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

feat(scheduler-core): implement scheduler-side admin request handler (task 9.4)

Browse source 
Implements the scheduler's first request-reply opcode (OPCode_schedAdmin).
sched_handle_admin_request() (handler.c) decodes SchedAdminRequest and
dispatches by action: recordStatus answers synchronously (pure read);
recordStart/recordStop are deferred onto the existing pend_updates queue
(XCE_SCHED_OP_ADMIN_RECORD) since sched_record_start()'s snapshot call
requires the session_active==0 precondition only guaranteed on the driver
thread, not the async request-handling thread. driver.c's
xce_sched_driver_translate_pending_events() performs the deferred action
and sends the reply via a new xcecli_reply_schedadmin() (client.c/client.h),
correlated by seq copied before the original request is freed.

Adversarial review found a genuine cross-thread race: sched_record_status()
read driver-owned recording state (including a pointer the driver thread
frees) from the vtask thread with no lock -- the codebase's first such
race, missed by ASan (doesn't detect races). Fixed with a dedicated
record_lock scoped strictly to in-memory field access, never spanning file
I/O; sched_record_status() now strdup()s under the lock instead of
returning a borrowed live pointer. Verified with a real two-thread
lock-contention test (independently confirmed non-vacuous by removing the
lock and observing the test fail) plus a deterministic use-after-free
reproduction.

26/26 scheduler suite, clang-format clean.
This commit is contained in:
Rongsong Shen 2026-08-05 14:11:43 +00:00
parent 7494542a60
commit e819a50600
Signed by: rshen
SSH key fingerprint: SHA256:8Vf2pZ3h6rJa7EhGK+WaAQ9Mta/apZvteW6g9U/WKKk
19 changed files with 1761 additions and 115 deletions
Download patch file Download diff file Expand all files Collapse all files

40
src/scheduler/testsuite/test_handlers.c
View file

@ -27,14 +27,30 @@
* test_job_array_expand.c for the real kvmgr-backed sched_get_job). */
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_get_job relocated to core.h (scheduler-core spec, task 4.1) -- now
* operates on xce_sched_core_t*, not xce_scheduler_t*. */
xce_sched_job_t* sched_get_job(xce_sched_core_t* sched, uint64_t jobid)
{
(void)sched; (void)jobid; return NULL;
(void)sched;
(void)jobid;
return NULL;
}
/* 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 (its own scope is notify/dataset
* enqueue), 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;
}
#include "../src/handler.c"
@ -118,8 +134,7 @@ static void test_handle_job_rusage_enqueues_rusage(void)
xce_sched_op_t op = (xce_sched_op_t)-1;
fixture_init(&sched);
TEST_ASSERT_EQUAL_INT(-EINVAL,
sched_handle_sched_job_rusage(&sched, NULL));
TEST_ASSERT_EQUAL_INT(-EINVAL, sched_handle_sched_job_rusage(&sched, NULL));
xce_job_rusages_t* ru = (xce_job_rusages_t*)calloc(1, sizeof(*ru));
ru->jobid = 7;
@ -132,20 +147,18 @@ static void test_handle_job_rusage_enqueues_rusage(void)
static void test_handle_update_resvals_skips_empty_enqueues_nonempty(void)
{
xce_scheduler_t sched;
xce_sched_op_t op = (xce_sched_op_t)-1;
xce_sched_op_t op = (xce_sched_op_t)-1;
xce_resval_list_t empty = { .count = 0, .vals = NULL };
xce_resval_list_t full = { .count = 1, .vals = NULL };
fixture_init(&sched);
/* NULL or count==0 -> skip (return 0, nothing enqueued) */
TEST_ASSERT_EQUAL_INT(0, sched_handle_sched_update_resvals(&sched, NULL));
TEST_ASSERT_EQUAL_INT(0,
sched_handle_sched_update_resvals(&sched, &empty));
TEST_ASSERT_EQUAL_INT(0, sched_handle_sched_update_resvals(&sched, &empty));
TEST_ASSERT_EQUAL_INT(0, pop_op(&sched, NULL));
/* count>0 -> enqueue UPDATE_RESVALS */
TEST_ASSERT_EQUAL_INT(0,
sched_handle_sched_update_resvals(&sched, &full));
TEST_ASSERT_EQUAL_INT(0, sched_handle_sched_update_resvals(&sched, &full));
TEST_ASSERT_EQUAL_INT(1, pop_op(&sched, &op));
TEST_ASSERT_EQUAL_INT(XCE_SCHED_OP_UPDATE_RESVALS, op);
}
@ -154,9 +167,9 @@ static void test_handle_update_resvals_skips_empty_enqueues_nonempty(void)
static void test_handle_resources_skips_empty_enqueues_nonempty(void)
{
xce_scheduler_t sched;
xce_sched_op_t op = (xce_sched_op_t)-1;
xce_resource_t* one[1];
xce_scheduler_t sched;
xce_sched_op_t op = (xce_sched_op_t)-1;
xce_resource_t* one[1];
fixture_init(&sched);
TEST_ASSERT_EQUAL_INT(0, sched_handle_resources(&sched, 0, NULL));
@ -188,7 +201,8 @@ static void test_handle_resvals_full_skips_empty_enqueues_nonempty(void)
int main(int argc, char* argv[])
{
(void)argc; (void)argv;
(void)argc;
(void)argv;
UNITY_BEGIN();
RUN_TEST(test_handle_update_job_enqueues_job_fields, 0);
RUN_TEST(test_handle_update_queue_enqueues_queue, 0);