host
22b83f118a
Stack: #216 -> #221 -> this. Worker breakpoint branch now calls any executor providing goal_resume_breakpoint_task (Local keeps its original path, gateway tasks still loud-fail); WarmPool reconcile_orphans is called on CHV worker startup and close with audit-on-failure; per-VM SSH host keys are provisioned before VMM start via cloud-init NoCloud seed (keyscan kept only as weak fallback, CHV_HOST_KEY_MODE=provisioned|keyscan); CHV_NET_JSON is validated in preflight and explicit direct egress is audited; chv-guest/build.sh is now real steps with --dry-run and fails fast without /dev/kvm. Tests: new test_chv_gaps.py (18), cloud full 1514 OK (skipped=4). No real VM verification: no KVM host.
154 lines
6.9 KiB
Python
154 lines
6.9 KiB
Python
"""Cloud Hypervisor 执行器配置解析（叶子模块，不依赖
|
||
cloud.sandbox，避免循环导入）。
|
||
|
||
职责只有两件：内存字符串解析，以及把构造参数 + 环境变量
|
||
解析成一份显式配置。参数优先于环境变量、环境变量优先于
|
||
默认值——与 #216 原 __init__ 的 `or` 链完全一致，只收紧了
|
||
两处原来会静默 fallback 的 nonsense 输入（见下文），收紧点
|
||
在 PR 描述里明写、单测钉住：
|
||
|
||
- CHV_SSH_USER 显式传空字符串：原来 `or` 链会静默 fallback
|
||
成 root（调用方以为没给用户、实际跑了 root），现在直接
|
||
ValueError。
|
||
- CHV_SSH_PORT 显式传 0、或解析后超出 1-65535：原来 0 会
|
||
静默 fallback 成 2222、其它越界值会原样进 ssh 命令，现在
|
||
直接 ValueError。
|
||
|
||
与 #215 的关系（只列清单，不复制模块）：#215 未合并，
|
||
本轨不假装复用它。#215 合并后应再复用的点：超时类
|
||
（api_timeout/ready_timeout/ready_interval/task_timeout →
|
||
timeouts 模块）、门禁类（preflight fail-fast、容量门、磁盘
|
||
配额门、egress fail-closed → gates 模块）、配额类
|
||
（max_vms、disk_gb、任务成本走 worker quota → quota 模块）、
|
||
隔离类（单任务单 VM、磁盘 copy 模式、egress 代理、SSH 钉死
|
||
→ sandbox_policy 模块）。见 PR 描述的复用清单。
|
||
"""
|
||
|
||
import re
|
||
|
||
|
||
def _parse_memory_bytes(value):
|
||
"""内存字符串转字节：2G/512M/1024K/2048（无单位=字节）。
|
||
非法值 ValueError，绝不静默按默认算。"""
|
||
m = re.match(r"^\s*(\d+)\s*([KMGkmg]?)\s*[Bb]?\s*$",
|
||
str(value))
|
||
if not m:
|
||
raise ValueError("CHV_MEM 格式非法：%r" % (value,))
|
||
mult = {"": 1, "K": 1024, "M": 1024 ** 2, "G": 1024 ** 3}
|
||
return int(m.group(1)) * mult[m.group(2).upper()]
|
||
|
||
|
||
class ChvConfig:
|
||
"""解析后的 CHV 配置：纯数据对象，字段名与
|
||
CloudHypervisorExecutor 原 __init__ 的属性名一一对应，
|
||
执行器 __init__ 直接把字段抄到 self 上，旧测试读属性
|
||
的方式全部不变。"""
|
||
|
||
def __init__(self, **fields):
|
||
for key, value in fields.items():
|
||
setattr(self, key, value)
|
||
|
||
|
||
def build_chv_config(params, env):
|
||
"""把显式构造参数（params，None=未给）与环境变量（env，
|
||
默认为 os.environ 的调用方传入 dict）解析成 ChvConfig。
|
||
|
||
显式参数只有 __init__ 本来就有的那些；max_vms、磁盘模式、
|
||
磁盘配额、egress、快照、预热池目标数本来就没有显式参数，
|
||
仍只走环境变量（与 #216 一致，不悄悄加新参数面）。"""
|
||
env = env if env is not None else {}
|
||
binary = params.get("binary") or env.get("CHV_BINARY") \
|
||
or "cloud-hypervisor"
|
||
kernel = params.get("kernel") or env.get("CHV_KERNEL")
|
||
rootfs = params.get("rootfs") or params.get("image") \
|
||
or env.get("CHV_ROOTFS") or env.get("CHV_IMAGE")
|
||
cpus = str(params.get("cpus") or env.get("CHV_CPU") or "2")
|
||
memory = params.get("memory") or env.get("CHV_MEM") or "2G"
|
||
state_dir = params.get("state_dir") or env.get("CHV_STATE_DIR") \
|
||
or "/tmp/chv-vms"
|
||
ssh_key = params.get("ssh_key") or env.get("CHV_SSH_KEY")
|
||
if params.get("ssh_user") is not None \
|
||
and params.get("ssh_user") == "":
|
||
raise ValueError("CHV_SSH_USER 不能为空字符串")
|
||
ssh_user = params.get("ssh_user") or env.get("CHV_SSH_USER") \
|
||
or "root"
|
||
if params.get("ssh_port") is not None:
|
||
raw_port = params.get("ssh_port")
|
||
else:
|
||
raw_port = env.get("CHV_SSH_PORT") or 2222
|
||
try:
|
||
ssh_port = int(raw_port)
|
||
except (TypeError, ValueError):
|
||
raise ValueError("CHV_SSH_PORT 必须是整数")
|
||
if not 1 <= ssh_port <= 65535:
|
||
raise ValueError("CHV_SSH_PORT 必须在 1-65535 之间")
|
||
guest_host_py = params.get("guest_host_py") or "/app/host.py"
|
||
cmdline = params.get("cmdline") or env.get("CHV_CMDLINE") \
|
||
or "console=hvc0 root=/dev/vda1 rw"
|
||
net = params.get("net") or env.get("CHV_NET")
|
||
net_json = params.get("net_json") or env.get("CHV_NET_JSON")
|
||
kvm_path = params.get("kvm_path") \
|
||
if params.get("kvm_path") is not None else "/dev/kvm"
|
||
cpuinfo_path = params.get("cpuinfo_path") \
|
||
if params.get("cpuinfo_path") is not None else "/proc/cpuinfo"
|
||
ch_remote = params.get("ch_remote") or env.get("CHV_REMOTE") \
|
||
or "ch-remote"
|
||
model = params.get("model")
|
||
try:
|
||
max_vms = int(env.get("CHV_MAX_VMS") or 4)
|
||
except ValueError:
|
||
raise ValueError("CHV_MAX_VMS 必须是整数")
|
||
disk_mode = env.get("CHV_DISK_MODE") or "copy"
|
||
if disk_mode not in ("copy", "reuse"):
|
||
raise ValueError(
|
||
"CHV_DISK_MODE 只能是 copy 或 reuse：%s" % disk_mode)
|
||
disk_gb_raw = env.get("CHV_DISK_GB")
|
||
disk_gb = float(disk_gb_raw) if disk_gb_raw else None
|
||
egress_proxy = env.get("CHV_EGRESS_PROXY")
|
||
allow_direct_egress = env.get("CHV_ALLOW_DIRECT_EGRESS") == "1"
|
||
host_key_mode = params.get("host_key_mode") \
|
||
or env.get("CHV_HOST_KEY_MODE") or "keyscan"
|
||
if host_key_mode not in ("provisioned", "keyscan"):
|
||
raise ValueError(
|
||
"CHV_HOST_KEY_MODE 只能是 provisioned 或 keyscan：%s"
|
||
% host_key_mode)
|
||
task_timeout_raw = env.get("CHV_TASK_TIMEOUT")
|
||
task_timeout = float(task_timeout_raw) \
|
||
if task_timeout_raw else None
|
||
snapshot_url = env.get("CHV_SNAPSHOT_URL")
|
||
try:
|
||
warm_pool_size = int(env.get("CHV_WARM_POOL_SIZE") or 0)
|
||
except ValueError:
|
||
raise ValueError("CHV_WARM_POOL_SIZE 必须是整数")
|
||
try:
|
||
api_timeout = float(
|
||
params.get("api_timeout")
|
||
if params.get("api_timeout") is not None
|
||
else env.get("CHV_API_TIMEOUT") or 30)
|
||
ready_timeout = float(
|
||
params.get("ready_timeout")
|
||
if params.get("ready_timeout") is not None
|
||
else env.get("CHV_READY_TIMEOUT") or 120)
|
||
ready_interval = float(
|
||
params.get("ready_interval")
|
||
if params.get("ready_interval") is not None
|
||
else env.get("CHV_READY_INTERVAL") or 5)
|
||
except ValueError:
|
||
raise ValueError("CHV_*_TIMEOUT/INTERVAL 必须是数字")
|
||
if ready_interval <= 0:
|
||
ready_interval = 5
|
||
return ChvConfig(
|
||
binary=binary, kernel=kernel, rootfs=rootfs, cpus=cpus,
|
||
memory=memory, state_dir=state_dir, ssh_key=ssh_key,
|
||
ssh_user=ssh_user, ssh_port=ssh_port,
|
||
guest_host_py=guest_host_py, cmdline=cmdline, net=net,
|
||
net_json=net_json, kvm_path=kvm_path,
|
||
cpuinfo_path=cpuinfo_path, ch_remote=ch_remote, model=model,
|
||
max_vms=max_vms, disk_mode=disk_mode, disk_gb=disk_gb,
|
||
egress_proxy=egress_proxy,
|
||
allow_direct_egress=allow_direct_egress,
|
||
host_key_mode=host_key_mode,
|
||
task_timeout=task_timeout, snapshot_url=snapshot_url,
|
||
warm_pool_size=warm_pool_size, api_timeout=api_timeout,
|
||
ready_timeout=ready_timeout, ready_interval=ready_interval)
|