myxce/src/controller/opupd.c
lei.chen 2fcacac2cb 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>
2026-10-27 03:45:28 +00:00

140 lines
5 KiB
C

#include "config.h"
#include <errno.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include "cluster.h"
#include "xce/cluster_def.h"
static int do_update_resvals(cluster_t* c, endpoint_t* ep,
xce_request_t* request)
{
ep_private_t* priv = NULL;
int rc = -EPERM;
xce_reply_t reply;
priv = (ep_private_t*)ep->data;
TRACE("endpoint %p priv data %p", ep, priv);
init_reply_by_req(&reply, request);
if (priv != NULL) {
int idx = priv->u.idx;
if (priv->role == HostRole_extres) {
/* external-license-resources Phase 1: the extres daemon
* (xceesd) pushes cluster-level values with NO workermgr slot
* -- w==NULL routes every entry through update_val_res()'s
* "SHARED 即收" guard (shared values land in c->sharedinst;
* host-based values are refused -EPERM per entry). The reply
* status is 0 for any syntactically valid list: per-entry
* refusals are logged by log_update_resval_failure() and must
* not fail the whole update (mirrors the worker path's
* per-item convention). */
xce_update_data_t* updatemsg = request->body.updatemsg;
xce_resval_list_t* resvals = updatemsg->data.resvals;
xce_resval_list_t applied = { .count = 0, .vals = NULL };
if ((resvals != NULL) && (resvals->count > 0)) {
applied.vals = (xce_resval_t**)calloc(
(size_t)resvals->count, sizeof(xce_resval_t*));
}
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_RESOURCE,
HOOK_BEFORE_EVENT, HOOK_DETAIL_RESOURCE_UPDATE, c,
resvals);
update_resval_list(c, NULL, resvals,
(applied.vals != NULL) ? &applied : NULL);
if (applied.count > 0) {
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_RESOURCE,
HOOK_AFTER_EVENT, HOOK_DETAIL_RESOURCE_UPDATE, c,
&applied);
}
free(applied.vals);
rc = 0;
} else if ((priv->role == HostRole_worker) && (idx >= 0)) {
worker_t* w = NULL;
rc = vget(c->workermgr, idx, (void**)&w);
if (w == NULL) {
rc = -E_XCE_BAD_WORKER;
} else {
xce_update_data_t* updatemsg = request->body.updatemsg;
xce_resval_list_t* resvals = updatemsg->data.resvals;
xce_resval_list_t applied = { .count = 0, .vals = NULL };
/* bug-1583: the AFTER_EVENT listeners (scheduler push,
* apiserver store) must only hear about the values this
* controller actually accepted -- not the raw client list,
* which may name resources it rejected. `applied` borrows
* pointers into `resvals`; nothing changes ownership. */
if ((resvals != NULL) && (resvals->count > 0)) {
applied.vals = (xce_resval_t**)calloc(
(size_t)resvals->count, sizeof(xce_resval_t*));
}
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_RESOURCE,
HOOK_BEFORE_EVENT, HOOK_DETAIL_RESOURCE_UPDATE, c,
resvals);
rc = update_resval_list(c, w, resvals,
(applied.vals != NULL) ? &applied
: NULL);
if (applied.count > 0) {
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_RESOURCE,
HOOK_AFTER_EVENT,
HOOK_DETAIL_RESOURCE_UPDATE, c, &applied);
}
free(applied.vals);
}
}
}
reply.status = rc;
reply.data_which = RequestReply_data_nodata;
xce_reply(ep, c->myhost, &reply);
return 0;
}
static int do_update_jobrusage(cluster_t* c, endpoint_t* ep,
xce_request_t* request)
{
int rc = 0;
xce_reply_t reply;
init_reply_by_req(&reply, request);
rc = update_job_rusages(c, ep, request);
reply.status = rc;
reply.data_which = RequestReply_data_nodata;
xce_reply(ep, c->myhost, &reply);
return rc;
}
int do_update_op(cluster_t* c, endpoint_t* ep, xce_request_t* request)
{
int rc = 0;
xce_reply_t reply;
init_reply_by_req(&reply, request);
switch (request->body.updatemsg->table) {
case Update_data_resvals:
rc = do_update_resvals(c, ep, request);
break;
case Update_data_jobrusages:
rc = do_update_jobrusage(c, ep, request);
break;
default:
rc = -ENOENT;
reply.status = rc;
reply.data_which = RequestReply_data_nodata;
xce_reply(ep, c->myhost, &reply);
break;
}
return rc;
}