resources: XCE_RESF_BUILTIN 从未被置位 — resources.yaml 加 builtin: true 声明式键

XCE_RESF_BUILTIN (0x01) 在生产链路上从未被任何一层置位:全树只有 types.h
定义、scheduler repl_info.c 显示表、一个测试 fixture 三处引用。worker
init_builtin_load_indices()(mem/io/r1m…)、controller add_hostattrs_resvals()/
set_host_slots() 硬编码生产这些资源的值,但定义的 flags 从 YAML→capnp→wire
全程没人打这个位——CLI 的 BUILTIN 列对 mem/io/slots 等恒显 false,与 extlic
等用户资源无法区分。

- resources.schema.json(+xceadmin 打包副本,构建时从 src/configs/schema
  同步):加 builtin: boolean 键
- mapping.py:RESOURCE_FLAG_BUILTIN=0x01,_build_resource 映射 builtin:true
  (与 consumable/release 同模式:缺省/false 不置位)
- build.py dump:补渲染 builtin=True;顺手补同样一直缺失的 external=True
  (此前 EXTERNAL 池 dump 只显示 shared=true)
- src/configs/resources.yaml:20 个硬编码生产者资源(slots + 11 load index
  + 8 host attributes)声明 builtin: true
- golden fixture full/expected.bin 相应再生(6696→6856B,diff 恰为 20 行
  builtin=True,非 builtin 行 0 差异)

验证:xceadmin 389 测试全绿(dev venv + meson build.dbg 各一遍);t1 实证:
树内 venv 重建 cluster.bin(与 live 逐行比对确认 delta 仅 builtin 20 行)→
config push gen=17 → apiserver 重启拾取(定义 store 只吃 join 时 config
push,激活只 re-push scheduler)→ xcecli definition list -l mem/io/slots
BUILTIN=true,extlic false、distribution/extlic 值/liccheck 作业 RUN→DONE
全链正常,5 daemon 健康。

Co-Authored-By: Claude Code <noreply@anthropic.com>
This commit is contained in:
lei.chen 2026-10-28 01:46:21 +00:00
parent 805288d747
commit 857f987f3c
8 changed files with 122 additions and 9 deletions

View file

@ -5,6 +5,7 @@ resources:
type: numeric
order: decrease
consumable: true
builtin: true
description: "job slot count (built-in)"
# built-in: dynamic memory load index reported by workers
@ -12,6 +13,7 @@ resources:
type: numeric
interval: 60
consumable: true
builtin: true
order: decrease
description: "available memory in bytes (built-in dynamic load index; CLI display converts to a human-readable unit)"
@ -21,6 +23,7 @@ resources:
type: numeric
interval: 60
consumable: false
builtin: true
order: increase
description: "1-minute load average (built-in dynamic load index)"
@ -28,6 +31,7 @@ resources:
type: numeric
interval: 60
consumable: false
builtin: true
order: increase
description: "15-minute load average (built-in dynamic load index)"
@ -35,6 +39,7 @@ resources:
type: numeric
interval: 60
consumable: false
builtin: true
order: increase
description: "15-second load average (built-in dynamic load index)"
@ -42,6 +47,7 @@ resources:
type: numeric
interval: 60
consumable: false
builtin: true
order: increase
description: "cpu utilization"
@ -49,6 +55,7 @@ resources:
type: numeric
interval: 60
consumable: false
builtin: true
order: increase
description: "page ratio"
@ -56,6 +63,7 @@ resources:
type: numeric
interval: 60
consumable: false
builtin: true
order: increase
description: "login count"
@ -63,13 +71,15 @@ resources:
type: numeric
interval: 60
consumable: false
builtin: true
order: increase
description: "idle time"
- name: swp
type: numeric
interval: 60
consumable: true
builtin: true
order: decrease
description: "swap size"
@ -77,13 +87,15 @@ resources:
type: numeric
interval: 60
consumable: false
builtin: true
order: increase
description: "io rate"
- name: tmp
type: numeric
interval: 60
consumable: true
builtin: true
order: decrease
description: "available tmp disk space in bytes (built-in dynamic load index; CLI display converts to a human-readable unit)"
@ -91,34 +103,42 @@ resources:
# controller/worker.c add_hostattrs_resvals()
- name: type
type: string
builtin: true
description: "host OS/arch type (built-in host attribute)"
- name: model
type: string
builtin: true
description: "host hardware model (built-in host attribute)"
- name: cpuf
type: numeric
builtin: true
description: "CPU speed factor (built-in host attribute)"
- name: maxcpus
type: numeric
builtin: true
description: "max CPU count (built-in host attribute)"
- name: maxmem
type: numeric
builtin: true
description: "max memory in bytes (built-in host attribute; CLI display converts to a human-readable unit)"
- name: maxswap
type: numeric
builtin: true
description: "max swap in bytes (built-in host attribute; CLI display converts to a human-readable unit)"
- name: maxtmp
type: numeric
builtin: true
description: "max tmp disk space in bytes (built-in host attribute; CLI display converts to a human-readable unit)"
- name: ndisks
type: numeric
builtin: true
description: "disk count (built-in host attribute)"
# dynamic hostbased resource, external load index

View file

@ -12,6 +12,7 @@
"order": { "type": "string", "enum": ["increase", "decrease", "na"] },
"consumable": { "type": "boolean" },
"release": { "type": "boolean" },
"builtin": { "type": "boolean" },
"description": { "type": "string" },
"resourcemap": {
"type": "array",

View file

@ -208,7 +208,9 @@ def _format_resource(r) -> str:
ordtype = _RESOURCE_ORDTYPE_NAMES.get(r.ordtype, r.ordtype)
consumable = bool(r.flags & mapping.RESOURCE_FLAG_CONSUMABLE)
release = bool(r.flags & mapping.RESOURCE_FLAG_RELEASE)
builtin = bool(r.flags & mapping.RESOURCE_FLAG_BUILTIN)
shared = bool(r.flags & mapping.RESOURCE_FLAG_SHARED)
external = bool(r.flags & mapping.RESOURCE_FLAG_EXTERNAL)
parts = [f"name={r.name}", f"type={valtype}", f"order={ordtype}"]
if r.desc:
parts.append(f"desc={r.desc!r}")
@ -216,6 +218,13 @@ def _format_resource(r) -> str:
parts.append(f"interval={r.interval}")
parts.append(f"consumable={consumable}")
parts.append(f"release={release}")
# builtin/external change the resource's semantics (whose values count,
# where they come from) -- always visible when set, never shown bare
# false: absent means the plain user-resource default.
if builtin:
parts.append("builtin=True")
if external:
parts.append("external=True")
if shared:
parts.append("shared=true")
if len(r.distributions) > 0:

View file

@ -64,12 +64,12 @@ reason -- never a silent drop.
``Resource`` (``resources.yaml``)
``valtype``/``ordtype``/``flags`` ARE mapped from YAML
``type``/``order``/``consumable``/``release`` -- the encoding is
documented, just not in ``controller.capnp``/design.md: it lives in
``type``/``order``/``consumable``/``release``/``builtin`` -- the encoding
is documented, just not in ``controller.capnp``/design.md: it lives in
``include/xce/types.h`` (``XCE_VAL_*``, ``xce_order_t``,
``XCE_RESF_CONSUMABLE``/``XCE_RESF_RELEASE``) and is actively read at
runtime (e.g. ``scheduler.c`` copies these three fields straight out
of the parsed resource). See :data:`RESOURCE_VALTYPE`,
``XCE_RESF_CONSUMABLE``/``XCE_RESF_RELEASE``/``XCE_RESF_BUILTIN``) and
is actively read at runtime (e.g. ``scheduler.c`` copies these three
fields straight out of the parsed resource). See :data:`RESOURCE_VALTYPE`,
:data:`RESOURCE_ORDTYPE`, and the flag constants below for the exact
values (also reused by ``xceadmin.build.dump_cluster_config`` to render
these int-encoded fields back to their YAML names). ``idx`` and
@ -205,10 +205,16 @@ _XCE_SCALAR_FIELDS: tuple[tuple[str, str], ...] = (
RESOURCE_VALTYPE: dict[str, int] = {"string": 0, "numeric": 1, "boolean": 2}
RESOURCE_ORDTYPE: dict[str, int] = {"increase": 0, "decrease": 1, "na": 2}
# resources.yaml ``consumable``/``release`` -> Resource.flags bits, mirroring
# include/xce/types.h's XCE_RESF_CONSUMABLE/XCE_RESF_RELEASE.
# resources.yaml ``consumable``/``release``/``builtin`` -> Resource.flags
# bits, mirroring include/xce/types.h's XCE_RESF_CONSUMABLE/
# XCE_RESF_RELEASE/XCE_RESF_BUILTIN.
RESOURCE_FLAG_CONSUMABLE = 0x80
RESOURCE_FLAG_RELEASE = 0x20
# XCE_RESF_BUILTIN: the resource's values are produced by hardcoded worker/
# controller reporters (resource_sync.c's load indices, worker.c's host
# attributes and slots) -- display/accounting code uses it to tell those
# from user-declared resources of the same name space.
RESOURCE_FLAG_BUILTIN = 0x01
# Set together on a resourcemap item whose location is exactly ["all"]
# (cluster-wide static shared pool): XCE_RESF_SHARED | XCE_RESF_GLOBAL in
@ -421,6 +427,8 @@ def _build_resource(item: dict, target: "capnp._DynamicStructBuilder") -> None:
flags |= RESOURCE_FLAG_CONSUMABLE
if item.get("release"):
flags |= RESOURCE_FLAG_RELEASE
if item.get("builtin"):
flags |= RESOURCE_FLAG_BUILTIN
resourcemap = item.get("resourcemap") or []
if resourcemap:
distributions = target.init("distributions", len(resourcemap))

View file

@ -12,6 +12,7 @@ resources:
type: numeric
interval: 60
consumable: false
builtin: true
order: decrease
description: "available memory in MB (built-in dynamic load index)"
@ -197,3 +198,16 @@ resources:
- name: gstring
description: string resource
type: string
# external-license-resources: cluster-wide license pool reported by
# the extres daemon (xceesd) -- config declares only the name/shape,
# the free counts come from the daemon's pushes
- name: extlic
description: externally reported license pool
type: numeric
interval: 0
consumable: true
order: decrease
resourcemap:
- location:
- external

Binary file not shown.

View file

@ -49,6 +49,32 @@ def test_dump_lists_each_resource_with_decoded_type_and_order(full_cluster_bin):
assert "consumable=False" in text
def test_dump_renders_builtin_and_external_flags(full_cluster_bin):
"""The flag bits that change a resource's semantics must be visible in a
dump: builtin (worker/controller hardcode the values -- the repo fixture's
load indices and host attributes) and external (values come only from the
extres daemon's pushes -- the extlic pool shape). Both were silently
invisible before: every builtin resource dumped as a plain user resource,
and an external pool dumped as bare shared=true.
"""
text = build.dump_cluster_config(str(full_cluster_bin))
mem_line = next(l for l in text.splitlines() if "name=mem type=numeric" in l)
assert "builtin=True" in mem_line
# a user-declared resource must not show a bare "builtin=" at all
assert "builtin=False" not in text
import yaml as _yaml
configs = str(FIXTURES_DIR / "full" / "configs")
with open(configs + "/resources.yaml", encoding="utf-8") as fh:
names = [r["name"] for r in _yaml.safe_load(fh)["resources"]
if (r.get("resourcemap") or []) and
(r["resourcemap"][0].get("location") or []) == ["external"]]
assert names, "fixture must contain an external resource for this test"
for name in names:
line = next(l for l in text.splitlines() if f"name={name} " in l)
assert "external=True" in line, line
def test_dump_renders_mxj_auto_detect_sentinel_not_raw_uint32(full_cluster_bin):
"""The exact bug that motivated this feature: hosts.yaml's `default`
host has `max_slot: -1`, which wire-encodes as HOSTCONFIG_MXJ_AUTO_DETECT

View file

@ -176,6 +176,29 @@ def test_map_list_section_resources_populates_mapped_fields_only(cluster_config)
assert r0.lastReport == 0
def test_map_list_section_resources_builtin_flag(cluster_config):
"""``builtin: true`` (resources.yaml) -> XCE_RESF_BUILTIN (0x01) OR'd
on top of the other bits: the load indices (mem/io/r1m...) and host
attributes (type/model/maxmem...) are produced by hardcoded worker/
controller reporters, and the flag tells them apart from user-declared
resources (the CLI's BUILTIN column renders it). Absent/false must
stay 0 -- the same convention as consumable/release.
"""
items = [
{"name": "mem", "type": "numeric", "interval": 60,
"consumable": True, "builtin": True, "description": "memory"},
{"name": "mylic", "type": "numeric", "consumable": True,
"builtin": False, "description": "user pool"},
{"name": "plain", "type": "numeric"}, # builtin absent
]
mapping.map_list_section(_spec_for("resources"), items, cluster_config)
r0, r1, r2 = cluster_config.resources
assert r0.flags == 0x80 | 0x01 # CONSUMABLE | BUILTIN
assert r1.flags == 0x80 # explicit false -> no BUILTIN bit
assert r2.flags == 0 # absent -> no BUILTIN bit
def test_map_list_section_noop_on_empty_or_missing_items(cluster_config):
mapping.map_list_section(_spec_for("resources"), [], cluster_config)
mapping.map_list_section(_spec_for("resources"), None, cluster_config)
@ -307,6 +330,18 @@ def test_map_list_section_resourcemap_real_repo_configs(cluster_config):
for name in ("staticres1", "staticres2", "staticres3", "host_quota"):
assert by_name[name].flags & (0x08 | 0x04) == 0
# builtin:true resources (the worker load indices + host attributes the
# repo config declares) carry XCE_RESF_BUILTIN; user-declared shapes
# (staticres*, extlic) do not.
for name in ("slots", "mem", "r1m", "r15m", "r15s", "ut", "pg", "ls", "it",
"swp", "io", "tmp", "type", "model", "cpuf", "maxcpus",
"maxmem", "maxswap", "maxtmp", "ndisks"):
assert by_name[name].flags & 0x01 == 0x01, f"{name} missing BUILTIN"
for name in ("dynres1", "dynres2", "staticres1", "staticres2", "staticres3",
"staticres4", "res1", "sres1", "bigmem", "strres1", "strres2",
"host_quota", "gstring", "extlic"):
assert by_name[name].flags & 0x01 == 0, f"{name} unexpectedly BUILTIN"
# ---------------------------------------------------------------------------
# map_list_section: users.yaml/hosts.yaml -> ugroups/hgroups (named groups)