实现首版 Gitea microVM runner

.gitea/workflows/test.yml

@@ -0,0 +1,25 @@
+name: test
+on:
+  push:
+  pull_request:
+
+jobs:
+  python:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - run: pip install -e '.[test]'
+      - run: pytest
+      - run: python -m compileall -q src
+
+  shell:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - run: |
+          sudo apt-get update
+          sudo apt-get install -y shellcheck
+      - run: shellcheck scripts/*

.gitignore

@@ -0,0 +1,7 @@
+__pycache__/
+*.py[cod]
+.pytest_cache/
+.venv/
+dist/
+build/
+*.egg-info/

README.md

@@ -1,3 +1,39 @@
-# gitea-microvm-runner
+# Gitea microVM runner
+
+为 Gitea Actions 按需启动 Cloud Hypervisor microVM。适合 kind、嵌套容器和其他不应
+在常驻 Kubernetes runner 中执行的 CI 工作负载。
+
+组件：
+
+- `controller`：接收 Gitea `workflow_job` webhook，将指定 label 的 queued job
+  发布到 NATS JetStream。
+- `worker`：在虚拟化宿主机领取任务，限制本机并发，并启动一次性 microVM。
+- `microvm-runner-launch`：为每个任务创建 COW disk、NoCloud seed 和 TAP，运行
+  Cloud Hypervisor，退出后完整清理。
+- `guest-runner`：在 guest 中领取一次性 runner registration token，注册 ephemeral
+  runner，执行一个 job 后关机。
+
+消息流使用一个 `WorkQueuePolicy` stream。相同 runner label 的所有 worker 共享同一
+durable consumer；扩容只需要增加 worker 或提高单机 capacity。
+
+## 开发
+
+```bash
+python -m venv .venv
+. .venv/bin/activate
+pip install -e '.[test]'
+pytest
+```
+
+## 安全边界
+
+- NATS 密码、webhook secret 和 Gitea registration token 只从文件读取。
+- registration token 不写入 seed image；worker 通过单次 nonce endpoint 交给 guest。
+- guest runner 使用 `--ephemeral`，每台 VM 只执行一个 job。
+- launcher 只接受 UUID instance ID 和 URL-safe nonce，所有临时文件都位于独立目录。
+- base image 不得包含 runner identity、registration token、SSH 密码或 host key。
+
+homelab 的 Kubernetes、OpenBao、LXC、bridge 和容量配置保留在
+`panxiao81/homelab-infra`。
 
 按需启动 Cloud Hypervisor microVM 的 Gitea Actions runner autoscaler

container/controller.Dockerfile

@@ -0,0 +1,12 @@
+FROM python:3.12.11-alpine3.22 AS build
+WORKDIR /src
+COPY pyproject.toml README.md ./
+COPY src ./src
+RUN python -m venv /venv && /venv/bin/pip install --no-cache-dir .
+
+FROM python:3.12.11-alpine3.22
+RUN addgroup -S -g 65532 runner && adduser -S -D -H -u 65532 -G runner runner
+COPY --from=build /venv /venv
+USER 65532:65532
+EXPOSE 8787
+ENTRYPOINT ["/venv/bin/gitea-microvm-controller"]

pyproject.toml

@@ -0,0 +1,24 @@
+[build-system]
+requires = ["setuptools>=75"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "gitea-microvm-runner"
+version = "0.1.0"
+description = "On-demand Cloud Hypervisor runners for Gitea Actions"
+requires-python = ">=3.11"
+dependencies = ["aiohttp==3.12.15", "nats-py==2.11.0"]
+
+[project.optional-dependencies]
+test = ["pytest==8.4.2", "pytest-asyncio==1.2.0"]
+
+[project.scripts]
+gitea-microvm-controller = "gitea_microvm_runner.controller:main"
+gitea-microvm-worker = "gitea_microvm_runner.worker:cli"
+
+[tool.pytest.ini_options]
+asyncio_mode = "auto"
+testpaths = ["tests"]
+
+[tool.setuptools.packages.find]
+where = ["src"]

scripts/gitea-microvm-guest-runner

@@ -0,0 +1,28 @@
+#!/bin/sh
+set -eu
+
+token_url=${1:?token URL is required}
+instance=${2:?Gitea instance is required}
+runner_name=${3:?runner name is required}
+runner_label=${4:?runner label is required}
+token_file=/run/gitea-runner-registration-token
+
+cleanup() {
+    rm -f -- "$token_file"
+    sync
+    poweroff -f
+}
+trap cleanup EXIT INT TERM
+
+umask 077
+curl --fail --silent --show-error --retry 10 --retry-all-errors \
+    --connect-timeout 2 --max-time 30 "$token_url" >"$token_file"
+gitea-runner register \
+    --no-interactive \
+    --ephemeral \
+    --instance "$instance" \
+    --name "$runner_name" \
+    --labels "$runner_label:host" \
+    --token-file "$token_file"
+rm -f -- "$token_file"
+gitea-runner daemon

scripts/microvm-runner-launch

@@ -0,0 +1,74 @@
+#!/bin/sh
+set -eu
+
+instance_id=${1:?instance ID is required}
+nonce=${2:?registration nonce is required}
+
+case "$instance_id" in
+    ????????-????-????-????-????????????) ;;
+    *) echo "invalid instance ID" >&2; exit 64 ;;
+esac
+case "$nonce" in
+    *[!A-Za-z0-9_-]*|'') echo "invalid nonce" >&2; exit 64 ;;
+esac
+
+state_root=${RUNNER_STATE_ROOT:-/var/lib/microvm-runner}
+base_image=${RUNNER_BASE_IMAGE:-$state_root/images/runner-base.qcow2}
+firmware=${RUNNER_FIRMWARE:-$state_root/firmware/CLOUDHV.fd}
+bridge=${RUNNER_BRIDGE:-mvrbr0}
+cloud_hypervisor=${CLOUD_HYPERVISOR:-/usr/local/bin/cloud-hypervisor}
+vm_timeout=${RUNNER_VM_TIMEOUT:-3h}
+cpus=${RUNNER_VM_CPUS:-4}
+memory=${RUNNER_VM_MEMORY:-3G}
+gitea_instance=${GITEA_INSTANCE:-https://git.ddupan.top}
+runner_label=${RUNNER_LABEL:-kind-microvm}
+token_url=${RUNNER_TOKEN_URL:-http://172.30.0.1:8787}
+
+vm_dir="$state_root/instances/$instance_id"
+tap="mvr${instance_id%%-*}"
+overlay="$vm_dir/root.qcow2"
+seed="$vm_dir/seed.img"
+serial="$vm_dir/serial.log"
+
+cleanup() {
+    ip link delete "$tap" 2>/dev/null || true
+    rm -rf -- "$vm_dir"
+}
+trap cleanup EXIT INT TERM
+
+test -r "$base_image"
+test -r "$firmware"
+mkdir -m 0700 -p "$vm_dir"
+qemu-img create -q -f qcow2 -F qcow2 -b "$base_image" "$overlay"
+
+cat >"$vm_dir/meta-data" <<EOF
+instance-id: $instance_id
+local-hostname: gitea-runner-${instance_id%%-*}
+EOF
+cat >"$vm_dir/user-data" <<EOF
+#cloud-config
+runcmd:
+  - [ /usr/local/libexec/gitea-microvm-guest-runner, "$token_url/token/$nonce", "$gitea_instance", "gitea-${instance_id%%-*}", "$runner_label" ]
+EOF
+cloud-localds "$seed" "$vm_dir/user-data" "$vm_dir/meta-data"
+
+digest=$(printf '%s' "$instance_id" | sha256sum | cut -c1-10)
+mac=$(printf '02:%s:%s:%s:%s:%s' \
+    "$(printf '%s' "$digest" | cut -c1-2)" \
+    "$(printf '%s' "$digest" | cut -c3-4)" \
+    "$(printf '%s' "$digest" | cut -c5-6)" \
+    "$(printf '%s' "$digest" | cut -c7-8)" \
+    "$(printf '%s' "$digest" | cut -c9-10)")
+ip tuntap add dev "$tap" mode tap
+ip link set "$tap" master "$bridge"
+ip link set "$tap" up
+
+timeout --signal=TERM --kill-after=30s "$vm_timeout" "$cloud_hypervisor" \
+    --firmware "$firmware" \
+    --cpus "boot=$cpus" \
+    --memory "size=$memory" \
+    --disk "path=$overlay" \
+    --disk "path=$seed,readonly=on" \
+    --net "tap=$tap,mac=$mac" \
+    --serial "file=$serial" \
+    --console off

scripts/microvm-runner-network

@@ -0,0 +1,37 @@
+#!/bin/sh
+set -eu
+
+action=${1:?up or down is required}
+bridge=${RUNNER_BRIDGE:-mvrbr0}
+subnet=${RUNNER_SUBNET:-172.30.0.0/24}
+gateway=${RUNNER_GATEWAY:-172.30.0.1}
+dhcp_start=${RUNNER_DHCP_START:-172.30.0.10}
+dhcp_end=${RUNNER_DHCP_END:-172.30.0.200}
+pid_file=${RUNNER_DNSMASQ_PID:-/run/microvm-runner/dnsmasq.pid}
+
+case "$action" in
+up)
+    mkdir -p "$(dirname "$pid_file")"
+    ip link show "$bridge" >/dev/null 2>&1 || ip link add "$bridge" type bridge
+    ip address show dev "$bridge" | grep -Fq "$gateway/24" || ip address add "$gateway/24" dev "$bridge"
+    ip link set "$bridge" up
+    sysctl -q -w net.ipv4.ip_forward=1
+    iptables -t nat -C POSTROUTING -s "$subnet" -j MASQUERADE 2>/dev/null || \
+        iptables -t nat -A POSTROUTING -s "$subnet" -j MASQUERADE
+    dnsmasq --interface="$bridge" --bind-interfaces --except-interface=lo \
+        --dhcp-range="$dhcp_start,$dhcp_end,255.255.255.0,1h" \
+        --dhcp-option="option:router,$gateway" --pid-file="$pid_file"
+    ;;
+down)
+    if test -r "$pid_file"; then
+        kill "$(cat "$pid_file")" 2>/dev/null || true
+        rm -f -- "$pid_file"
+    fi
+    iptables -t nat -D POSTROUTING -s "$subnet" -j MASQUERADE 2>/dev/null || true
+    ip link delete "$bridge" 2>/dev/null || true
+    ;;
+*)
+    echo "expected up or down" >&2
+    exit 64
+    ;;
+esac

src/gitea_microvm_runner/__init__.py

@@ -0,0 +1 @@
+"""Gitea microVM runner controller and worker."""

src/gitea_microvm_runner/controller.py

@@ -0,0 +1,116 @@
+#!/usr/bin/env python3
+"""Gitea workflow_job webhook to NATS JetStream producer."""
+
+import hashlib
+import hmac
+import json
+import os
+import ssl
+from pathlib import Path
+
+import nats
+from aiohttp import web
+from nats.js.api import DiscardPolicy, RetentionPolicy, StorageType, StreamConfig
+from nats.js.errors import NotFoundError
+
+LABEL = os.environ.get("RUNNER_LABEL", "kind-microvm")
+SUBJECT = os.environ.get("NATS_SUBJECT", f"ci.runner.{LABEL}")
+STREAM = os.environ.get("NATS_STREAM", "CI_RUNNER")
+NATS_URL = os.environ.get("NATS_URL", "tls://nats.ad.ddupan.top:4222")
+NATS_USER = os.environ.get("NATS_USER", "ci-producer")
+NATS_PASSWORD_FILE = Path(os.environ.get("NATS_PASSWORD_FILE", "/run/secrets/nats/password"))
+NATS_CA_FILE = os.environ.get("NATS_CA_FILE", "/etc/ssl/certs/ca-certificates.crt")
+WEBHOOK_SECRET_FILE = Path(os.environ.get("WEBHOOK_SECRET_FILE", "/run/secrets/gitea/webhook-secret"))
+
+
+def accepts(payload: object) -> tuple[bool, str | None]:
+    if not isinstance(payload, dict) or payload.get("action") != "queued":
+        return False, None
+    job = payload.get("workflow_job")
+    if not isinstance(job, dict) or LABEL not in job.get("labels", []):
+        return False, None
+    job_id = job.get("id")
+    if not isinstance(job_id, int) or isinstance(job_id, bool):
+        return False, None
+    return True, str(job_id)
+
+
+def valid_signature(body: bytes, signature: str) -> bool:
+    expected = hmac.new(WEBHOOK_SECRET_FILE.read_bytes().strip(), body, hashlib.sha256).hexdigest()
+    return hmac.compare_digest(signature.removeprefix("sha256="), expected)
+
+
+async def ensure_stream(js: object) -> None:
+    config = StreamConfig(
+        name=STREAM,
+        subjects=["ci.runner.*"],
+        retention=RetentionPolicy.WORK_QUEUE,
+        storage=StorageType.FILE,
+        discard=DiscardPolicy.OLD,
+        max_age=24 * 60 * 60,
+        max_msgs=10_000,
+        max_bytes=256 * 1024 * 1024,
+        duplicate_window=24 * 60 * 60,
+    )
+    try:
+        await js.stream_info(STREAM)
+    except NotFoundError:
+        await js.add_stream(config=config)
+    else:
+        await js.update_stream(config=config)
+
+
+async def webhook(request: web.Request) -> web.Response:
+    body = await request.read()
+    if not valid_signature(body, request.headers.get("X-Gitea-Signature", "")):
+        raise web.HTTPUnauthorized()
+    try:
+        payload = json.loads(body)
+    except json.JSONDecodeError as error:
+        raise web.HTTPBadRequest(text="invalid JSON\n") from error
+    accepted, job_id = accepts(payload)
+    if not accepted:
+        return web.Response(status=204)
+    await request.app["js"].publish(
+        SUBJECT,
+        body,
+        headers={"Nats-Msg-Id": f"gitea-workflow-job-{job_id}"},
+    )
+    return web.Response(status=202, text="queued\n")
+
+
+async def health(request: web.Request) -> web.Response:
+    connected = request.app["nc"].is_connected
+    return web.Response(text="ok\n" if connected else "disconnected\n", status=200 if connected else 503)
+
+
+async def nats_context(app: web.Application):
+    tls = ssl.create_default_context(cafile=NATS_CA_FILE)
+    nc = await nats.connect(
+        NATS_URL,
+        user=NATS_USER,
+        password=NATS_PASSWORD_FILE.read_text().strip(),
+        tls=tls,
+        name="microvm-runner-controller",
+    )
+    app["nc"] = nc
+    app["js"] = nc.jetstream()
+    await ensure_stream(app["js"])
+    yield
+    await nc.drain()
+
+
+def create_app() -> web.Application:
+    app = web.Application(client_max_size=1024 * 1024)
+    app.cleanup_ctx.append(nats_context)
+    app.router.add_post("/webhook", webhook)
+    app.router.add_get("/healthz", health)
+    return app
+
+
+def main() -> None:
+    web.run_app(create_app(), host=os.environ.get("LISTEN", "0.0.0.0"), port=int(os.environ.get("PORT", "8787")))
+
+
+if __name__ == "__main__":
+    main()

src/gitea_microvm_runner/worker.py

@@ -0,0 +1,155 @@
+#!/usr/bin/env python3
+"""Capacity-bounded JetStream consumer that launches one ephemeral VM per job."""
+
+import asyncio
+import logging
+import os
+import secrets
+import ssl
+import uuid
+from pathlib import Path
+
+import nats
+from aiohttp import web
+from nats.errors import TimeoutError
+from nats.js.api import AckPolicy, ConsumerConfig
+
+LOG = logging.getLogger(__name__)
+CAPACITY = int(os.environ.get("RUNNER_CAPACITY", "1"))
+SUBJECT = os.environ.get("NATS_SUBJECT", "ci.runner.kind-microvm")
+STREAM = os.environ.get("NATS_STREAM", "CI_RUNNER")
+DURABLE = os.environ.get("NATS_DURABLE", "kind-microvm")
+MAX_INFLIGHT = int(os.environ.get("RUNNER_MAX_INFLIGHT", "64"))
+NATS_URL = os.environ.get("NATS_URL", "tls://nats.ad.ddupan.top:4222")
+NATS_USER = os.environ.get("NATS_USER", "ci-worker")
+NATS_PASSWORD_FILE = Path(os.environ.get("NATS_PASSWORD_FILE", "/etc/microvm-runner/nats-password"))
+NATS_CA_FILE = os.environ.get("NATS_CA_FILE", "/etc/ssl/certs/ca-certificates.crt")
+REGISTRATION_TOKEN_FILE = Path(os.environ.get("REGISTRATION_TOKEN_FILE", "/etc/microvm-runner/registration-token"))
+LAUNCHER = os.environ.get("LAUNCHER", "/usr/local/libexec/microvm-runner-launch")
+TOKEN_LISTEN = os.environ.get("TOKEN_LISTEN", "172.30.0.1")
+TOKEN_PORT = int(os.environ.get("TOKEN_PORT", "8787"))
+
+tokens: dict[str, bytes] = {}
+token_lock = asyncio.Lock()
+
+
+async def token(request: web.Request) -> web.Response:
+    nonce = request.match_info["nonce"]
+    async with token_lock:
+        value = tokens.pop(nonce, None)
+    if value is None:
+        raise web.HTTPNotFound()
+    return web.Response(body=value, headers={"Cache-Control": "no-store"})
+
+
+async def heartbeat(message: object, stop: asyncio.Event) -> None:
+    while True:
+        try:
+            await asyncio.wait_for(stop.wait(), timeout=60)
+            return
+        except asyncio.TimeoutError:
+            await message.in_progress()
+
+
+async def run_one(message: object) -> None:
+    instance_id = str(uuid.uuid4())
+    nonce = secrets.token_urlsafe(32)
+    async with token_lock:
+        tokens[nonce] = REGISTRATION_TOKEN_FILE.read_bytes().strip()
+    stop = asyncio.Event()
+    pulse = asyncio.create_task(heartbeat(message, stop))
+    try:
+        process = await asyncio.create_subprocess_exec(LAUNCHER, instance_id, nonce)
+        return_code = await process.wait()
+        if return_code == 0:
+            await message.ack()
+        else:
+            LOG.error("launcher for %s exited with %d", instance_id, return_code)
+            await message.nak(delay=30)
+    except Exception:
+        await message.nak(delay=30)
+        raise
+    finally:
+        stop.set()
+        await pulse
+        async with token_lock:
+            tokens.pop(nonce, None)
+
+
+def _report_task(task: asyncio.Task[None]) -> None:
+    if task.cancelled():
+        return
+    error = task.exception()
+    if error is not None:
+        LOG.error(
+            "runner task failed",
+            exc_info=(type(error), error, error.__traceback__),
+        )
+
+
+async def consume() -> None:
+    if CAPACITY < 1:
+        raise ValueError("RUNNER_CAPACITY must be at least 1")
+    tls = ssl.create_default_context(cafile=NATS_CA_FILE)
+    nc = await nats.connect(
+        NATS_URL,
+        user=NATS_USER,
+        password=NATS_PASSWORD_FILE.read_text().strip(),
+        tls=tls,
+        name=DURABLE,
+    )
+    js = nc.jetstream()
+    subscription = await js.pull_subscribe(
+        SUBJECT,
+        durable=DURABLE,
+        stream=STREAM,
+        config=ConsumerConfig(
+            durable_name=DURABLE,
+            filter_subject=SUBJECT,
+            ack_policy=AckPolicy.EXPLICIT,
+            ack_wait=5 * 60,
+            max_ack_pending=MAX_INFLIGHT,
+            max_deliver=5,
+        ),
+    )
+    active: set[asyncio.Task[None]] = set()
+    try:
+        while True:
+            active = {task for task in active if not task.done()}
+            free = CAPACITY - len(active)
+            if free == 0:
+                await asyncio.wait(active, return_when=asyncio.FIRST_COMPLETED)
+                continue
+            try:
+                messages = await subscription.fetch(batch=free, timeout=5)
+            except TimeoutError:
+                continue
+            for message in messages:
+                task = asyncio.create_task(run_one(message))
+                task.add_done_callback(_report_task)
+                active.add(task)
+    finally:
+        if active:
+            await asyncio.gather(*active, return_exceptions=True)
+        await nc.drain()
+
+
+async def main() -> None:
+    app = web.Application()
+    app.router.add_get("/token/{nonce}", token)
+    runner = web.AppRunner(app)
+    await runner.setup()
+    await web.TCPSite(runner, TOKEN_LISTEN, TOKEN_PORT).start()
+    try:
+        await consume()
+    finally:
+        await runner.cleanup()
+
+
+def cli() -> None:
+    logging.basicConfig(level=os.environ.get("LOG_LEVEL", "INFO"))
+    asyncio.run(main())
+
+
+if __name__ == "__main__":
+    cli()

systemd/gitea-microvm-worker.service

@@ -0,0 +1,20 @@
+[Unit]
+Description=Gitea microVM runner worker
+After=network-online.target microvm-runner-network.service
+Wants=network-online.target
+Requires=microvm-runner-network.service
+
+[Service]
+Type=simple
+EnvironmentFile=-/etc/microvm-runner/worker.env
+ExecStart=/opt/gitea-microvm-runner/venv/bin/gitea-microvm-worker
+Restart=on-failure
+RestartSec=5s
+SupplementaryGroups=kvm
+PrivateTmp=yes
+ProtectHome=yes
+ProtectSystem=strict
+ReadWritePaths=/var/lib/microvm-runner /run/microvm-runner
+
+[Install]
+WantedBy=multi-user.target

systemd/microvm-runner-network.service

@@ -0,0 +1,12 @@
+[Unit]
+Description=Network bridge for Gitea microVM runners
+Before=gitea-microvm-worker.service
+
+[Service]
+Type=oneshot
+RemainAfterExit=yes
+ExecStart=/usr/local/libexec/microvm-runner-network up
+ExecStop=/usr/local/libexec/microvm-runner-network down
+
+[Install]
+WantedBy=multi-user.target

tests/test_controller.py

@@ -0,0 +1,31 @@
+import hashlib
+import hmac
+
+from gitea_microvm_runner import controller
+
+
+def test_accepts_matching_queued_job(monkeypatch):
+    monkeypatch.setattr(controller, "LABEL", "kind-microvm")
+    assert controller.accepts({
+        "action": "queued",
+        "workflow_job": {"id": 47, "labels": ["linux", "kind-microvm"]},
+    }) == (True, "47")
+
+
+def test_rejects_other_actions_labels_and_boolean_id(monkeypatch):
+    monkeypatch.setattr(controller, "LABEL", "kind-microvm")
+    assert controller.accepts({"action": "completed", "workflow_job": {"id": 1, "labels": ["kind-microvm"]}}) == (False, None)
+    assert controller.accepts({"action": "queued", "workflow_job": {"id": 1, "labels": ["host"]}}) == (False, None)
+    assert controller.accepts({"action": "queued", "workflow_job": {"id": True, "labels": ["kind-microvm"]}}) == (False, None)
+
+
+def test_signature_accepts_gitea_and_prefixed_forms(tmp_path, monkeypatch):
+    secret = b"test-secret"
+    body = b'{"action":"queued"}'
+    secret_file = tmp_path / "secret"
+    secret_file.write_bytes(secret)
+    monkeypatch.setattr(controller, "WEBHOOK_SECRET_FILE", secret_file)
+    digest = hmac.new(secret, body, hashlib.sha256).hexdigest()
+    assert controller.valid_signature(body, digest)
+    assert controller.valid_signature(body, f"sha256={digest}")
+    assert not controller.valid_signature(body, "bad")