lei.chen/myxce
1
0
Fork 1
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

chore: checkpoint all prior work for clean state

Browse source 
Captures all uncommitted work from ha-config-bootstrap,
ha-heartbeat-liveness, and associated spec/tooling updates:

- src: ha.c, ha.h, cluster.c, config_repl.c, myapp.c, raft.c —
  heartbeat liveness, RDHUP integration, committing phase fixes
- tests: test_ha_role.c, test_config_repl.c, test_ha_rdhup_integration.c,
  test_p1_integration.c, test_p3_hardening.c, scheduler test
- specs: election-iomgr-refactor, ha-heartbeat-liveness,
  ha-peer-connection-reuse, raft-library (new); ha-config-bootstrap
  and election-iomgr-refactor task/research updates
- tooling: .wolf/ state, ha/data cluster fixtures, raft/raft.tla,
  src/build symlink, xce-build skill update
This commit is contained in:
Rongsong Shen 2026-06-04 13:04:16 +00:00
parent 15bd291bdd
commit e31673dd88
66 changed files with 122422 additions and 860 deletions
Download patch file Download diff file Expand all files Collapse all files

64
src/controller/ha.h
View file

@ -131,14 +131,7 @@ typedef struct {
uint32_t committing_timeout_ms; /* Quorum-ACK deadline for CTRL_PRIMARY_COMMITTING (default 10000) */
} ha_config_t;
typedef struct {
xce_candidate_t *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;
/* 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 {
@ -152,14 +145,12 @@ typedef struct {
_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 */
/* 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 + last_heartbeat */
/* Watchdog thread — started in P1-3 */
_Atomic int watchdog_stop;
pthread_t watchdog_thread;
/* 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 */
@ -183,6 +174,7 @@ typedef struct {
/* ── 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) */
void *committing_timeout_ctx; /* committing_timeout_ctx_t* for cancel on step-down */
/* ── 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 */
} ha_state_t;
@ -201,11 +193,7 @@ int ha_init(ha_state_t *ha, const ha_config_t *cfg, int my_priority);
*/
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);
/* am_i_primary() deleted — replaced by ha_start_election_async (election-iomgr-refactor) */
/*
* ha_promote_to_primary: stub — atomically sets role to PRIMARY.
@ -234,35 +222,6 @@ void ha_do_promote(ha_state_t *ha);
*/
void ha_do_demote(ha_state_t *ha);
/*
* ha_install_sigusr1: register a SIGUSR1 handler that atomically sets
* ha->failover_requested. The handler uses only async-signal-safe operations
* (atomic store on an int-width type — POSIX.1-2017 §2.4.3).
* Must be called once, before any signal can arrive.
*/
void ha_install_sigusr1(ha_state_t *ha);
/* ── Watchdog thread API (P1-3) ────────────────────────────── */
/*
* ha_start_watchdog: spawn the heartbeat watchdog pthread.
* Must be called after ha_init(). Returns 0 on success, -errno on failure.
*/
int ha_start_watchdog(ha_state_t *ha);
/*
* ha_stop_watchdog: set watchdog_stop flag and pthread_join the thread.
* Safe to call if watchdog was never started (thread == 0).
*/
void ha_stop_watchdog(ha_state_t *ha);
/*
* ha_check_heartbeat_nocluster: test-only entry point — logic is inlined in
* ha_watchdog_thread() in production. Only compiled under XCE_TESTING.
*/
#ifdef XCE_TESTING
void ha_check_heartbeat_nocluster(ha_state_t *ha);
#endif
/* ── Redirect helpers used by join.c ──────────────────────── */
@ -289,18 +248,7 @@ int ha_is_primary(const ha_state_t *ha);
/* ha_check_priority_stepdown() deleted — replaced by quorum election (Req 2.1) */
/*
* start_heartbeat_listener: start a minimal pre-Phase-2 SSL listener
* that responds to OP_heartbeat probes. Called after am_i_primary()
* returns 1. Records tid in c->heartbeat_listener_tid.
*/
void start_heartbeat_listener(cluster_t *c);
/*
* stop_heartbeat_listener: signal and join the heartbeat listener thread.
* Must be called before iomgr_init() to free the listening port (EADDRINUSE).
*/
void stop_heartbeat_listener(cluster_t *c);
/* start_heartbeat_listener() / stop_heartbeat_listener() deleted — never called (election-iomgr-refactor) */
/*
* ha_dispatch_gate: role-based operation filter for the vtaskmgr dispatch loop.