refactor(ha): passive standby model — primary connects outbound to all peers
Remove fetch_config_from_primary, ha_find_and_connect_to_primary, and the tier-1/2/3 discovery path. Standbys never initiate outbound connections to the primary; the primary owns all inter-controller channels. Key changes: - ha.c: add primary heartbeat loop (ha_start_primary_heartbeat) that sends OPCode_nop to connected standbys every heartbeat_interval_ms; loop self-cancels on demotion via role check before re-arm. - ha.c: add outbound reconnect in primary_heartbeat_fn — for peers absent from standby_endpoints, open fresh outbound TLS connection (on_standby_connected sends ctrlhello; standby_ep_ctx_t mirrors vote_ep_ctx_t layout). - ha.c: remove ha_find_and_connect_to_primary + helpers (ha_raw_tcp_connect, ha_tcp_connect_hook); remove election_timeout_fn (superseded by raft_election_timeout_fn); remove fetch_config_from_primary call from ha_elect_evaluate_and_signal STANDBY branch. - cluster.c: OPCode_requestVote denial no longer reuses inbound connection; late joiners are bootstrapped via primary heartbeat outbound connect. - config_repl.c: remove connect_ssl_raw, do_one_config_fetch, fetch_config_from_primary (~250 LOC). - myapp.c: remove my_tag > 0 fetch branch; all standbys wait passively. - ha.h: remove ha_find_and_connect_to_primary declaration + macros + ha_tcp_connect_hook seam; add ha_start_primary_heartbeat declaration. - meson.build: remove test_ha_connect.c (tests deleted function). - controller_test.c: remove test_ha_connect registration. - CLAUDE.md, src/controller/CLAUDE.md: document passive standby model, inbound-vs-outbound connection ownership, async I/O constraint, heartbeat model. - request.h: add xce_request declaration (removes scattered local externs).
This commit is contained in:
parent
842b9a838e
commit
7b39650229
11 changed files with 716 additions and 919 deletions
|
|
@ -67,15 +67,19 @@ typedef enum {
|
|||
* 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 */
|
||||
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;
|
||||
|
||||
/*
|
||||
|
|
@ -433,6 +437,16 @@ 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 ────────────────────── */
|
||||
|
||||
/*
|
||||
|
|
@ -458,31 +472,6 @@ void ha_start_election_async(ha_state_t *ha, cluster_t *c,
|
|||
uint64_t my_config_tag, uint64_t my_lsn,
|
||||
const char *my_name);
|
||||
|
||||
/* ── Task 9.2: Persistent Control Channel (Req 6.1) ───────────────────────── */
|
||||
|
||||
/*
|
||||
* ha_find_and_connect_to_primary: three-tier primary discovery and raw TCP connect.
|
||||
*
|
||||
* Tier 1: ha->voted_for_name non-empty → direct connect to that candidate.
|
||||
* Backoff HA_FIND_PRIMARY_T1_BACKOFF_MS; retry HA_FIND_PRIMARY_T1_MAX_RETRIES.
|
||||
* Tier 2: probe remaining candidates; follow XCE_ERR_STANDBY redirect.
|
||||
* Tier 3: blind scan with 100ms→5s exponential backoff (no exit until success).
|
||||
*
|
||||
* On success: sets ha->primary_ctrl_fd; when c != NULL, registers fd with
|
||||
* c->iomgr.epoll_fd for EPOLLIN|EPOLLRDHUP. Returns fd >= 0.
|
||||
* Pass c == NULL to skip iomgr registration (unit test mode).
|
||||
* Requirements: 6.1
|
||||
*/
|
||||
int ha_find_and_connect_to_primary(ha_state_t *ha,
|
||||
const ha_config_t *cfg,
|
||||
const xce_cluster_config_t *peers,
|
||||
cluster_t *c);
|
||||
|
||||
#define HA_FIND_PRIMARY_T1_MAX_RETRIES 3
|
||||
#define HA_FIND_PRIMARY_T1_BACKOFF_MS 200
|
||||
#define HA_FIND_PRIMARY_T3_INIT_MS 100
|
||||
#define HA_FIND_PRIMARY_T3_MAX_MS 5000
|
||||
|
||||
/*
|
||||
* ha_repl_ack_received: called when a standby ACKs config+WAL catch-up
|
||||
* (OPCode_replCatchUpDone). Increments repl_ack_count; when majority
|
||||
|
|
@ -502,6 +491,7 @@ 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
|
||||
|
|
@ -525,6 +515,17 @@ extern int (*ha_send_ctrlhello_hook)(void *c);
|
|||
*/
|
||||
extern int (*ha_push_config_hook)(void *c);
|
||||
|
||||
/*
|
||||
* 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
|
||||
|
|
@ -532,13 +533,6 @@ extern int (*ha_push_config_hook)(void *c);
|
|||
*/
|
||||
uint64_t ha_trigger_manual_failover_for_test(ha_state_t *ha);
|
||||
|
||||
/*
|
||||
* ha_tcp_connect_hook: test-only seam for TCP connections.
|
||||
* When non-NULL, ha_find_and_connect_to_primary() calls this instead of
|
||||
* the real connect() path. Returns connected fd on success, -errno on failure.
|
||||
*/
|
||||
extern int (*ha_tcp_connect_hook)(const char *host, int port);
|
||||
|
||||
/*
|
||||
* ha_rdhup_election_hook: test-only seam for ha_start_election_async in the
|
||||
* RDHUP failover path.
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue