feat: ha_should_redirect + join.c HA redirect/nomaster guard (P1-6)
Add redirect helpers to ha.c/ha.h so a standby controller never accepts join requests as if it were the primary: - ha_should_redirect(): returns 1 when role is STANDBY and primary_host/port are known — caller should send E_XCE_REDIRECT. - ha_no_primary_known(): returns 1 when role is STANDBY but primary address is not yet known — caller should send E_XCE_NOMASTER (retry later). - Add E_XCE_NOMASTER and E_XCE_REDIRECT to errnox.h. - Wire both guards into handle_join_() in join.c (before the role switch) so all join types (worker, scheduler, apiserver, client) are protected. - Full redirect response sends status=-E_XCE_REDIRECT with nodata body; the primary host:port are logged so operators can trace misrouted clients. Full Cap'n Proto RedirectInfo response body is deferred to a follow-up (schema union would require regenerating capnp bindings). 5 new TDD tests — 110 total, 0 failures.
This commit is contained in:
parent
c627f69d50
commit
f5b0ac0af3
7 changed files with 191 additions and 0 deletions
|
|
@ -186,6 +186,38 @@ void ha_fini(ha_state_t *ha)
|
|||
pthread_mutex_destroy(&ha->lock);
|
||||
}
|
||||
|
||||
/* ── P1-6: Redirect helpers ────────────────────────────────── */
|
||||
|
||||
/*
|
||||
* ha_should_redirect: returns 1 when this standby knows the primary's
|
||||
* address and should redirect incoming join requests there.
|
||||
* Returns 0 for PRIMARY role, or for STANDBY with no known primary yet.
|
||||
*/
|
||||
int ha_should_redirect(const ha_state_t *ha)
|
||||
{
|
||||
ctrl_role_t role =
|
||||
(ctrl_role_t)atomic_load_explicit(&ha->role, memory_order_acquire);
|
||||
if (role == CTRL_PRIMARY)
|
||||
return 0;
|
||||
if (ha->primary_host[0] == '\0' || ha->primary_port == 0)
|
||||
return 0;
|
||||
return 1;
|
||||
}
|
||||
|
||||
/*
|
||||
* ha_no_primary_known: returns 1 when this node is a STANDBY but does not
|
||||
* yet know the primary's address. Callers should reply E_XCE_NOMASTER so
|
||||
* the client retries rather than treating the error as permanent.
|
||||
*/
|
||||
int ha_no_primary_known(const ha_state_t *ha)
|
||||
{
|
||||
ctrl_role_t role =
|
||||
(ctrl_role_t)atomic_load_explicit(&ha->role, memory_order_acquire);
|
||||
if (role == CTRL_PRIMARY)
|
||||
return 0;
|
||||
return (ha->primary_host[0] == '\0' || ha->primary_port == 0) ? 1 : 0;
|
||||
}
|
||||
|
||||
/*
|
||||
* P1-5: cluster_t now embeds ha_state_t ha, so the three functions below
|
||||
* can dereference c->ha.
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue