Изоляция в VM для защищённых агентов, работающих с кодом

Помимо Docker: усиленная изоляция

Как работает gVisor

# Configure Docker to use gVisor runtime (runsc)
# /etc/docker/daemon.json:
# {
#   "runtimes": {
#     "runsc": { "path": "/usr/local/bin/runsc" }
#   }
# }

import docker
client = docker.from_env()

output = client.containers.run(
    'python:3.12-slim',
    'python -c "print(\"hello from gVisor\")"',
    runtime='runsc',          # use gVisor
    network_disabled=True,
    auto_remove=True
)
print(output.decode())

Перехват системных вызовов gVisor

# gVisor blocks dangerous syscalls like ptrace.
# This code would fail inside a gVisor container:
#
# import ctypes
# libc = ctypes.CDLL(None)
# libc.ptrace(...)   # EPERM: Operation not permitted
#
# Normal Python I/O and computation works fine:
# open(), read(), write(), socket() (if network enabled)
# are all emulated safely by Sentry.
print('gVisor intercepts syscalls before they reach the host kernel')

Компромисс между производительностью gVisor

import time
import docker

client = docker.from_env()

start = time.time()
client.containers.run('python:3.12-slim', 'python -c "pass"',
                      runtime='runsc', auto_remove=True)
print(f'gVisor startup: {time.time()-start:.2f}s')   # ~0.3-0.8s

start = time.time()
client.containers.run('python:3.12-slim', 'python -c "pass"',
                      auto_remove=True)
print(f'Docker startup: {time.time()-start:.2f}s')   # ~0.1-0.3s

MicroVMs Firecracker

# Firecracker is controlled via a REST API on a Unix socket.
# Python SDK example (firecracker-python-sdk or direct HTTP):

import requests_unixsocket

session = requests_unixsocket.Session()
base = 'http+unix://%2Ftmp%2Ffirecracker.socket'

# Boot the microVM
session.put(f'{base}/boot-source', json={
    'kernel_image_path': '/opt/kernel/vmlinux',
    'boot_args': 'console=ttyS0 reboot=k panic=1 pci=off'
})
session.put(f'{base}/actions', json={'action_type': 'InstanceStart'})
print('MicroVM booted in ~50ms')

Модель безопасности Firecracker

# Firecracker security properties:
# 1. Each microVM has its own Linux kernel instance
# 2. Guest-to-host attack surface is tiny (5 device types)
# 3. The VMM (Virtual Machine Monitor) runs unprivileged
# 4. No shared memory between VMs
# 5. Snapshot/restore: freeze a running VM, clone it for next request

# Used in production by:
# - AWS Lambda (each function invocation = Firecracker microVM)
# - Fly.io (each app container)
# - Replit (code execution)
print('Firecracker: full VM isolation at container startup speed')

Kata Containers: объединение обоих подходов

import docker
client = docker.from_env()

# Kata Containers registered as 'kata-runtime' in daemon.json
output = client.containers.run(
    'python:3.12-slim',
    'python -c "import platform; print(platform.node())"',
    runtime='kata-runtime',   # each container = a VM
    mem_limit='256m',
    network_disabled=True,
    auto_remove=True
)
print(output.decode())  # unique VM hostname

Выбор подходящего уровня изоляции

Таблица безопасности и задержки запуска

# Isolation vs Latency summary:
#
# Runtime          | Isolation     | Startup  | Overhead
# -----------------|---------------|----------|----------
# runc (Docker)    | Namespace      | ~100ms   | ~0%
# gVisor (runsc)   | Syscall filter | ~300ms   | ~15-30%
# Kata Containers  | Full VM        | ~500ms   | ~10%
# Firecracker      | Full VM        | ~50ms    | ~5%
# QEMU KVM         | Full VM        | ~1-2s    | ~5%
#
# For interactive agent tools: gVisor is usually the sweet spot.
# For high-throughput batch jobs: Firecracker snapshots.

ISOLATION_OPTIONS = {
    'runc (Docker)':   {'isolation': 'Namespace',      'startup': '~100ms', 'overhead': '~0%'},
    'gVisor (runsc)':  {'isolation': 'Syscall filter',  'startup': '~300ms', 'overhead': '~15-30%'},
    'Kata Containers': {'isolation': 'Full VM',         'startup': '~500ms', 'overhead': '~10%'},
    'Firecracker':     {'isolation': 'Full VM',         'startup': '~50ms',  'overhead': '~5%'},
    'QEMU KVM':         {'isolation': 'Full VM',        'startup': '~1-2s',  'overhead': '~5%'},
}

for runtime, info in ISOLATION_OPTIONS.items():
    print(f"{runtime:<17} | {info['isolation']:<14} | startup {info['startup']:<7} | overhead {info['overhead']}")

Предварительный прогрев песочниц

import queue, threading

SANDBOX_POOL_SIZE = 5
pool = queue.Queue()

def pre_warm():
    'Start a sandbox and put it in the pool.'
    container = client.containers.create(
        'python:3.12-slim',
        'tail -f /dev/null',
        runtime='runsc',
        mem_limit='256m',
        network_disabled=True
    )
    container.start()
    pool.put(container)

# Pre-warm the pool at startup
for _ in range(SANDBOX_POOL_SIZE):
    threading.Thread(target=pre_warm, daemon=True).start()

def claim_sandbox():
    return pool.get(timeout=5)  # blocks until one is ready

Снимки и восстановление для масштабирования

# Firecracker snapshot workflow:
# 1. Boot microVM, run Python interpreter, wait for REPL ready
# 2. Pause VM
# 3. Create snapshot
#    PUT /snapshot/create { snapshot_path, mem_file_path }
# 4. For each request:
#    PUT /snapshot/load { snapshot_path, mem_file_path }
#    # VM resumes from paused state with Python already loaded
#    # Send code via stdin/virtio-serial, read output
# 5. Discard VM after request (never reuse)

print('Snapshot restore: ~10ms vs 50ms cold boot for Firecracker')

Какой компонент gVisor размещается между контейнером и ядром хоста?

Итоги по изоляции VM