feat: add config replication fields to myconf_t, cluster_t, ha_state_t, persist_t; create byteorder.h

src/controller/ha.h

@@ -18,16 +18,45 @@
  * The watchdog (P1-3) will include netio.h directly where it needs endpoint_t.
  */
 
+#include <fcntl.h>
 #include <pthread.h>
 #include <stdatomic.h>
 #include <stdint.h>
 #include <time.h>
+#include <unistd.h>
 
 #include "config.h"   /* XCE_MAXNAME_LEN, MAX_STANDBYS, etc. */
+#include "zarray.h"
 
 /* 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;
+}
+
+static inline void ha_seed_jitter(uint64_t *seed, int my_priority)
+{
+    int fd = open("/dev/urandom", O_RDONLY);
+    if (fd >= 0) {
+        if (read(fd, seed, 8) == 8 && *seed != 0) { close(fd); return; }
+        close(fd);
+    }
+    struct timespec ts;
+    clock_gettime(CLOCK_MONOTONIC, &ts);
+    *seed = (uint64_t)ts.tv_nsec
+          ^ ((uint64_t)my_priority << 56)
+          ^ ((uint64_t)getpid() << 16);
+}
+
 /* ── Role enum ─────────────────────────────────────────────── */
 typedef enum {
     CTRL_PRIMARY = 0,
@@ -42,6 +71,8 @@ typedef enum {
 #define HA_DEFAULT_ELECTION_TIMEOUT_MS      2000
 #define HA_DEFAULT_PROBE_CONNECT_TIMEOUT_MS 500
 #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) */
@@ -49,8 +80,22 @@ typedef struct {
     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;
 
+/* Forward declaration for election probe context */
+struct xce_candidate_s;
+
+typedef struct {
+    struct xce_candidate_s *candidate; /* peer to probe */
+    void                   *ssl_ctx;   /* SSL_CTX* (void* to avoid openssl header) */
+    uint32_t                timeout_ms;
+    atomic_int             *election_done;
+    int                     got_ack;
+    pthread_t               thread;
+} probe_ctx_t;
+
 /* ── 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 */
@@ -71,6 +116,9 @@ typedef struct {
     /* Watchdog thread — started in P1-3 */
     _Atomic int       watchdog_stop;
     pthread_t         watchdog_thread;
+    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 */
 } ha_state_t;
 
 /* ── Public API ────────────────────────────────────────────── */
@@ -166,6 +214,11 @@ int ha_should_redirect(const ha_state_t *ha);
  */
 int ha_no_primary_known(const ha_state_t *ha);
 
+int  ha_is_primary(const ha_state_t *ha);
+void ha_check_priority_stepdown(ha_state_t *ha, int sender_priority, uint64_t sender_term);
+void start_heartbeat_listener(cluster_t *c);
+void stop_heartbeat_listener(cluster_t *c);
+
 /* ── P3-6: Test-only failover shim ────────────────────────────── */
 
 #ifdef XCE_TESTING

src/include/byteorder.h

@@ -0,0 +1,18 @@
+#pragma once
+/* Portable be64toh() for non-glibc or pre-2.25 targets. */
+#if defined(__linux__)
+#  include <endian.h>
+#elif defined(__APPLE__)
+#  include <machine/endian.h>
+#  include <libkern/OSByteOrder.h>
+#  define be64toh(x) OSSwapBigToHostInt64(x)
+#else
+#  include <stdint.h>
+static inline uint64_t be64toh(uint64_t x) {
+#  if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+    return __builtin_bswap64(x);
+#  else
+    return x;
+#  endif
+}
+#endif

src/include/myconf.h

@@ -4,11 +4,17 @@
 
 #define MAX_MASTER_CANDIDATES (64)
 
+#include <time.h>
+#include <stdint.h>
+
 #include <tlog.h>
 
 #include "clusterconfig.h"
 #include "xce/cluster.h"
 
+/* Forward declaration — avoids circular include with cluster_def.h */
+typedef struct cluster_s cluster_t;
+
 struct logging {
     char* logdir;
     char* loglevel;
@@ -22,9 +28,20 @@ typedef struct {
     char*                workdir;    /* working directory for WAL/snapshot storage */
     char*                name;       /* controller name (hostname by default) */
     xce_cluster_config_t peers_cfg;  /* HA peer list parsed from --peers; count==0 = single-node */
+    uint64_t             config_version_tag;   /* first 8 bytes of SHA-256, host order */
+    uint8_t              config_sha256[32];     /* full SHA-256 of conffile bytes */
+    int                  conf_keep_n;           /* versioned file retention count (default 2) */
+    uint64_t             config_generation;     /* monotonic audit counter */
+    time_t               conf_stale_timeout;    /* seconds before saved config flagged stale (default 86400) */
+    int                  config_stale;          /* 1 when saved config older than conf_stale_timeout */
 } myconf_t;
 
 extern cluster_config_t* get_default_conf(void*);
 extern int               add_config(void*, char*, char*);
 
+void myconf_fini(myconf_t *myconf);
+
+int load_primary_config(cluster_t *c);
+int fetch_config_from_primary(cluster_t *c);
+
 #endif

src/include/persist.h

@@ -24,6 +24,7 @@ typedef struct {
     uint32_t finished_retain_s;       /* retain finished jobs N seconds (default 3600) */
     uint32_t worker_retain_s;         /* retain unavailable workers N seconds (default 86400) */
     uint32_t sync_timeout_ms;         /* sync replication ACK timeout ms (default 50) */
+    uint32_t max_wal_records;          /* checkpoint trigger: records since last snap (default 10000) */
 } persist_config_t;
 
 static inline persist_config_t persist_config_defaults(void)
@@ -37,6 +38,7 @@ static inline persist_config_t persist_config_defaults(void)
     c.finished_retain_s       = DEFAULT_FINISHED_RETAIN_S;
     c.worker_retain_s         = DEFAULT_WORKER_RETAIN_S;
     c.sync_timeout_ms         = DEFAULT_SYNC_TIMEOUT_MS;
+    c.max_wal_records         = 10000;
     return c;
 }
 
@@ -78,12 +80,13 @@ struct persist_s {
 
     /* Concurrency */
     pthread_mutex_t lock;
+    _Atomic uint32_t  wal_record_count;       /* records appended since last checkpoint */
+    _Atomic int       checkpoint_in_progress; /* CAS guard: 0=idle, 1=scheduled/running */
     atomic_int      fsync_stop;
     atomic_int      fsync_thread_running;
     pthread_t       fsync_thread;
 
     /* Checkpoint (stubs for now — wired in Task 10) */
-    atomic_int      checkpoint_in_progress;
     atomic_int      checkpoint_requested;
     pthread_cond_t  checkpoint_done;
     pthread_mutex_t checkpoint_mutex;

src/include/xce/cluster_def.h

@@ -120,6 +120,10 @@ typedef struct cluster_s {
     int                 running;
     persist_t           persist;   /* Persistence module — P0-F */
     ha_state_t          ha;        /* HA role management — P1-5 */
+    _Atomic int         restart_requested;           /* set by OP_upgradeConfig handler */
+    pthread_t           heartbeat_listener_tid;      /* pre-Phase-2 SSL listener thread */
+    _Atomic int         heartbeat_listener_running;
+    _Atomic int         lost_and_found_job_count;    /* incremented during persist_recover() */
 } cluster_t;
 
 #endif /* XCE_CLUSTER_DEF_H */