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

feat: implement real am_i_primary() with election probing, ha_is_primary(), ha_check_priority_stepdown()

Browse source 
- Replace stub am_i_primary() with real election probe logic
- probe_thread(): non-blocking TCP connect with optional SSL handshake
- wait_any_probe(): deadline-based spin-poll across all probe threads
- am_i_primary(): priority-0 always primary; higher priorities probe
  lower-priority peers and self-promote if deadline expires
- ha_is_primary(): lock-free role check
- ha_check_priority_stepdown(): simultaneous-boot stepdown at term=0
- start/stop_heartbeat_listener(): stubs for Task 7
- ha_init(): explicit initialization of ssl_ctx/jitter_seed/standby_endpoints
- TDD: add test_am_i_primary suite with 3 tests covering p0/p1 paths
This commit is contained in:
Rongsong Shen 2026-05-13 16:39:59 +00:00
parent 8d86a1bcfe
commit fe3cc57f27
3 changed files with 337 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/controller/testsuite/controller_test.c
View file

@ -20,6 +20,7 @@ extern void test_e2e_hooks(void);
extern void test_e2e_gc(void);
extern void test_e2e_capnp(void);
extern void test_ha_role(void);
extern void test_am_i_primary(void);
extern void test_ha_cluster(void);
extern void test_ha_redirect(void);
extern void test_p1_integration(void);
@ -121,6 +122,7 @@ int main(int argc, char* argv[])
TEST(test_e2e_gc);
TEST(test_e2e_capnp);
TEST(test_ha_role);
TEST(test_am_i_primary);
TEST(test_ha_cluster);
TEST(test_ha_redirect);
TEST(test_p1_integration);

97
src/controller/testsuite/test_ha_role.c
View file

@ -7,6 +7,8 @@
#include <unity/unity.h>
#include "ha.h"
#include "myconf.h"
#include "xce/cluster_def.h"
static void test_ha_init_default_role_is_standby(void)
{
@ -232,6 +234,92 @@ static void test_sigusr1_sets_failover_requested(void)
printf("test_sigusr1_sets_failover_requested: PASS\n");
}
/* ── P1-6: am_i_primary() election tests ────────────────────────────── */
/* test: priority-0 with no peers → immediately primary (no probing needed) */
void test_am_i_primary_p0_no_peers(void)
{
cluster_t c;
memset(&c, 0, sizeof(c));
myconf_t myconf;
memset(&myconf, 0, sizeof(myconf));
c.myconf = &myconf;
ha_config_t cfg = {
.heartbeat_interval_ms = HA_DEFAULT_HEARTBEAT_INTERVAL_MS,
.heartbeat_timeout_ms = HA_DEFAULT_HEARTBEAT_TIMEOUT_MS,
.election_timeout_ms = 500, /* minimum valid value */
.probe_connect_timeout_ms = 100,
.max_promotion_retries = 1,
.election_jitter_max_ms = 0,
.election_priority_step_ms = 0,
};
TEST_ASSERT_EQUAL_INT(0, ha_init(&c.ha, &cfg, 0));
TEST_ASSERT_EQUAL_INT(1, am_i_primary(&c));
ha_fini(&c.ha);
printf("test_am_i_primary_p0_no_peers: PASS\n");
}
/* test: priority-0 with peers → still primary (never probes higher-priority nodes) */
void test_am_i_primary_p0_with_peers(void)
{
cluster_t c;
memset(&c, 0, sizeof(c));
myconf_t myconf;
memset(&myconf, 0, sizeof(myconf));
myconf.peers_cfg.candidates_count = 2;
strncpy(myconf.peers_cfg.candidates[0].hostname, "127.0.0.1", XCE_MAXNAME_LEN - 1);
myconf.peers_cfg.candidates[0].port = 19900;
strncpy(myconf.peers_cfg.candidates[1].hostname, "127.0.0.1", XCE_MAXNAME_LEN - 1);
myconf.peers_cfg.candidates[1].port = 19901;
c.myconf = &myconf;
ha_config_t cfg = {
.heartbeat_interval_ms = HA_DEFAULT_HEARTBEAT_INTERVAL_MS,
.heartbeat_timeout_ms = HA_DEFAULT_HEARTBEAT_TIMEOUT_MS,
.election_timeout_ms = 500, /* minimum valid value */
.probe_connect_timeout_ms = 100,
.max_promotion_retries = 1,
.election_jitter_max_ms = 0,
.election_priority_step_ms = 0,
};
TEST_ASSERT_EQUAL_INT(0, ha_init(&c.ha, &cfg, 0));
TEST_ASSERT_EQUAL_INT(1, am_i_primary(&c));
ha_fini(&c.ha);
printf("test_am_i_primary_p0_with_peers: PASS\n");
}
/* test: priority-1 with no higher-priority peer alive → deadline expires → primary */
void test_am_i_primary_p1_deadline_expires(void)
{
cluster_t c;
memset(&c, 0, sizeof(c));
myconf_t myconf;
memset(&myconf, 0, sizeof(myconf));
/* Point to ports where nothing is listening */
myconf.peers_cfg.candidates_count = 2;
strncpy(myconf.peers_cfg.candidates[0].hostname, "127.0.0.1", XCE_MAXNAME_LEN - 1);
myconf.peers_cfg.candidates[0].port = 19910; /* nothing listening */
strncpy(myconf.peers_cfg.candidates[1].hostname, "127.0.0.1", XCE_MAXNAME_LEN - 1);
myconf.peers_cfg.candidates[1].port = 19911;
c.myconf = &myconf;
ha_config_t cfg = {
.heartbeat_interval_ms = HA_DEFAULT_HEARTBEAT_INTERVAL_MS,
.heartbeat_timeout_ms = HA_DEFAULT_HEARTBEAT_TIMEOUT_MS,
.election_timeout_ms = 600, /* expires quickly; > 500ms floor */
.probe_connect_timeout_ms = 200,
.max_promotion_retries = 1,
.election_jitter_max_ms = 0,
.election_priority_step_ms = 0,
};
TEST_ASSERT_EQUAL_INT(0, ha_init(&c.ha, &cfg, 1)); /* priority 1 — must probe priority 0 */
int result = am_i_primary(&c);
TEST_ASSERT_EQUAL_INT(1, result); /* no peer responded → self-declare primary */
ha_fini(&c.ha);
printf("test_am_i_primary_p1_deadline_expires: PASS\n");
}
void test_ha_role(void)
{
RUN_TEST(test_ha_init_default_role_is_standby);
@ -247,3 +335,12 @@ void test_ha_role(void)
RUN_TEST(test_demote_sets_standby_role);
RUN_TEST(test_sigusr1_sets_failover_requested);
}
/* ── P1-6 suite: am_i_primary() election ─────────────────────────────── */
void test_am_i_primary(void)
{
RUN_TEST(test_am_i_primary_p0_no_peers);
RUN_TEST(test_am_i_primary_p0_with_peers);
RUN_TEST(test_am_i_primary_p1_deadline_expires);
}