero.
cluster_t embeds commit_engine_t; init in cluster_init_phase2 after the
vtaskmgr guard (idempotence-guarded — phase2 can run twice), wiring
repl_set_commit_engine + ha.repl back-pointer before any standby can
register; fini after iomgr/vtask shutdown. persist_wal_sync_append
passes written_lsn; engine-wired path drops -ENODEV and the
committed_lsn store (engine owns advancement); LSN-0 first-entry
routes to legacy per the accepted interim. p2 -ENODEV pin updated to
the Req 6.3 contract. 34/34 + 6/6 green through honest delegation;
census exactly at the 3 validated baselines; production binary links.
replicator_t gains ce pointer (set-once-before-traffic contract).
repl_on_ack feeds commit_on_ack after releasing r->lock (iomgr-safe);
four membership mutators feed commit_on_membership_change post-unlock,
gated on actual mutation. walAck branch delegates to commit_submit(WAIT)
when ce wired AND entry_lsn != 0 (LSN-0 interim guard until 5.3);
legacy counting kept for ce==NULL, marked DEPRECATED. commit.c linked
into production target (inert until 5.3 wiring). Tests 30-31 + all
repl_majority walAck cases green; 33/34 remain RED for 5.3; baseline
unchanged.
Tests 21-28: repl_active_standby_count contract (5 RED vs inert -1
stub) + 3 gate-level pins (n_peers<=1 always-true, zero-connected
reject, stateless re-accept) that 4.2 must preserve. Declaration in
repl.h; ha.c/ha.h untouched (4.2 boundary). 28 tests / 5 RED; suite
at the 3-failure baseline with unchanged signatures.
Standby sends WalAckReply via xce_reply after each successfully
applied WAL entry. ha_apply_wal_catchup_entry signature extended
with endpoint_t* and cluster_t* parameters. walackreplymsg union
arm added to RequestReply capnp schema and xce_reply_t. Error
entries skip ACK. Dispatch gate test confirms OPCode_walCatchupEntry
allowed in CTRL_STANDBY/ELECTING/INIT.
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
Add self-referential entries @3 :List(WalCatchupEntry) field with
$C.maplistcount("n_entries"). Single-entry path unaffected — n_entries
defaults to 0, entries to NULL when not using batch mode.
Add StateReport struct {appliedLsn, configTag} as stateReportMsg @15
variant in RequestReply.data union. Standby populates this in heartbeat
replies so the primary can track per-standby convergence.
capnpc-c 1.0.1 has a bug with inline :group inside codecgen unions;
workaround uses named outer struct (wire-equivalent). typemap.h
extended with state_report_t and union member for C codec access.
- config_repl.c: add handle_repl_config_push — standby handler for
OPCode_replConfigPush. Verifies SHA-256, saves blob to disk via
conf_save_config, reloads via load_primary_config, ACKs primary.
- config_repl.h: declare handle_repl_config_push.
- cluster.c: dispatch OPCode_replConfigPush to handle_repl_config_push;
populate c->myhost_info.name from myconf->name (ctrl-1/ctrl-2/ctrl-3)
instead of the static "controller" placeholder.
- ha.c: fix raft_cb_become_leader push_config_to_standbys call to pass
real config bytes and tag read from disk (was NULL/0 — standbys got
empty push and never saved config).
- typemap.h: add raw_sha256/raw_bytes/raw_bytes_len fields to
repl_config_push_req_t (mirrors upgrade_config_req_t pattern).
- request.c: pre-extract List(UInt8) sha256/bytes from OPCode_replConfigPush
before capn_free() in xce_decode(); free them in xce_free_request().
- helper.c: add all HA/replication opcode names to xce_request_op_name
so "unknown opcode 30" becomes "replConfigPush" in logs.
- cluster_def.h: add embedded myhost_info field to cluster_t struct.
- ha.h: declare ha_start_primary_heartbeat; remove dead
ha_find_and_connect_to_primary declaration.
Add void (*on_connected)(endpoint_t *ep) field to endpoint_t with
endpoint_set_on_connected() helper. io_handler fires it exactly once
immediately after ssl_handshake_done=1 then nulls the pointer.
Enables ha_start_election_async to send OP_requestVote as soon as
the TLS handshake with a peer completes — no blocking SSL_connect.
6 new unit tests pass; controller suite 1/1 OK.
Add millisecond-granularity delay_task_ms() to delaymgr using
clock_gettime(CLOCK_MONOTONIC) for deadline computation. Extends
delay_task_t with nextrun_ts field; delay_worker distinguishes
ms-tasks from second-tasks via non-zero nextrun_ts. Backward
compatible with existing delay_task callers.
4 delay tests pass (2 new: tolerance and invalid-args).
Provides the timeout primitive for election and committing watchdogs.
Add ctrl_tunables struct to cluster_t with per-table fields:
jobmgr_nhash/delta, workermgr_nhash/delta, qmgr_nhash/delta,
resmgr_nhash/delta/inst, xstrings_nhash
init_controller_tunables() sets defaults (jobs=512, others=128)
and is called from cluster_init_phase1 so values are available
before cluster_init_phase2. Phase2 reads from c->tunables instead
of cluster_config or local #defines.
Each table gets its own values since they hold different item counts:
jobs can scale to hundreds, workers/queues/resources are typically
single-digit to tens.
The vote_request_thread was sending raw capnp(RequestVoteRequest) bytes
but the server-side iomgr decodes every incoming packet as a Request
struct. This caused the term field (uint64) to be misread as the opcode
field (uint16), so vote RPCs were silently misrouted (term=1 → OPCode_reply,
term=2 → OPCode_hello) and no node ever got a vote from its peers.
Fix:
- controller.capnp: add requestvotemsg @27 to Request.body and
requestvotereplymsg @14 to RequestReply.data
- typemap.h: move request_vote_req_t/reply_t before xce_request_t;
add requestvotemsg/requestvotereplymsg to body/data unions
- ha.c: rewrite vote_request_thread send/recv to use xce_encode()
wrapper and decode outer Request→inner RequestReply on receive
- cluster.c: add case OPCode_requestVote handler calling
handle_request_vote() and replying via xce_reply()
All 188 unit tests pass.
