merge: sync Rongsong's scheduler-framework into chatbot
Full merge of origin/scheduler-framework (scheduler-core restructure,
failover-adoption, WAL_JOB_DISPATCH, apiserver backend health/heartbeat,
build-time versioning, bug-1673/1676/1678/1679/1680).
Conflict resolution:
- scheduler: adopt Rongsong's scheduler-core architecture (driver loop,
queue project/picker fields, resource bug-1569 fix)
- worker/controller_connector.c: keep Rongsong's reconnect/rejoin
structure, PORT our bug-1509 resend_job_status onto the rejoin success
path (his reconnect didn't re-report job state)
- apiserver backend: take Rongsong's health/heartbeat (supersedes our
e505066 circuit breaker)
- group.c: keep our bug-1513 comment
- misc: take theirs for additive fixes (go_build versioning,
test_group.c, persist.c RUSAGE_UPDATE, FilterRows bug-1680)
NOTE: our scheduler fixes (bug-1494 family dispatch-fail requeue,
PEND-reason classification) are NOT in Rongsong's branch — needs
verification/porting onto scheduler-core (separate follow-up).
Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
lei.chen
commit
4e894d2184
395 changed files with 88517 additions and 5742 deletions
|
|
@ -29,27 +29,42 @@
|
|||
|
||||
int sched_init_config(xce_scheduler_t* s, xce_conf4sched_t* c)
|
||||
{
|
||||
(void)s; (void)c; return 0;
|
||||
(void)s;
|
||||
(void)c;
|
||||
return 0;
|
||||
}
|
||||
|
||||
/* sched_record_status (recording.c, scheduler-core spec, task 9.4) --
|
||||
* handler.c's OPCode_schedAdmin/recordStatus path references it; this file
|
||||
* never exercises OPCode_schedAdmin, so a link-satisfying stub is enough,
|
||||
* same rationale as sched_init_config above. */
|
||||
int sched_record_status(xce_scheduler_t* sched, sched_admin_reply_t* reply)
|
||||
{
|
||||
(void)sched;
|
||||
(void)reply;
|
||||
return -EINVAL;
|
||||
}
|
||||
|
||||
/* REAL kvmgr-backed job add/get -- same rtti path production uses (mirrors
|
||||
* test_job_update.c's precedent for exercising sched_get_job "for real"). */
|
||||
int sched_add_job(xce_scheduler_t* sched, xce_sched_job_t* j)
|
||||
* test_job_update.c's precedent for exercising sched_get_job "for real").
|
||||
* Relocated to core.h (scheduler-core spec, task 4.1) -- now operate on
|
||||
* xce_sched_core_t*, not xce_scheduler_t*. */
|
||||
int sched_add_job(xce_sched_core_t* core, xce_sched_job_t* j)
|
||||
{
|
||||
int rc;
|
||||
lock(sched->jobs, RTTI_LOCK_WRITE);
|
||||
rc = key_add(sched->jobs, (void*)j->jobid, j);
|
||||
unlock(sched->jobs);
|
||||
lock(core->jobs, RTTI_LOCK_WRITE);
|
||||
rc = key_add(core->jobs, (void*)j->jobid, j);
|
||||
unlock(core->jobs);
|
||||
return rc;
|
||||
}
|
||||
|
||||
xce_sched_job_t* sched_get_job(xce_scheduler_t* sched, uint64_t jobid)
|
||||
xce_sched_job_t* sched_get_job(xce_sched_core_t* core, uint64_t jobid)
|
||||
{
|
||||
int rc;
|
||||
xce_sched_job_t* job = NULL;
|
||||
lock(sched->jobs, RTTI_LOCK_READ);
|
||||
rc = key_find(sched->jobs, (void*)jobid, (void**)&job);
|
||||
unlock(sched->jobs);
|
||||
lock(core->jobs, RTTI_LOCK_READ);
|
||||
rc = key_find(core->jobs, (void*)jobid, (void**)&job);
|
||||
unlock(core->jobs);
|
||||
if (rc <= 0) {
|
||||
return NULL;
|
||||
}
|
||||
|
|
@ -83,19 +98,19 @@ static void fixture_init(xce_scheduler_t* sched)
|
|||
.datakiller = NULL };
|
||||
|
||||
memset(sched, 0, sizeof(*sched));
|
||||
mylock_init(&(sched->lock));
|
||||
sched->pend_updates[0] = (dataq_t*)calloc(1, sizeof(dataq_t));
|
||||
dataq_init(sched->pend_updates[0], NULL);
|
||||
sched->pend_updates[1] = (dataq_t*)calloc(1, sizeof(dataq_t));
|
||||
dataq_init(sched->pend_updates[1], NULL);
|
||||
sched->jobs = makeInstance(&xkvmgr_type, &jobs_params);
|
||||
mylock_init(&(sched->core.lock));
|
||||
sched->core.pend_updates[0] = (dataq_t*)calloc(1, sizeof(dataq_t));
|
||||
dataq_init(sched->core.pend_updates[0], NULL);
|
||||
sched->core.pend_updates[1] = (dataq_t*)calloc(1, sizeof(dataq_t));
|
||||
dataq_init(sched->core.pend_updates[1], NULL);
|
||||
sched->core.jobs = makeInstance(&xkvmgr_type, &jobs_params);
|
||||
}
|
||||
|
||||
static void seed_existing_job(xce_scheduler_t* sched, uint64_t jobid)
|
||||
{
|
||||
xce_sched_job_t* job = (xce_sched_job_t*)calloc(1, sizeof(*job));
|
||||
job->jobid = jobid;
|
||||
sched_add_job(sched, job);
|
||||
job->jobid = jobid;
|
||||
sched_add_job(&(sched->core), job);
|
||||
}
|
||||
|
||||
/* Builds a heap-allocated, heap-owned-strings (jobArray, submit) pair -- the
|
||||
|
|
@ -109,9 +124,8 @@ static void seed_existing_job(xce_scheduler_t* sched, uint64_t jobid)
|
|||
static xce_job_submit_t* init_job_array(uint64_t base_jobid,
|
||||
uint64_t array_size)
|
||||
{
|
||||
job_submit_data_t* submit
|
||||
= (job_submit_data_t*)calloc(1, sizeof(*submit));
|
||||
xce_job_submit_t* ja = (xce_job_submit_t*)calloc(1, sizeof(*ja));
|
||||
job_submit_data_t* submit = (job_submit_data_t*)calloc(1, sizeof(*submit));
|
||||
xce_job_submit_t* ja = (xce_job_submit_t*)calloc(1, sizeof(*ja));
|
||||
|
||||
submit->queue = strdup("normal");
|
||||
submit->user = strdup("tester");
|
||||
|
|
@ -131,7 +145,7 @@ static xce_job_submit_t* init_job_array(uint64_t base_jobid,
|
|||
* mirror sched_pend_update_killer). Returns -1 if the queue is empty. */
|
||||
static int pop_job_update(xce_scheduler_t* sched, xce_job_t*** jobs_out)
|
||||
{
|
||||
data_item_t* it = dataq_deq(sched->pend_updates[0], NULL);
|
||||
data_item_t* it = dataq_deq(sched->core.pend_updates[0], NULL);
|
||||
xce_sched_update_request_t* req;
|
||||
int njobs;
|
||||
|
||||
|
|
@ -155,12 +169,12 @@ static int pop_job_update(xce_scheduler_t* sched, xce_job_t*** jobs_out)
|
|||
|
||||
static void test_job_array_push_expands_into_n_tasks(void)
|
||||
{
|
||||
xce_scheduler_t sched;
|
||||
xce_job_submit_t* ja;
|
||||
dataset_t dataset;
|
||||
xce_job_t** jobs = NULL;
|
||||
int njobs;
|
||||
int i;
|
||||
xce_scheduler_t sched;
|
||||
xce_job_submit_t* ja;
|
||||
dataset_t dataset;
|
||||
xce_job_t** jobs = NULL;
|
||||
int njobs;
|
||||
int i;
|
||||
|
||||
fixture_init(&sched);
|
||||
ja = init_job_array(5000, 3);
|
||||
|
|
@ -198,11 +212,11 @@ static void test_job_array_push_expands_into_n_tasks(void)
|
|||
|
||||
static void test_job_array_redelivery_does_not_duplicate(void)
|
||||
{
|
||||
xce_scheduler_t sched;
|
||||
dataset_t dataset;
|
||||
xce_job_t** jobs = NULL;
|
||||
int njobs;
|
||||
int i;
|
||||
xce_scheduler_t sched;
|
||||
dataset_t dataset;
|
||||
xce_job_t** jobs = NULL;
|
||||
int njobs;
|
||||
int i;
|
||||
|
||||
fixture_init(&sched);
|
||||
|
||||
|
|
@ -299,9 +313,9 @@ static void test_wire_dispatch_chain_delivers_n_tasks(void)
|
|||
xce_data_t data;
|
||||
xce_request_t request;
|
||||
xce_request_t decoded;
|
||||
io_packet_t *pkt;
|
||||
io_packet_t* pkt;
|
||||
dataset_t dataset;
|
||||
xce_job_t **jobs = NULL;
|
||||
xce_job_t** jobs = NULL;
|
||||
int njobs;
|
||||
int i;
|
||||
|
||||
|
|
@ -329,12 +343,13 @@ static void test_wire_dispatch_chain_delivers_n_tasks(void)
|
|||
request.body_which = Request_body_pushmsg;
|
||||
request.body.pushmsg = &data;
|
||||
|
||||
pkt = (io_packet_t *)calloc(1, sizeof(*pkt));
|
||||
pkt = (io_packet_t*)calloc(1, sizeof(*pkt));
|
||||
TEST_ASSERT_NOT_NULL(pkt);
|
||||
TEST_ASSERT_EQUAL_INT(1, xce_encode(&request, pkt));
|
||||
|
||||
memset(&decoded, 0, sizeof(decoded));
|
||||
TEST_ASSERT_EQUAL_INT(0, xce_decode(pkt, &decoded)); /* consumes/frees pkt */
|
||||
TEST_ASSERT_EQUAL_INT(0,
|
||||
xce_decode(pkt, &decoded)); /* consumes/frees pkt */
|
||||
|
||||
/* Act 1: the REAL transport dispatcher (task 5.3b's fix) -- exactly what
|
||||
* vtask_entry() (xcectx.c) calls on every inbound push. */
|
||||
|
|
@ -374,7 +389,8 @@ static void test_wire_dispatch_chain_delivers_n_tasks(void)
|
|||
|
||||
int main(int argc, char* argv[])
|
||||
{
|
||||
(void)argc; (void)argv;
|
||||
(void)argc;
|
||||
(void)argv;
|
||||
UNITY_BEGIN();
|
||||
RUN_TEST(test_job_array_push_expands_into_n_tasks, 0);
|
||||
RUN_TEST(test_job_array_redelivery_does_not_duplicate, 0);
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue