#ifndef HA_H #define HA_H /* * XCE Controller HA — role management and election (P1). * * P1-1 audit: the existing create_ssl_context() + iomgr_set_ssl_ctx() path * in cluster.c (line 559, set at line 583) covers all controller-to-controller SSL. * HA listeners (heartbeat, election probe, replication accept) reuse the same * ssl_ctx already installed on c->iomgr. * No new TLS infrastructure is needed — XCE runs on a trusted management LAN. * Peer identity is validated by host:port match against the --peers candidate list. * See design doc Part 5.9 and memory: Persistence & HA Trusted LAN Decision. * * P1-2: full struct definitions and API. * endpoint_t* (primary_ep) is intentionally omitted here — including netio.h * would pull in heavy OpenSSL headers and create circular dependency risks. * The watchdog (P1-3) will include netio.h directly where it needs endpoint_t. */ #include #include #include #include #include #include #include "config.h" /* XCE_MAXNAME_LEN, MAX_STANDBYS, etc. */ #include "myconf.h" /* myconf_t, config_version_tag */ #include "persist.h" /* persist_t, apply_wal_entry */ #include "typemap.h" /* wal_catchup_entry_t, state_report_t, xce_reply_t */ #include "xce/cluster.h" /* xce_candidate_t */ #include "zarray.h" #include "raft/raft.h" /* raft_state_t, raft_init */ /* Forward declaration — avoids circular include with cluster_def.h */ typedef struct cluster_s cluster_t; /* ── Inline PRNG for election jitter ───────────────────────── */ static inline uint64_t xorshift64_next(uint64_t *state) { uint64_t x = *state; x ^= x << 13; x ^= x >> 7; x ^= x << 17; *state = x; return x; } /* * ha_seed_jitter: seed the xorshift64 PRNG from /dev/urandom (8 bytes). * Falls back to CLOCK_MONOTONIC ^ priority ^ pid if urandom is unavailable. * Not inline — contains syscalls (open/read/close/clock_gettime/getpid). */ void ha_seed_jitter(uint64_t *seed, int my_priority); /* ── Role enum ─────────────────────────────────────────────── */ typedef enum { CTRL_PRIMARY = 0, CTRL_STANDBY = 1, CTRL_INIT = 2, /* Startup: listener open, awaiting heartbeat or election timeout */ CTRL_ELECTING = 3 /* Running quorum election via OP_requestVote */ } ctrl_role_t; /* ── Election types ────────────────────────────────────────── */ /* * ha_vote_entry_t: per-peer state accumulated by the election candidate. * One entry per peer in ha_elect_ctx_t.votes[] (flexible array). */ /* Forward declaration to avoid pulling netio.h into ha.h */ struct endpoint_t; typedef struct { xce_candidate_t *peer; /* Peer being solicited */ uint64_t my_term; /* Term sent in OP_requestVote */ uint64_t my_tag; /* config_tag sent in request */ uint64_t my_lsn; /* WAL LSN sent in request */ int vote_granted; /* 1 if peer granted vote */ int replied; /* 1 if peer replied (granted or denied) */ uint64_t peer_tag; /* peer's config_tag from reply */ uint64_t peer_lsn; /* peer's WAL LSN from reply */ struct endpoint_t *ep; /* Outgoing vote endpoint; NULL if connect failed or not yet connected */ } ha_vote_entry_t; /* * ha_elect_ctx_t: shared context for one quorum election round. * Allocated as: calloc(1, sizeof(*ctx) + (n_peers-1) * sizeof(ctx->votes[0])) * Stored in ha_state_t.elect_ctx (void * _Atomic) during election; NULL otherwise. */ typedef struct { int n_peers; /* Total peer count (excluding self) */ int votes_granted; /* Votes received; starts at 1 (self-vote) */ int n_replied; /* Number of peers that replied */ uint64_t max_resp_tag; /* Highest config_tag seen in any reply */ uint64_t max_resp_lsn; /* Highest WAL LSN seen among max_resp_tag peers */ int result; /* 1=primary, 0=standby, <0=error */ int done_posted; /* Guard: non-zero once sem_post(&done) has been called */ pthread_mutex_t lock; /* Protects votes_granted/n_replied/max_resp_tag/max_resp_lsn/result */ sem_t done; /* Startup thread blocks; dispatch posts when done */ /* Fix 4 (HIGH): pointer back to the election_timeout_ctx_t so that task 4.1 * (quorum-reached path) can set timeout_ctx->cancelled = 1 to cancel the * watchdog. Set by ha_start_election_async after scheduling the timeout. */ void *timeout_ctx; /* election_timeout_ctx_t*; NULL until watchdog scheduled */ /* Task 4.1: cluster_t* so ha_elect_evaluate_and_signal can call * cluster_init_phase2(c). * NULL in unit tests (c=NULL bypasses phase2). */ cluster_t *c; /* Task 6.3: candidate's own LSN/tag, stored unconditionally so that * ha_compute_safe_committed_lsn can use them even for single-node elections * where votes[] is empty (n_peers=0). */ uint64_t self_lsn; /* Candidate's own WAL LSN at election start */ uint64_t self_tag; /* Candidate's own config_tag at election start */ ha_vote_entry_t votes[]; /* C99 flexible array: n_peers-1 entries */ } ha_elect_ctx_t; /* ── HA configuration ──────────────────────────────────────── */ /* Default values used by cluster_init(). Tuned for a LAN with ≤5ms RTT. */ #define HA_DEFAULT_HEARTBEAT_INTERVAL_MS 3000 #define HA_DEFAULT_HEARTBEAT_TIMEOUT_MS 10000 #define HA_DEFAULT_ELECTION_TIMEOUT_MS 5000 #define HA_DEFAULT_PROBE_CONNECT_TIMEOUT_MS 500 /* Log the first connect failure per peer, then every Nth attempt. */ #define HA_CONNECT_LOG_THROTTLE 10 #define HA_DEFAULT_MAX_PROMOTION_RETRIES 5 #define HA_DEFAULT_ELECTION_JITTER_MAX_MS 200 #define HA_DEFAULT_ELECTION_PRIORITY_STEP_MS 500 typedef struct { uint32_t heartbeat_interval_ms; /* Primary heartbeat send interval (min 2000 ms) */ uint32_t heartbeat_timeout_ms; /* Standby timeout before promoting (>= interval) */ uint32_t election_timeout_ms; /* Election probe shared deadline (min 500 ms) */ uint32_t probe_connect_timeout_ms; /* Per-probe TCP connect timeout */ uint32_t max_promotion_retries; /* Max consecutive failed promotion attempts */ uint32_t election_jitter_max_ms; /* random jitter added to election timeout (default 200) */ uint32_t election_priority_step_ms; /* extra ms per priority level (default 500) */ } ha_config_t; /* probe_ctx_t deleted — only used by am_i_primary() (election-iomgr-refactor) */ /* ── HA runtime state (embedded in cluster_t as `ha_state_t ha` in P1-5) ── */ typedef struct { _Atomic uint64_t term; /* Election term — fencing token */ _Atomic int32_t role; /* Cast to ctrl_role_t at access sites */ int my_priority; /* Index in --peers list (lower = higher priority) */ _Atomic uint64_t applied_lsn; /* Standby: last applied WAL LSN */ char primary_host[XCE_MAXNAME_LEN]; /* Hostname of current primary */ uint32_t primary_port; /* Port of current primary */ /* last_heartbeat deleted — heartbeat freshness now derives from last_activity */ _Atomic int promotion_failed; _Atomic int promotion_retry_count; _Atomic int in_catch_up; /* Non-zero while processing historical WAL entries */ /* failover_requested deleted — watchdog replaced by ha_arm_heartbeat_timeout_vtask */ int hooks_registered; /* Idempotency guard for xce_add_hook calls */ uint32_t last_received_crc; /* Chained CRC of last received replicated entry */ ha_config_t config; pthread_mutex_t lock; /* Protects primary_host/port + voted_for_term/name */ /* watchdog_stop / watchdog_thread deleted — replaced by ha_arm_heartbeat_timeout_vtask */ void *ssl_ctx; /* SSL_CTX* cast; avoids pulling openssl headers here */ uint64_t jitter_seed; /* xorshift64 PRNG state for election jitter */ zarray_t *standby_endpoints; /* connected standby controller endpoints for config push */ /* ── New fields added by ha-config-bootstrap spec ──────── */ uint64_t voted_for_term; /* Req 9: term of last granted vote */ char voted_for_name[XCE_MAXNAME_LEN]; /* Req 9: candidate of last granted vote */ int primary_ctrl_fd; /* Req 6: persistent channel fd (-1 = none) */ bool defer_config_fetch; /* Req 3: tag=0 node defers fetch to post-election */ void * _Atomic elect_ctx; /* Req 2: ha_elect_ctx_t* during election; NULL otherwise */ _Atomic uint64_t last_known_committed_lsn; /* Req 5: from primary heartbeats */ sem_t heartbeat_seen; /* Req 1: posted by heartbeat handler during CTRL_INIT */ uint64_t last_known_committed_config_tag; /* Req 8: from primary heartbeats */ _Atomic uint64_t committed_config_tag; /* Req 8.1: set on quorum ACK */ /* ── New fields added by election-iomgr-refactor spec (Task 2.1) ── */ void *client_ssl_ctx; /* SSL_CTX* (TLS_client_method); created in myapp_run */ int phase2_done; /* 1 after cluster_init_phase2 runs */ int n_peers; /* total cluster size (including self), matches raft convention */ /* ── New fields added by raft-library spec (Task 6.1) ──────── */ raft_state_t raft; /* Raft consensus state (wired in task 6.2) */ /* ── New fields added by raft-library spec (Task 6.2) ──────── */ cluster_t *raft_c; /* cluster_t* set by ha_start_election_async; used by raft callbacks */ void *raft_election_timeout_ctx; /* election_timeout_ctx_t* for cancel (task 6.2) */ /* ── New fields added by ha-heartbeat-liveness spec (Task 1.1) ── */ time_t last_activity; /* CLOCK_MONOTONIC seconds of last primary message; 0 = none yet */ /* ── New fields added by ha-repl-hardening spec (Task 1.4) ──────── */ uint64_t standby_reported_tag[MAX_HA_CANDIDATES]; /* Last config_tag reported by each standby */ uint64_t standby_reported_lsn[MAX_HA_CANDIDATES]; /* Last applied_lsn reported by each standby */ bool standby_converged[MAX_HA_CANDIDATES]; /* Whether standby[i] has converged with primary */ int peer_connect_fail_count[MAX_HA_CANDIDATES]; /* throttle log spam on repeated connect failure */ /* ── New field added by ha-commit-engine spec (Task 4.2) ──────── */ replicator_t *repl; /* Back-pointer to the standby registry (persist_t.repl). * When set, ha_has_write_quorum counts registry truth via * repl_active_standby_count (ep != NULL && !in_catch_up); * NULL → legacy standby_endpoints->count fallback. * (Req 3.1-3.3, 6.1, 6.2; wired at init by task 5.3.) */ /* ── New field added by ha-convergence-recovery spec (Task 3.x) ──────── */ _Atomic int rejoin_reconciled; /* Defensive once-guard for rejoin * reconciliation (Req 2.1): set after the * first truncate+self-restart so a second * CtrlHelloReply in the same process * lifetime cannot re-fire the restart. * 0 at init (cleared by ha_init memset). */ /* ── New field added by ha-convergence-recovery spec (Task 4.x) ──────── */ _Atomic int catchup_inflight[MAX_STANDBYS]; /* Per-standby single-flight * guard for ACK-driven catch-up * continuation (Req 5.2): set when a * continuation is scheduled for a * standby slot, cleared when it * completes; a duplicate walAck while * the flag is set schedules nothing. * Slot identity (the repl registry slot * index) is stable across schedule/run. * 0 at init (cleared by ha_init memset). */ /* ── New field added by ha-convergence-recovery spec (Task 5.x) ──────── */ _Atomic int quorum_lost; /* Quorum-transition edge detector (Req * 8.1-8.3): 0 = quorum held (or unknown * at init), 1 = quorum lost. Flipped by * ha_log_quorum_transition via CAS so the * loss/restore WARN is emitted exactly * once per edge (no log storms across * repeated dispatch-gate rejections). * 0 at init (cleared by ha_init memset). */ } ha_state_t; /* ── Public API ────────────────────────────────────────────── */ /* * ha_init: zero-initialise *ha, validate cfg, store config and my_priority. * Returns 0 on success, -EINVAL on bad config. * Initial role is always CTRL_STANDBY. */ int ha_init(ha_state_t *ha, const ha_config_t *cfg, int my_priority); /* * ha_fini: destroy mutex. Watchdog thread join added in P1-3. */ void ha_fini(ha_state_t *ha); /* am_i_primary() deleted — replaced by ha_start_election_async (election-iomgr-refactor) */ /* * ha_promote_to_primary: stub — atomically sets role to PRIMARY. * Full promotion sequence (hooks, WAL flush, peer notify) added in P1-3a. */ int ha_promote_to_primary(cluster_t *c); /* * ha_demote_to_standby: stub — atomically sets role to STANDBY. * Full demotion sequence added in P1-3a. */ int ha_demote_to_standby(cluster_t *c); /* ── Internal promotion/demotion (P1-3a) ───────────────────── */ /* * ha_do_promote: increment term, set role=PRIMARY, reset last_received_crc. * No cluster_t dependency — fully testable standalone. * Callers: ha_promote_to_primary() (P1-5), watchdog failover path. */ void ha_do_promote(ha_state_t *ha); /* * ha_do_demote: set role=STANDBY, reset hooks_registered idempotency guard. * Hook disable requires cluster_t and is done in ha_demote_to_standby() (P1-5). */ void ha_do_demote(ha_state_t *ha); /* ── Demotion convergence + self-restart primitive ───────────── * (ha-convergence-recovery Requirement 1: a demoted ex-primary discards its * uncommitted, potentially divergent state and rejoins from committed state * only via truncation + process self-restart through boot recovery.) */ /* * controller_saved_argv: accessor for the NULL-terminated argv captured by * main() before argp_parse, used by ha_self_restart to re-exec the controller * (ha-convergence-recovery Req 1.3, design "Self-Restart Primitive"). * Returns NULL if argv was never saved (e.g. unit-test binaries). */ char **controller_saved_argv(void); /* * ha_self_restart: the truncate-and-restart primitive's restart half. * * Production contract (Req 1.3, 1.4): flush logs, execv(controller_saved_argv()) * to rebuild in-memory state through boot recovery from the persisted committed * state only; if exec cannot be performed, terminate FATALLY (abort) rather than * continue running with potentially divergent state — NEVER returns in * production. * * Test contract (Req 1.6): under XCE_TESTING, invoke ha_restart_hook instead of * execv and return its result (0 on the success path); a failing ha_restart_hook * routes to ha_fatal_hook in place of abort so tests can assert the FATAL path * without dying. * * Preconditions: persistence hooks already disabled; truncation completed * before this call. Invariant: no new WAL entry is appended by this node * between hook-disable and exec. */ int ha_self_restart(cluster_t *c); /* * ha_schedule_demotion_convergence: schedule the one-shot delaymgr task that * truncates above committed_lsn (Req 1.2), WARN-logs the discarded range * (Req 1.5), and self-restarts (Req 1.3). Called from raft_cb_become_follower's * was-PRIMARY branch AFTER the persistence hooks are disabled inline (Req 1.1), * so all file I/O and the exec run off the become-follower callback thread (D1). * Returns 0 on success, negative on alloc/schedule failure (suffix is then * reconciled by rejoin reconciliation at the next join). */ int ha_schedule_demotion_convergence(cluster_t *c); #ifdef XCE_TESTING /* * ha_demotion_convergence_fn: the delaymgr task body — exposed under XCE_TESTING * only so the demotion-convergence suite can reference its contract; the test * fixture drives the queued task through its stored entry pointer. */ int ha_demotion_convergence_fn(void *arg); #endif /* * ha_rejoin_reconcile: converge a rejoining node whose local WAL log runs ahead * of the cluster's committed boundary (ha-convergence-recovery Req 2.1–2.3, * design "Rejoin Reconciliation", research D5). * * Called from the standby's CtrlHelloReply intake (cluster.c) after the existing * last_known_committed_lsn store, with primary_committed_lsn = the boundary the * primary reported. * * Contract (task 3.2 GREEN implements; task 3.1 ships a RED no-op stub): * - local_tip = persist.current_lsn - 1. * - If local_tip > primary_committed_lsn AND the rejoin_reconciled once-guard * is clear: cutoff = max(primary_committed_lsn, local committed_lsn) — the * CLAMP that never discards the locally known committed prefix (Req 2.2) — * persist_truncate_wal_above(cutoff), WARN the discarded range, set the * once-guard, then ha_self_restart (deferred to delaymgr if the intake runs * on iomgr, same rule as demotion). Returns the restart result. * - Else (tip <= boundary): return 0 with NO side effects (Req 2.3). * - A second call in the same process lifetime takes no restart (Req 2.1 — * defensive once-guard; "once" is also structural since post-restart the tip * equals the boundary). * * Generalizes the RDHUP truncation pattern (ha_on_primary_ctrl_fd_rdhup), which * remains in place unchanged for the failover path. */ int ha_rejoin_reconcile(cluster_t *c, uint64_t primary_committed_lsn); /* * cluster_apply_ctrlhello_reply: standby-side CtrlHelloReply intake body * (ha-convergence-recovery task 3.1). Stores the primary-reported committed * boundary + config tag; called from cluster.c's myreq_handler on every * CtrlHelloReply. Defined in ha_convergence.c (a unit-linkable TU) so the * rejoin intake-integration test can drive the real path. Task 3.2 adds the * ha_rejoin_reconcile trigger after the store. */ void cluster_apply_ctrlhello_reply(cluster_t *c, uint64_t committed_lsn, uint64_t config_tag); /* * ha_walack_on_ack: the post-ACK catch-up decision (ha-convergence-recovery * task 4.2, Req 5.1, 5.2, 7.1, design D6). Called from the walAck branch of * repl_ack_decode_and_dispatch (ha.c) AFTER repl_on_ack, and from the * ha_walack_continuation_for_test shim so production and tests exercise the * same logic. Defined in config_repl.c (alongside ha_stream_wal_to_standby and * the continuation task body). * * target = max(committed_lsn, last_written) (same derivation as ha.c:2771-2776) * if acked_lsn < target → schedule ONE catch-up continuation that streams * [acked_lsn+1, target] on delaymgr (never inline on * iomgr), UNLESS c->ha.catchup_inflight[peer_idx] is * already set (per-standby single-flight, Req 5.2). * if acked_lsn >= target → repl_complete_catchup(&c->persist.repl, ep) to * re-include the standby in live replication (Req 7.1). * * c — cluster_t* (real persist + repl registry; never NULL). * ep — repl registry endpoint key for the standby (endpoint_t* / * repl_ep_t); identifies the standby slot for streaming + parity. * peer_idx — 0-based standby slot index (into c->ha.catchup_inflight[]). * acked_lsn— the LSN the standby just acknowledged. * * Returns 0 on the parity / single-flight-suppressed paths and on a successfully * scheduled continuation; negative on a scheduling/allocation failure. Never * performs file I/O itself (streaming runs in the deferred continuation task). */ int ha_walack_on_ack(cluster_t *c, void *ep, int peer_idx, uint64_t acked_lsn); /* * ha_log_quorum_transition: emit an operator-visible WARN on each write-quorum * loss/restore EDGE (ha-convergence-recovery task 5.x, Req 8.1, 8.2, 8.3). * * Evaluates the current write-quorum state and compares it against the * ha_state_t.quorum_lost edge-detector flag. On a TRANSITION (and only on a * transition), it atomically flips the flag via CAS and emits exactly one WARN: * - loss: "HA quorum lost: connected=%d required=%d" (Req 8.1) * - restore: "HA quorum restored: connected=%d required=%d" (Req 8.2) * The flag makes the logging an edge detector, NOT a latch: repeated calls while * the state is unchanged emit nothing (Req 8.3 — no log storms across repeated * dispatch-gate rejections), but a later loss/restore cycle logs again. The CAS * guarantees once-per-transition under concurrency. * * Call sites (task 5.2): the standby_endpoints mutation points (promotion * registration, RDHUP removal, on_standby_connected) plus the ha_dispatch_gate * quorum-rejection branch as a backstop. Observability only — never gates an * operation outcome. * * Defined in ha_convergence.c (a unit-linkable TU) so the quorum-transition * tests can drive it directly against a real persist/repl fixture. * * RED scaffold (task 5.1): the current definition is a NO-OP — it performs no * edge detection, flips no flag, and emits no WARN — so the quorum-transition * tests FAIL until task 5.2 lands the real edge-detection logic and wires the * call sites. */ void ha_log_quorum_transition(ha_state_t *ha); /* ── Redirect helpers used by join.c ──────────────────────── */ /* * ha_should_redirect: returns 1 if this controller should redirect join * requests to the primary. * Returns 0 if: (a) role is PRIMARY, or (b) primary_host is empty / * primary_port is 0 (no primary known yet — client should retry). */ int ha_should_redirect(const ha_state_t *ha); /* * ha_no_primary_known: returns 1 if role is STANDBY and primary_host is * empty or primary_port is 0. Caller should reply E_XCE_NOMASTER so the * client knows to retry later rather than treating the error as permanent. */ int ha_no_primary_known(const ha_state_t *ha); /* * ha_is_primary: returns 1 if ha->role is CTRL_PRIMARY, 0 otherwise. * Lock-free. Safe to call from any thread. */ int ha_is_primary(const ha_state_t *ha); /* ha_check_priority_stepdown() deleted — replaced by quorum election (Req 2.1) */ /* start_heartbeat_listener() / stop_heartbeat_listener() deleted — never called (election-iomgr-refactor) */ /* * ha_dispatch_gate: role-based operation filter for the vtaskmgr dispatch loop. * Returns: * 0 — operation is permitted for the current role * -E_XCE_NOT_READY — role is CTRL_INIT or CTRL_ELECTING and opcode is not * OP_requestVote or OP_probeConfigTag * -E_XCE_STANDBY — role is CTRL_STANDBY and opcode is a primary-only op * CTRL_PRIMARY always returns 0. */ int ha_dispatch_gate(ha_state_t *ha, int opcode); /* * ha_apply_wal_catchup_entry: apply a single WAL catch-up entry to local * persistent storage and advance ha->applied_lsn on success. * * Called from cluster.c OPCode_walCatchupEntry dispatch handler (Task 2.1). * On success (rc == 0): applied_lsn advances to entry->lsn+1 and a * WalAckReply {term, lsn, success=1} is sent back to the primary via * xce_reply(ep, c->myhost, &reply) (Task 3.1, Req 3.1). * On error (rc < 0): logs ERROR, returns error; no ACK sent (Task 3.2). * applied_lsn is in-memory only — not persisted to disk. * ep and c may be NULL in unit-test builds (XCE_TESTING); ACK is skipped. * Requirements: 3.1, 3.2, 3.3, 3.4, 3.5 */ int ha_apply_wal_catchup_entry(ha_state_t *ha, persist_t *p, wal_catchup_entry_t *entry, struct endpoint_t *ep, cluster_t *c); /* ha_nop_reply_state_report — populate a heartbeat reply with stateReport. * Fills *sr from ha->applied_lsn (atomic read) and myconf->config_version_tag, * then sets reply_out->data_which = stateReportMsg and * reply_out->data.state_report = sr. * Caller must keep *sr live until xce_reply() serialises the reply. */ void ha_nop_reply_state_report(ha_state_t *ha, myconf_t *myconf, state_report_t *sr, xce_reply_t *reply_out); /* ── Task 4.1 (ha-repl-hardening): safe commit point computation ───────────── * * ha_compute_safe_committed_lsn: determine safe_committed_lsn and safe_config_tag * from vote replies collected in ctx after winning an election. * * Collects LSNs from all granted voters (self + peers with vote_granted=1), * sorts descending, and returns the majority-threshold element. * * single-node (n_peers=0): returns ctx->self_lsn and ctx->self_tag directly — * self is the only majority; returning 0 would truncate all WAL on re-election. * * Requirements: 2.3 (ha-repl-hardening spec) * Task 6.3: single-node fix (self_lsn/self_tag fields added to ha_elect_ctx_t) */ void ha_compute_safe_committed_lsn(ha_elect_ctx_t *ctx, uint64_t *safe_lsn_out, uint64_t *safe_tag_out); /* ── Task 3.2: Unified replication decision enum and evaluator ────────────── */ /* * ha_repl_action_t: result of ha_evaluate_repl_action(). * * Encodes the single replication action the primary should take for a standby * on the current heartbeat cycle, based solely on the standby's reported * (config_tag, applied_lsn) vs the primary's committed state. * * Decision tree (design §Unified Heartbeat-Driven Protocol): * standby_tag < committed_tag → PUSH_CONFIG * standby_lsn < oldest_wal_lsn → SEND_SNAPSHOT * standby_lsn < committed_lsn → STREAM_WAL * tag >= committed AND lsn >= committed → CONVERGED * * Requirements: 2.2, 2.3, 2.4 (ha-repl-hardening spec) */ typedef enum { HA_REPL_PUSH_CONFIG, /* standby config tag is behind — push config first */ HA_REPL_SEND_SNAPSHOT, /* standby LSN predates oldest WAL — transfer snapshot */ HA_REPL_STREAM_WAL, /* standby LSN is within WAL window — stream entries */ HA_REPL_CONVERGED, /* standby tag and LSN are both current */ } ha_repl_action_t; /* * ha_evaluate_repl_action: pure decision function — no side effects. * * Evaluates the standby's reported (standby_tag, standby_lsn) against the * primary's committed state (committed_tag, committed_lsn, oldest_wal_lsn) * and returns the single action the primary should take this heartbeat cycle. * * Arguments: * standby_tag — config_tag last reported by this standby * standby_lsn — applied_lsn last reported by this standby * committed_tag — primary's committed config_tag * committed_lsn — primary's committed WAL LSN * oldest_wal_lsn — oldest retained WAL LSN (entries before this are gone) * * Requirements: 2.2, 2.3, 2.4 (ha-repl-hardening spec) * Boundary: Primary Heartbeat Handler (ha.c) */ ha_repl_action_t ha_evaluate_repl_action(uint64_t standby_tag, uint64_t standby_lsn, uint64_t committed_tag, uint64_t committed_lsn, uint64_t oldest_wal_lsn); /* * ha_process_standby_state: update per-standby convergence tracking. * * Called on each heartbeat reply from a standby while the primary is in * CTRL_PRIMARY. Stores the standby's reported * (config_tag, applied_lsn) and evaluates whether the standby has converged * with the primary's committed state. * * Convergence criteria (Req 1.3): * reported_tag >= committed_tag AND reported_lsn >= committed_lsn * * Logs INFO on the first transition from not-converged → converged (Req 7.2). * Regression (converged → not-converged) clears standby_converged[peer_idx] * and re-evaluates (Req 2.5). * * peer_idx: 0-based index into ha->standby_reported_* arrays; must be in * [0, MAX_HA_CANDIDATES). * * Requirements: 1.2, 2.2, 2.5 (ha-repl-hardening spec) * Boundary: Primary Heartbeat Handler (ha.c) */ void ha_process_standby_state(ha_state_t *ha, int peer_idx, uint64_t reported_tag, uint64_t reported_lsn, uint64_t committed_tag, uint64_t committed_lsn); /* ── Task 3.5c: Standby snapshot receive handler ──────────────────────────── */ /* * ha_handle_snapshot_chunk: receive one snapshot transfer chunk on the standby. * * Each chunk's payload bytes are written (or appended) to snap.part in snap_dir. * When chunk->is_last is non-zero: * 1. Verify total bytes written == chunk->total_size. * 2. Atomically rename snap.part → snap-{snapshot_lsn:016x}.bin. * 3. Load the snapshot via persist_load_snapshot(). * 4. Set ha->applied_lsn = p->checkpoint_lsn (in-memory only). * * On mid-transfer reconnect (caller resets state), snap.part is discarded. * Returns 0 on success, negative errno on error. * * Requirements: 4.2, 4.3, 4.4 (ha-repl-hardening spec) * Boundary: Standby Dispatch (cluster.c, ha.c) */ int ha_handle_snapshot_chunk(ha_state_t *ha, persist_t *p, const char *snap_dir, snapshot_transfer_t *chunk, const uint8_t *payload_bytes, size_t payload_len); /* ── HA Config Bootstrap & Term Durability (ha-config-bootstrap spec) ── */ /* * ha_persist_term: write ha-term.bin atomically to {workdir}/ha-term.bin. * Uses write + rename for durability (existing pattern in the codebase). * Must be called before any vote is granted or term is incremented. * If workdir is NULL, the file write is skipped (safe for unit tests). */ void ha_persist_term(ha_state_t *ha, const char *workdir); /* * ha_init_raft: initialize the embedded raft state machine with cluster topology. * * Must be called ONCE at controller startup after config is loaded and * ha_restore_term() has run. Subsequent elections (initial and re-elections * after primary loss) reuse the same raft state — only raft_start_election() * and raft_on_leader_lost() are called for each election cycle. * * Calling raft_init() more than once would reset raft's internal state * (term, voted_for, role) and could lose durable election progress. * * n_peers: total cluster size including self (candidates_count from config). */ void ha_init_raft(ha_state_t *ha, cluster_t *c, int n_peers); /* * ha_restore_term: read {workdir}/ha-term.bin at startup and restore * ha->term and ha->voted_for_* into ha_state_t. * * On missing file (ENOENT): no-op — term stays 0, voted_for_name stays empty. * Returns 0 (safe first-boot path). Req 9.3. * On CRC/magic mismatch: log WARN, zero ha->term and ha->voted_for_* for * safety and return 0. Req 9.2. * On valid file: atomically restore ha->term; copy voted_for_term * and voted_for_name. Returns 0. Req 9.2. * On unexpected I/O error: return -errno. * * Must be called after ha_init() and before any election or vote processing. * If workdir is NULL, the function is a no-op (safe for unit tests). * Requirements: 9.1, 9.2, 9.3. */ int ha_restore_term(ha_state_t *ha, const char *workdir); /* * handle_request_vote: process an incoming OP_requestVote RPC. * Applies term/voted_for/freshness gate; persists state via ha_persist_term(). * Returns 1 = vote granted, 0 = vote denied, <0 = error. * Requirements: 2.2, 2.3, 2.4, 2.5, 2.6, 9.1 * * TEST-ONLY (XCE_TESTING): production vote dispatch is cluster.c → * raft_on_vote_request. This is the legacy entry point for test-only * role-gate unit tests (test_ha_vote_gate.c, test_ha_election.c). */ #ifdef XCE_TESTING int handle_request_vote(ha_state_t *ha, uint64_t term, const char *candidate_id, uint64_t config_tag, uint64_t last_lsn, uint64_t my_config_tag, uint64_t my_last_lsn, int in_catch_up_flag); #endif /* * ha_vote_self_freshness: compute the voter's effective freshness floor. * * Election safety: a voter must deny candidates that are outdated against the * strongest knowledge it has of the cluster's COMMITTED state — not merely its * own local config file / applied LSN. The floor is the per-field max of the * voter's local state and its learned-committed state: * * *out_tag = max(local_config_tag, atomic committed_config_tag) * *out_lsn = max(local_applied_lsn, atomic last_known_committed_lsn) * * Uses acquire loads of the atomic learned-committed fields; never reads the * non-atomic last_known_committed_config_tag (data-race safe). Pure aside from * the atomic reads — no state mutation. */ void ha_vote_self_freshness(ha_state_t *ha, uint64_t local_config_tag, uint64_t local_applied_lsn, uint64_t *out_tag, uint64_t *out_lsn); /* * ha_elect_evaluate_and_signal: evaluate accumulated ha_elect_ctx_t votes. * Sets ctx->result (1=primary, 0=standby) and posts ctx->done semaphore. * Applies quorum check, fresher-peer yield gate, and config_tag=0 fatal gate. * Requirements: 2.1, 2.7, 2.8 */ ctrl_role_t ha_elect_evaluate_and_signal(ha_state_t *ha, ha_elect_ctx_t *ctx); /* * handle_request_vote_reply: process an incoming reply to an OP_requestVote RPC. * * Called by each per-peer vote-request thread once the peer replies (or times out). * Updates the entry in ctx->votes[peer_idx] with the reply fields. * Increments ctx->votes_granted if vote_granted is non-zero. * Increments ctx->n_replied unconditionally. * Updates ctx->max_resp_tag / ctx->max_resp_lsn to track the freshest peer seen. * When quorum is reached (votes_granted >= quorum) OR all peers have replied * (n_replied >= n_peers), calls ha_elect_evaluate_and_signal() to post ctx->done. * * peer_idx: 0-based index into ctx->votes[] identifying the replying peer. * term: term the peer reported in its reply (used for fencing if > ha->term). * vote_granted: non-zero if the peer granted the vote, 0 if denied. * peer_config_tag: peer's current config_tag at reply time. * peer_lsn: peer's current WAL LSN at reply time. * * Requirements: 2.2, 2.3, 2.4, 2.5, 2.6, 9.1 */ void handle_request_vote_reply(ha_state_t *ha, ha_elect_ctx_t *ctx, int peer_idx, uint64_t term, int vote_granted, uint64_t peer_config_tag, uint64_t peer_lsn); /* * xce_probe_config_tag: single-RTT OP_probeConfigTag RPC to one peer. * Fills *tag_out with the peer's current config_tag on success. * Returns 0 on success, -errno on connection/protocol error. */ int xce_probe_config_tag(const char *host, uint16_t port, uint64_t *tag_out); /* * ha_wait_for_heartbeat_or_timeout: wait in CTRL_INIT for an incoming heartbeat. * * Blocks on sem_timedwait(&ha->heartbeat_seen, &deadline) where * deadline = now(CLOCK_REALTIME) + election_timeout_ms + xorshift64_jitter * * Returns CTRL_STANDBY — heartbeat arrived; ha_do_demote() was called * (role is now CTRL_STANDBY). * Returns CTRL_ELECTING — deadline expired; caller must drive the election. * * The heartbeat handler posts heartbeat_seen only when role == CTRL_INIT. * OPCode_heartbeat is allowed through ha_dispatch_gate() in CTRL_INIT state * so that the primary's periodic heartbeat can reach the handler. * * Requirements: 1.1 (heartbeat → CTRL_STANDBY), 1.2 (timeout → CTRL_ELECTING). * Boundary: Controller FSM (ha.c). */ ctrl_role_t ha_wait_for_heartbeat_or_timeout(ha_state_t *ha); /* ── Task 9.4: EPOLLRDHUP Failover and Heartbeat Timeout (Req 6.2–6.4, 6.8) ─ * ha_on_primary_ctrl_fd_rdhup: EPOLLRDHUP event handler. * Closes primary_ctrl_fd, transitions to CTRL_ELECTING, truncates WAL to * last_known_committed_lsn, fires ha_start_election_async (via cluster when non-NULL). * Pass c == NULL to skip persist/election (unit test mode). */ void ha_on_primary_ctrl_fd_rdhup(ha_state_t *ha, cluster_t *c); /* * ha_arm_heartbeat_timeout_vtask: start/re-arm the heartbeat watchdog thread. * Fires ha_on_primary_ctrl_fd_rdhup after election_timeout_ms + rand_jitter of * silence. Calling ha_on_heartbeat_received() resets the deadline. */ void ha_arm_heartbeat_timeout_vtask(ha_state_t *ha, cluster_t *c); /* ha_discover_primary: step down from CTRL_ELECTING to CTRL_STANDBY when a * live primary message (NOP, config push, ctrlhello, WAL, snapshot) arrives. * Safe to call from any state — no-ops unless role == CTRL_ELECTING. */ void ha_discover_primary(ha_state_t *ha, cluster_t *c); /* ha_on_heartbeat_received: reset the heartbeat deadline (Req 6.3). */ void ha_on_heartbeat_received(ha_state_t *ha); /* ha_disarm_heartbeat_timeout_vtask: stop the heartbeat watchdog thread. */ void ha_disarm_heartbeat_timeout_vtask(ha_state_t *ha); /* * ha_start_primary_heartbeat: arm a repeating delaymgr task that sends * OPCode_nop to every standby in ha->standby_endpoints every * heartbeat_interval_ms. Keeps the standby-side watchdog from timing out * when the cluster is idle (no WAL entries, no config pushes). * Must be called after ha->role is set to CTRL_PRIMARY. * No-op when c == NULL (test mode). */ void ha_start_primary_heartbeat(cluster_t *c); /* ── Task 2.4: Non-blocking async election initiator ────────────────────── */ /* * ha_start_election_async: initiate a quorum election without blocking. * * Steps: * 1. Store n_peers in ha->n_peers. * 2. For single-node (n_peers == 1): call ha_elect_evaluate_and_signal directly * with a self-only ha_elect_ctx_t — shortcircuit, no iomgr/delaymgr needed. * 3. For multi-node: for each peer in peers[], allocate vote_ep_ctx_t, init * endpoint with client_ssl_ctx, set on_vote_connected + vote_ep_err_handler, * call endpoint_connect + iomgr_monitor; skip peer on connect failure. * Allocate election_timeout_ctx_t (cancelled=0) and schedule * delay_task_ms(delaymgr, election_timeout_ms, 1, election_timeout_fn, ctx). * 4. Returns immediately; election result delivered via ha_elect_evaluate_and_signal. * * Observable: returns in < 5ms; endpoints registered in iomgr; watchdog in delaymgr. * Requirements: 1.3 (non-blocking), 2.1 (single-node shortcircuit), 2.4 (async vote) * Boundary: ha.c (election orchestration) */ void ha_start_election_async(ha_state_t *ha, cluster_t *c, int n_peers, xce_candidate_t **peers, uint64_t my_config_tag, uint64_t my_lsn, const char *my_name); /* * ha_dispatch_repl_action_for_standby: evaluate the replication decision for * one standby and execute the resulting action. * * Reads ha->standby_reported_tag[peer_idx] and ha->standby_reported_lsn[peer_idx] * (stored by ha_process_standby_state on the previous call), calls * ha_evaluate_repl_action, and acts on the result: * - HA_REPL_PUSH_CONFIG: In production builds, calls push_config_to_standbys(c, …). * In XCE_TESTING builds, calls ha_repl_push_config_for_standby_hook(c, peer_idx). * - HA_REPL_STREAM_WAL: calls ha_stream_wal_to_standby(ep, wal_path, standby_lsn, * committed_lsn) to batch-stream WAL entries via xce_request() (non-blocking). * In XCE_TESTING builds, calls ha_repl_stream_wal_hook if non-NULL. * - HA_REPL_SEND_SNAPSHOT: calls ha_send_snapshot_to_standby(ep, snap_path, lsn). * In XCE_TESTING builds, calls ha_repl_send_snapshot_hook(peer_idx) if non-NULL. * - HA_REPL_CONVERGED: no-op. * * One action per heartbeat cycle per standby (design §Unified Heartbeat-Driven * Protocol). CONVERGED is a no-op. * * ep — outbound endpoint to the standby (used for STREAM_WAL; may be * NULL in tests that only exercise PUSH_CONFIG or CONVERGED paths) * peer_idx — 0-based index into ha->standby_reported_* arrays * committed_tag — primary's committed config_tag (from c->myconf or test fixture) * committed_lsn — primary's committed WAL LSN (from c->persist or test fixture) * oldest_wal_lsn— oldest retained WAL LSN (0 = all WAL retained, skip snapshot) * * Returns 0 on success; negative on internal error. * Requirements: 1.4, 5.1–5.5 (ha-repl-hardening spec) */ int ha_dispatch_repl_action_for_standby(ha_state_t *ha, cluster_t *c, endpoint_t *ep, int peer_idx, uint64_t committed_tag, uint64_t committed_lsn, uint64_t oldest_wal_lsn); /* * ha_send_ctrlhello_to_all_standbys: iterate ha->standby_endpoints and send * an OP_hello CtrlHelloRequest to each connected standby. * This triggers the existing catch-up replication path in handle_ctrlhello * (Req 7.2). Defined in cluster.c; called from ha_elect_evaluate_and_signal * in the post-election path. */ void ha_send_ctrlhello_to_all_standbys(cluster_t *c); /* ── P3-6: Test-only failover shim ────────────────────────────── */ #ifdef XCE_TESTING /* * ha_phase2_hook: test-only seam for cluster_init_phase2. * When non-NULL, ha_elect_evaluate_and_signal() calls this INSTEAD OF the * real cluster_init_phase2() so unit tests can count phase2 calls without * requiring a real cluster_t. Pattern mirrors xce_vote_request_hook. */ extern int (*ha_phase2_hook)(void *c); /* * ha_send_ctrlhello_hook: test-only seam for ha_send_ctrlhello_to_all_standbys. * When non-NULL, ha_elect_evaluate_and_signal() calls this in the post-election * path instead of the real function (cluster.c not linked in test binary). * Requirements: 7.2. */ extern int (*ha_send_ctrlhello_hook)(void *c); /* * ha_push_config_hook: test-only seam for push_config_to_standbys. * When non-NULL, ha_elect_evaluate_and_signal() calls this in the post-election * path instead of the real function. Requirements: 7.1. */ extern int (*ha_push_config_hook)(void *c); /* * ha_repl_push_config_for_standby_hook: test-only seam for the per-standby * config push triggered by the heartbeat-reply decision loop (Task 3.3). * * When non-NULL, ha_dispatch_repl_action_for_standby() calls this INSTEAD OF * push_config_to_standbys() when the decision is HA_REPL_PUSH_CONFIG, so unit * tests can verify the wiring without requiring a real cluster_t or network. * * Signature: int hook(void *c, int peer_idx) * c — cluster_t* (may be NULL in test mode) * peer_idx — 0-based index of the standby that triggered the push * Requirements: 1.4 (ha-repl-hardening) */ extern int (*ha_repl_push_config_for_standby_hook)(void *c, int peer_idx); /* * ha_repl_stream_wal_hook: test-only seam for ha_stream_wal_to_standby. * * When non-NULL, ha_dispatch_repl_action_for_standby() calls this INSTEAD OF * ha_stream_wal_to_standby() when the decision is HA_REPL_STREAM_WAL, so unit * tests can count batch-send invocations without requiring a real endpoint or * WAL directory. * * Signature: int hook(void *ep, const char *wal_path, * uint64_t standby_lsn, uint64_t committed_lsn) * ep — endpoint_t* (may be NULL in test mode) * wal_path — WAL directory path * standby_lsn — standby's last applied LSN * committed_lsn— primary's committed LSN * Requirements: 5.1–5.5 (ha-repl-hardening) */ extern int (*ha_repl_stream_wal_hook)(void *ep, const char *wal_path, uint64_t standby_lsn, uint64_t committed_lsn); /* * ha_repl_send_snapshot_hook: test-only seam for ha_send_snapshot_to_standby. * * When non-NULL, ha_dispatch_repl_action_for_standby() calls this INSTEAD OF * ha_send_snapshot_to_standby() when the decision is HA_REPL_SEND_SNAPSHOT, * so unit tests can verify the wiring without requiring a real endpoint or * snapshot directory. * * Signature: int hook(int peer_idx) * peer_idx — 0-based index of the standby that triggered the snapshot * Requirements: 4.1–4.5 (ha-repl-hardening) */ extern int (*ha_repl_send_snapshot_hook)(int peer_idx); /* * ha_tcp_connect_hook: test-only seam for the raw TCP connect inside * ha_find_and_connect_to_primary. When non-NULL, the function calls this * INSTEAD OF the real getaddrinfo/connect path, allowing unit tests to inject * socketpair fds without real network I/O. * Signature: int hook(const char *host, int port) * Returns fd >= 0 on success, or -errno on failure. * Requirements: task 9.2. */ extern int (*ha_tcp_connect_hook)(const char *host, int port); /* Test-only shim: demote then re-promote; returns new term. * Exercises the manual failover state machine without a live cluster_t. * Calls ha_do_demote() then ha_do_promote(); validates role transitions * and term monotonicity. See design doc P3-6 and src/docs/persistence-and-ha-design.md. */ uint64_t ha_trigger_manual_failover_for_test(ha_state_t *ha); /* * ha_rdhup_election_hook: test-only seam for ha_start_election_async in the * RDHUP failover path. * * When non-NULL, ha_on_primary_ctrl_fd_rdhup() calls this INSTEAD OF the real * ha_start_election_async() so unit tests can verify the RDHUP path triggers * async re-election without requiring a live iomgr/delaymgr. * * The hook receives the same arguments that would be passed to ha_start_election_async. * Requirements: 6.3, 6.5, 9.3. */ extern void (*ha_rdhup_election_hook)(ha_state_t *ha, cluster_t *c, int n_peers, xce_candidate_t **peers, uint64_t my_config_tag, uint64_t my_lsn, const char *my_name); /* * vote_ep_ctx_set_cluster_for_test: set the cluster_t pointer inside the * vote_ep_ctx_t stored at ep->data. Used by unit tests that need the * promoted-endpoint dispatch path to reach ha_promote_to_primary(c) with a * live cluster pointer. * The vote_ep_ctx_t struct is internal to ha.c; this helper avoids exposing it. * Requirements: task 7.3 (ha-peer-connection-reuse). */ void vote_ep_ctx_set_cluster_for_test(struct endpoint_t *ep, cluster_t *c); /* * ha_restart_hook: test-only seam for ha_self_restart's process re-execution * (ha-convergence-recovery Req 1.6). * * When non-NULL, ha_self_restart() invokes this INSTEAD OF execv() so unit * tests can observe the eventual restart deterministically (the demotion * convergence task and rejoin reconciliation both end in ha_self_restart). * The hook's return value is ha_self_restart's return value on the * test-success path; a NON-ZERO return models an exec failure and routes * ha_self_restart to the FATAL contract via ha_fatal_hook (Req 1.4). * * Signature: int hook(cluster_t *c) * Returns 0 to model a successful restart; non-zero to model exec failure. */ extern int (*ha_restart_hook)(cluster_t *c); /* * ha_fatal_hook: test-only seam for the FATAL (abort) contract of * ha_self_restart (ha-convergence-recovery Req 1.4). * * When non-NULL, ha_self_restart() invokes this INSTEAD OF abort() when the * restart cannot be performed, so a test binary can assert the FATAL path was * taken without the process dying. ha_self_restart returns after invoking it * (test builds only — production aborts). * * Signature: void hook(const char *msg) */ extern void (*ha_fatal_hook)(const char *msg); /* * raft_cb_become_follower_with_cluster_for_test: drive the follower path with * a LIVE cluster pointer (ha-convergence-recovery task 2.1 demotion-sequence * tests). Unlike raft_cb_become_follower_for_test (which forces raft_c = NULL * to suppress production calls), this shim sets ha->raft_c = c first so the * cluster-dependent demotion-convergence branch (task 2.2: hook disable + * scheduled truncate/restart) is exercised against a real persist/hooksys/ * delaymgr fixture. Mirrors the real-cluster seam ha_promote_to_primary(c) * used by the promotion-side lifecycle tests. */ void raft_cb_become_follower_with_cluster_for_test(cluster_t *c, uint64_t term); /* * ha_walack_continuation_for_test: test-only entry point for the ACK-driven * catch-up continuation logic (ha-convergence-recovery task 4.x, Req 5.1, 5.2, * 7.1). * * The production trigger lives in the walAck branch of * repl_ack_decode_and_dispatch (ha.c), which decodes a real Cap'n Proto * WalAckReply off the wire — too heavy to drive from a unit test. This shim * exposes the SAME post-ACK decision the walAck branch performs after * repl_on_ack, so the continuation / single-flight / parity behaviors can be * exercised directly against a unit fixture: * * target = max(committed_lsn, last_written) (same derivation as ha.c:2771-2776) * if acked_lsn < target → schedule ONE continuation that streams * [acked_lsn+1, target] via the catch-up streaming * path, UNLESS ha.catchup_inflight[peer_idx] is set * (single-flight, Req 5.2); the continuation must not * dispatch any heartbeat/stateReport action (Req 5.1). * if acked_lsn >= target → repl_complete_catchup(&c->persist.repl, ep), which * clears the standby's in_catch_up (Req 7.1). * * c — cluster_t* (real persist + repl registry; never NULL in tests) * ep — repl registry endpoint key for the standby (the same pointer * passed to repl_add_standby); identifies the standby slot. * peer_idx — 0-based standby slot index (into ha.catchup_inflight[]). * acked_lsn— the LSN the standby just acknowledged. * * Returns 0 on the no-op / parity paths and on a successfully scheduled * continuation; negative on a scheduling failure. * * RED scaffold (task 4.1): ha_convergence.c currently records the ACK only and * neither schedules a continuation nor calls repl_complete_catchup — task 4.2 * implements the real decision. The continuation / single-flight / parity tests * therefore FAIL until 4.2 lands. */ int ha_walack_continuation_for_test(cluster_t *c, void *ep, int peer_idx, uint64_t acked_lsn); /* * ha_quorum_transition_log_hook: test-only emission-count seam for * ha_log_quorum_transition (ha-convergence-recovery task 5.x, Req 8.1-8.3). * * There is NO log-capture harness in this testsuite, so the quorum-transition * tests use a counter/edge-observable instead (the task permits "log-capture OR * counter-hook pattern"). When non-NULL, ha_log_quorum_transition invokes this * hook EXACTLY ONCE on each transition it WARNs about, passing the new state and * the connected/required counts that go into the WARN line. Tests count * invocations to assert "logged once per transition" (Req 8.3) and inspect the * arguments to assert the loss line carries the right counts (Req 8.1). * * Signature: void hook(int lost, int connected, int required) * lost — 1 on a quorum-LOSS edge, 0 on a quorum-RESTORE edge. * connected — connected standby count reported in the WARN line. * required — required standby count (quorum threshold) in the WARN line. * * RED scaffold (task 5.1): ha_log_quorum_transition is a no-op stub that never * invokes this hook, so the transition tests' emission-count assertions FAIL * until task 5.2 implements the real edge detection. */ extern void (*ha_quorum_transition_log_hook)(int lost, int connected, int required); #endif #endif /* HA_H */