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

refactor(ha-repl-hardening): standardize n_peers = total cluster size including self

Browse source 
- ha_state_t.n_peers now matches raft_config_t.n_peers convention:
  total cluster size (including self), consistently across both layers
- ha_start_election_async: ha->n_peers = n_peers (candidates_count)
- Convergence/counting loops: i < n_peers - 1 (skip self for standby arrays)
- Single-node: n_peers=1, threshold=0 (same behavior, clear semantics)
- ha_elect_ctx_t.n_peers unchanged (separate field for vote array sizing)
- Tests: 3-node n_peers=2->3, single-node 0->1, loop bounds updated

E2E test 6.7: 3-node cluster lifecycle verified
- Initial: ctrl-1 PRIMARY via majority convergence, no degraded mode
- Kill primary: RDHUP detected on both standbys, ctrl-2 elected at term=4
- No data loss: config tag preserved across failover
- Full ASAN build green
This commit is contained in:
Rongsong Shen 2026-06-05 09:57:23 +00:00
parent 361397ac02
commit f236d320a2
4 changed files with 71 additions and 31 deletions
Download patch file Download diff file Expand all files Collapse all files

19
src/controller/testsuite/test_ha_role.c
View file

@ -383,8 +383,9 @@ static void test_process_standby_state_multiple_peers(void)
* count the number of converged standbys and promote to CTRL_PRIMARY when the
* majority threshold is met and the current role is CTRL_PRIMARY_COMMITTING.
*
* Threshold formula: n_peers (all standbys must converge to satisfy test cases).
* Single-node (n_peers=0): threshold=0 → satisfied immediately.
* Threshold formula: n_peers - 1 (all standbys must converge).
* Single-node (n_peers=1): threshold=0 → satisfied immediately (matches raft convention).
* n_peers = total cluster size including self.
*
* Requirements: 2.3, 2.4, 6.1, 6.3, 6.5 (ha-repl-hardening)
*/
@ -411,7 +412,7 @@ static void test_majority_convergence_3node_one_standby_stays_committing(void)
.committing_timeout_ms = HA_DEFAULT_COMMITTING_TIMEOUT_MS,
};
ha_init(&c.ha, &cfg, 0);
c.ha.n_peers = 2; /* 3-node cluster: primary + 2 standbys */
c.ha.n_peers = 3; /* 3-node cluster: primary + 2 standbys */
atomic_store_explicit(&c.ha.role, (int32_t)CTRL_PRIMARY_COMMITTING,
memory_order_release);
@ -451,7 +452,7 @@ static void test_majority_convergence_3node_all_standbys_promotes(void)
.committing_timeout_ms = HA_DEFAULT_COMMITTING_TIMEOUT_MS,
};
ha_init(&c.ha, &cfg, 0);
c.ha.n_peers = 2; /* 3-node cluster */
c.ha.n_peers = 3; /* 3-node cluster */
atomic_store_explicit(&c.ha.role, (int32_t)CTRL_PRIMARY_COMMITTING,
memory_order_release);
@ -491,7 +492,7 @@ static void test_majority_convergence_single_node_immediate(void)
.committing_timeout_ms = HA_DEFAULT_COMMITTING_TIMEOUT_MS,
};
ha_init(&c.ha, &cfg, 0);
c.ha.n_peers = 0; /* single-node: no standbys */
c.ha.n_peers = 1; /* single-node: just self */
atomic_store_explicit(&c.ha.role, (int32_t)CTRL_PRIMARY_COMMITTING,
memory_order_release);
@ -500,7 +501,7 @@ static void test_majority_convergence_single_node_immediate(void)
int role = (int)atomic_load_explicit(&c.ha.role, memory_order_acquire);
TEST_ASSERT_EQUAL_INT_MESSAGE((int)CTRL_PRIMARY, role,
"single-node: n_peers=0 → threshold=0 satisfied → must promote to CTRL_PRIMARY (Req 6.5)");
"single-node: n_peers=1 → threshold=0 satisfied → must promote to CTRL_PRIMARY (Req 6.5)");
ha_fini(&c.ha);
printf("test_majority_convergence_single_node_immediate: PASS\n");
@ -839,7 +840,7 @@ static void test_committing_timeout_promotes_degraded_with_partial_convergence(v
.committing_timeout_ms = HA_DEFAULT_COMMITTING_TIMEOUT_MS,
};
ha_init(&c.ha, &cfg, 0);
c.ha.n_peers = 2; /* 3-node cluster; 2 standbys */
c.ha.n_peers = 3; /* 3-node cluster; 2 standbys */
atomic_store_explicit(&c.ha.role, (int32_t)CTRL_PRIMARY_COMMITTING,
memory_order_release);
@ -853,7 +854,7 @@ static void test_committing_timeout_promotes_degraded_with_partial_convergence(v
*/
int n_converged = 0;
int n_pending = 0;
for (int i = 0; i < c.ha.n_peers; i++) {
for (int i = 0; i < c.ha.n_peers - 1; i++) {
if (c.ha.standby_converged[i])
n_converged++;
else
@ -898,7 +899,7 @@ static void test_committing_timeout_promotes_degraded_zero_converged(void)
.committing_timeout_ms = HA_DEFAULT_COMMITTING_TIMEOUT_MS,
};
ha_init(&c.ha, &cfg, 0);
c.ha.n_peers = 2; /* 3-node cluster; all standbys unreachable */
c.ha.n_peers = 3; /* 3-node cluster; all standbys unreachable */
atomic_store_explicit(&c.ha.role, (int32_t)CTRL_PRIMARY_COMMITTING,
memory_order_release);