E2 Phase 1: external-license-resources — xceesd daemon, extres role, EXTERNAL admission
Implements Phase 1 of .kiro/specs/external-license-resources/ (design.md): externally-reported license pools pushed by a dedicated daemon through the existing resval pipeline, with EXTERNAL-aware admission arithmetic. Wire & controller: - controller.capnp HostRole.extres (@5, appended); xce_join_req accepts it - extres.c: HostRole_extres join table (endpoint+name, no workermgr slot), leave cleanup; join.c/cluster.c dispatch - opupd.c do_update_resvals: extres branch runs the resource hooks and update_resval_list(c, NULL, ...) — host=="" entries route through update_val_res' SHARED branch into c->sharedinst; per-entry -EPERM for non-shared targets is logged, never fails the list - worker.c update_val_res: NULL worker only writes SHARED resources - cluster.c cluster_build_resources: rebuilt on resourceApplyDef (bug-1854) — EEXIST-tolerant so definitions added by an activation register on a RUNNING controller (bug-1973), and RES_APPLY_CHANGED updates definition fields (valtype/ordtype/flags/interval) in place so a corrected config heals a stale registration (bug-1974); seed_sharedinst_from_config skips EXTERNAL pools (daemon-reported free counts only; seeding would fabricate capacity while the daemon is down) Scheduler: - core_events.c RESVALS_DELTA: NULL/"" host marks a SHARED value and lands in core->sharedInst via dup_val (bug-1585 ownership rule), mirroring snapshot_load's host=="" precedent — previously WARN-skipped as unknown worker - resource.c unsatisfy_: EXTERNAL skips the inuse term (F >= uncomit + wanted; F is already net of our checkouts) xceesd (src/esd, new component): - script collectors polled per source, debounce on unchanged values, fail-open stale policy; pushes host=="" shared resvals over xcecli - reconnect gap fix (bug-1975): with a stable value the debounce pushed nothing and reconnects only fire inside a push — after a controller restart the daemon sat on a dead connection forever; the main loop now forces a full re-push when xcecli_is_connection_broken() (bug-1760 predicate) latches Config/mapping: - resources.yaml: extlic sample (location: [external]) - mapping.py: RESOURCE_FLAG_EXTERNAL (0x10) + location:["external"] mapping; xceadmin tests Tests (TDD, red->green per fix): test_extres_resvals.c (join+resval pipeline), test_config_resource_reconcile.c +2 (register past EEXIST / hot-apply changed definition), test_core_events.c +131 lines (shared DELTA landing), mapping tests. Suites: controller 1358/0, scheduler 100/0, esd 7/0, lib 1/0; check-no-fork covers src/esd. Live t1 E2E: config gen=15 push -> xceesd push extlic=4 lands in sharedinst -> rusage[extlic=3] job RUN; second job PENDs at free=1; release re-admits it; controller restart -> forced re-push restores the value and admission resumes. Full precommit job verification passed. Co-Authored-By: Claude Code <noreply@anthropic.com>
This commit is contained in:
parent
ba42fdd82e
commit
2fcacac2cb
33 changed files with 2556 additions and 29 deletions
|
|
@ -730,6 +730,97 @@ test_core_safe_allocation_chain_driver_parity(void)
|
|||
destroy(core_sim->resmgr);
|
||||
}
|
||||
|
||||
/*
|
||||
* external-license-resources Phase 1 (E2), design.md 3.3: the EXTERNAL
|
||||
* accounting rule. An EXTERNAL resource's "total" as pushed by the extres
|
||||
* daemon is already a FREE value F (license server's free count, net of
|
||||
* both external consumers and our own checked-out jobs) -- so re-subtracting
|
||||
* the scheduler's own usage bookkeeping (sharedInUse / w->resInUse) inside
|
||||
* the admission formula would double-count X. The unsatisfy_ loop must
|
||||
* therefore skip the inuse term for resources flagged XCE_RESF_EXTERNAL:
|
||||
*
|
||||
* EXTERNAL: total >= uncomit + wanted
|
||||
* non-EXTERNAL: total >= inuse + uncomit + wanted (unchanged)
|
||||
*
|
||||
* Shared leg (sched_check_shared_satisfy_): a SHARED|EXTERNAL resource with
|
||||
* total=F=4, sharedInUse=3, uncomit=0 must ADMIT wanted=4 (F >= 0+4) even
|
||||
* though the legacy formula (4 < 3+0+4) would deny it -- and the same shape
|
||||
* WITHOUT the EXTERNAL flag must still deny (legacy semantics pinned).
|
||||
*/
|
||||
static void test_unsatisfy_external_skips_inuse_shared_leg(void)
|
||||
{
|
||||
xce_sched_core_t core;
|
||||
xce_resource_t wire_resource;
|
||||
xce_resource_t* made;
|
||||
xce_resource_t* r = NULL;
|
||||
xvec_t uncomitted;
|
||||
xvec_idval_t wanted, unmeet;
|
||||
xce_val_t total, inuse;
|
||||
int rc;
|
||||
|
||||
memset(&core, 0, sizeof(core));
|
||||
/* makeResource() -> resobj_init() -> makeString() needs the intern table
|
||||
* (same per-test init as test_meet_host_selection_string_match). */
|
||||
xstring_table_init(139);
|
||||
init_test_resmgr(&core);
|
||||
zarray_init(&core.sharedInst, 4, NULL);
|
||||
zarray_init(&core.sharedInUse, 4, NULL);
|
||||
|
||||
/* Resource "lic": SHARED (cluster-wide pool) + EXTERNAL (free-value
|
||||
* reporting) -- the shape mapping.py's `location: [external]` produces.
|
||||
* idx 0. */
|
||||
memset(&wire_resource, 0, sizeof(wire_resource));
|
||||
wire_resource.name = "lic";
|
||||
wire_resource.idx = 0;
|
||||
wire_resource.flags = XCE_RESF_SHARED | XCE_RESF_EXTERNAL;
|
||||
made = (xce_resource_t*)makeResource(core.resmgr,
|
||||
&wire_resource);
|
||||
TEST_ASSERT_NOT_NULL(made);
|
||||
TEST_ASSERT_TRUE(key_find(core.resmgr, (void*)"lic", (void**)&r) >= 0);
|
||||
TEST_ASSERT_NOT_NULL(r);
|
||||
|
||||
memset(&total, 0, sizeof(total));
|
||||
total.which = Value_u_fvalue;
|
||||
total.u.fvalue = 4.0f;
|
||||
memset(&inuse, 0, sizeof(inuse));
|
||||
inuse.which = Value_u_fvalue;
|
||||
inuse.u.fvalue = 3.0f;
|
||||
|
||||
zarray_put(&core.sharedInst, 0, &total);
|
||||
zarray_put(&core.sharedInUse, 0, &inuse);
|
||||
|
||||
xvec_init(&uncomitted, 1, sizeof(float));
|
||||
xvec_idval_init(&wanted, 1);
|
||||
xvec_idval_store(&wanted, 0, 4.0f);
|
||||
xvec_idval_init(&unmeet, 1);
|
||||
|
||||
/* EXTERNAL: F=4 >= uncomit(0) + wanted(4) -> grant, despite inuse=3. */
|
||||
rc = sched_check_shared_satisfy(&core, &uncomitted, &wanted, &unmeet);
|
||||
TEST_ASSERT_EQUAL_INT(1, rc);
|
||||
|
||||
xvec_idval_fini(&wanted);
|
||||
xvec_idval_fini(&unmeet);
|
||||
|
||||
/* Same shape without EXTERNAL (plain SHARED pool): the legacy formula
|
||||
* must still apply -- 4 < 3+0+4 -> deny. Overwrite the flag in place. */
|
||||
r->flags = XCE_RESF_SHARED;
|
||||
|
||||
xvec_init(&uncomitted, 1, sizeof(float));
|
||||
xvec_idval_init(&wanted, 1);
|
||||
xvec_idval_store(&wanted, 0, 4.0f);
|
||||
xvec_idval_init(&unmeet, 1);
|
||||
|
||||
rc = sched_check_shared_satisfy(&core, &uncomitted, &wanted, &unmeet);
|
||||
TEST_ASSERT_EQUAL_INT(0, rc);
|
||||
|
||||
xvec_idval_fini(&wanted);
|
||||
xvec_idval_fini(&unmeet);
|
||||
xvec_fini(&uncomitted);
|
||||
zarray_fini(&core.sharedInst);
|
||||
zarray_fini(&core.sharedInUse);
|
||||
destroy(core.resmgr);
|
||||
}
|
||||
|
||||
#define TEST(x) \
|
||||
do { \
|
||||
if (check_test(&arguments, #x)) { \
|
||||
|
|
@ -759,6 +850,7 @@ int main(int argc, char* argv[])
|
|||
TEST(test_sched_update_existing_queue_null_payload);
|
||||
TEST(test_dead_pushmsg_symbols_absent);
|
||||
TEST(test_core_safe_allocation_chain_driver_parity);
|
||||
TEST(test_unsatisfy_external_skips_inuse_shared_leg);
|
||||
|
||||
return UNITY_END();
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue