Rongsong Shen
a289edb777
- Full ha.h: ctrl_role_t enum (CTRL_PRIMARY/CTRL_STANDBY), ha_config_t, ha_state_t with _Atomic fields (term, role, applied_lsn, promotion counters, watchdog_stop), pthread_mutex_t lock, and public API. - endpoint_t* omitted from ha_state_t — including netio.h would pull OpenSSL headers and risk circular deps; watchdog (P1-3) includes netio.h directly where needed. - ha_init validates: heartbeat_interval_ms >= 2000, heartbeat_timeout_ms >= heartbeat_interval_ms, election_timeout_ms >= 500; returns -EINVAL on bad config; zeros struct and sets initial role to CTRL_STANDBY. - ha_fini destroys mutex; watchdog thread join deferred to P1-3. - am_i_primary / ha_promote_to_primary / ha_demote_to_standby are no-op stubs; cluster_t->ha field not yet wired (P1-5), so these avoid incomplete-type dereferences until then. - TDD: 5 new tests in test_ha_role.c confirmed RED before implementation, all 5 GREEN after; all prior controller tests remain green.
100 lines
4.4 KiB
C
100 lines
4.4 KiB
C
#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 <pthread.h>
|
|
#include <stdatomic.h>
|
|
#include <stdint.h>
|
|
#include <time.h>
|
|
|
|
#include "config.h" /* XCE_MAXNAME_LEN, MAX_STANDBYS, etc. */
|
|
|
|
/* Forward declaration — avoids circular include with cluster_def.h */
|
|
typedef struct cluster_s cluster_t;
|
|
|
|
/* ── Role enum ─────────────────────────────────────────────── */
|
|
typedef enum {
|
|
CTRL_PRIMARY = 0,
|
|
CTRL_STANDBY = 1
|
|
} ctrl_role_t;
|
|
|
|
/* ── HA configuration ──────────────────────────────────────── */
|
|
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 */
|
|
} ha_config_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 */
|
|
_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 */
|
|
struct timespec last_heartbeat; /* CLOCK_MONOTONIC timestamp of last heartbeat */
|
|
_Atomic int promotion_failed;
|
|
_Atomic int promotion_retry_count;
|
|
_Atomic int in_catch_up; /* Non-zero while processing historical WAL entries */
|
|
_Atomic int failover_requested; /* Set by SIGUSR1 handler; watchdog executes */
|
|
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 + last_heartbeat */
|
|
/* Watchdog thread — started in P1-3 */
|
|
_Atomic int watchdog_stop;
|
|
pthread_t watchdog_thread;
|
|
} 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: stub — priority-0 node is primary.
|
|
* Full election probing added in P1-3.
|
|
*/
|
|
int am_i_primary(cluster_t *c);
|
|
|
|
/*
|
|
* 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);
|
|
|
|
#endif /* HA_H */
|