feat(cloud): harden multi-tenant runtime resources

This commit is contained in:
Junyan Qin
2026-07-29 11:32:26 +08:00
parent 32abbb636f
commit ae85ac2b16
211 changed files with 14963 additions and 1968 deletions
+17 -10
View File
@@ -6,6 +6,7 @@ import re
from pathlib import PurePath
from ..core import app
from ..utils import bounded_executor
from ..api.http.authz import WorkspaceRequiredError
from ..api.http.context import ExecutionContext, RequestContext
from . import provider
@@ -212,16 +213,17 @@ class StorageMgr:
return None
workspace_uuid = match.group('workspace')
generation = int(match.group('generation'))
try:
await self.ap.workspace_service.get_execution_binding(
workspace_uuid,
expected_generation=generation,
)
except Exception:
return None
if not await self.storage_provider.exists(object_key):
return None
return await self.storage_provider.load(object_key)
with bounded_executor.blocking_work_scope(workspace_uuid):
try:
await self.ap.workspace_service.get_execution_binding(
workspace_uuid,
expected_generation=generation,
)
except Exception:
return None
if not await self.storage_provider.exists(object_key):
return None
return await self.storage_provider.load(object_key)
@classmethod
def require_scoped_object_key(
@@ -331,3 +333,8 @@ class StorageMgr:
self.ap.logger.info('Initialized local storage backend.')
await self.storage_provider.initialize()
async def shutdown(self) -> None:
storage_provider = getattr(self, 'storage_provider', None)
if storage_provider is not None:
await storage_provider.shutdown()
+5
View File
@@ -14,6 +14,11 @@ class StorageProvider(abc.ABC):
async def initialize(self):
pass
async def shutdown(self) -> None:
"""Release provider-owned clients or pools."""
return None
@abc.abstractmethod
async def save(
self,
@@ -1,5 +1,6 @@
from __future__ import annotations
import asyncio
import os
import aiofiles
import shutil
@@ -40,10 +41,9 @@ class LocalStorageProvider(provider.StorageProvider):
key: str,
value: bytes,
):
resolved = _safe_resolve(LOCAL_STORAGE_PATH, key)
resolved = await asyncio.to_thread(_safe_resolve, LOCAL_STORAGE_PATH, key)
parent = os.path.dirname(resolved)
if not os.path.exists(parent):
os.makedirs(parent)
await asyncio.to_thread(os.makedirs, parent, exist_ok=True)
async with aiofiles.open(resolved, 'wb') as f:
await f.write(value)
@@ -51,7 +51,7 @@ class LocalStorageProvider(provider.StorageProvider):
self,
key: str,
) -> bytes:
resolved = _safe_resolve(LOCAL_STORAGE_PATH, key)
resolved = await asyncio.to_thread(_safe_resolve, LOCAL_STORAGE_PATH, key)
async with aiofiles.open(resolved, 'rb') as f:
return await f.read()
@@ -59,28 +59,31 @@ class LocalStorageProvider(provider.StorageProvider):
self,
key: str,
) -> bool:
resolved = _safe_resolve(LOCAL_STORAGE_PATH, key)
return os.path.exists(resolved)
resolved = await asyncio.to_thread(_safe_resolve, LOCAL_STORAGE_PATH, key)
return await asyncio.to_thread(os.path.exists, resolved)
async def delete(
self,
key: str,
):
resolved = _safe_resolve(LOCAL_STORAGE_PATH, key)
os.remove(resolved)
resolved = await asyncio.to_thread(_safe_resolve, LOCAL_STORAGE_PATH, key)
await asyncio.to_thread(os.remove, resolved)
async def size(
self,
key: str,
) -> int:
resolved = _safe_resolve(LOCAL_STORAGE_PATH, key)
return os.path.getsize(resolved)
resolved = await asyncio.to_thread(_safe_resolve, LOCAL_STORAGE_PATH, key)
return await asyncio.to_thread(os.path.getsize, resolved)
async def delete_dir_recursive(
self,
dir_path: str,
):
resolved = _safe_resolve(LOCAL_STORAGE_PATH, dir_path)
# 直接删除整个目录
if os.path.exists(resolved):
shutil.rmtree(resolved)
resolved = await asyncio.to_thread(
_safe_resolve,
LOCAL_STORAGE_PATH,
dir_path,
)
if await asyncio.to_thread(os.path.exists, resolved):
await asyncio.to_thread(shutil.rmtree, resolved)
+65 -27
View File
@@ -1,9 +1,12 @@
from __future__ import annotations
import asyncio
import boto3
from botocore.exceptions import ClientError
from ...core import app
from ...utils import bounded_executor
from .. import provider
@@ -14,6 +17,7 @@ class S3StorageProvider(provider.StorageProvider):
super().__init__(ap)
self.s3_client = None
self.bucket_name = None
self._io_semaphore = asyncio.Semaphore(16)
async def initialize(self):
"""Initialize S3 client with configuration from config.yaml"""
@@ -26,6 +30,11 @@ class S3StorageProvider(provider.StorageProvider):
secret_access_key = s3_config.get('secret_access_key', '')
region_name = s3_config.get('region', 'us-east-1')
self.bucket_name = s3_config.get('bucket', 'langbot-storage')
try:
max_concurrency = int(s3_config.get('max_concurrency', 16))
except (TypeError, ValueError):
max_concurrency = 16
self._io_semaphore = asyncio.Semaphore(max(1, min(max_concurrency, 128)))
# Initialize S3 client
session = boto3.session.Session()
@@ -37,7 +46,25 @@ class S3StorageProvider(provider.StorageProvider):
aws_secret_access_key=secret_access_key,
)
# Ensure bucket exists
await self._run_io(self._ensure_bucket)
async def shutdown(self) -> None:
"""Close the botocore HTTP connection pool without blocking the loop."""
client = self.s3_client
self.s3_client = None
if client is not None:
await bounded_executor.run_blocking_cleanup(client.close)
async def _run_io(self, operation, /, *args, **kwargs):
"""Run one blocking boto3 operation behind a bounded concurrency gate."""
async with self._io_semaphore:
return await asyncio.to_thread(operation, *args, **kwargs)
def _ensure_bucket(self) -> None:
"""Probe/create the bucket without blocking the application event loop."""
try:
self.s3_client.head_bucket(Bucket=self.bucket_name)
except ClientError as e:
@@ -61,7 +88,8 @@ class S3StorageProvider(provider.StorageProvider):
):
"""Save bytes to S3"""
try:
self.s3_client.put_object(
await self._run_io(
self.s3_client.put_object,
Bucket=self.bucket_name,
Key=key,
Body=value,
@@ -76,22 +104,30 @@ class S3StorageProvider(provider.StorageProvider):
) -> bytes:
"""Load bytes from S3"""
try:
response = self.s3_client.get_object(
Bucket=self.bucket_name,
Key=key,
)
return response['Body'].read()
return await self._run_io(self._load_sync, key)
except Exception as e:
self.ap.logger.error(f'Failed to load from S3: {e}')
raise
def _load_sync(self, key: str) -> bytes:
response = self.s3_client.get_object(
Bucket=self.bucket_name,
Key=key,
)
body = response['Body']
try:
return body.read()
finally:
body.close()
async def exists(
self,
key: str,
) -> bool:
"""Check if object exists in S3"""
try:
self.s3_client.head_object(
await self._run_io(
self.s3_client.head_object,
Bucket=self.bucket_name,
Key=key,
)
@@ -109,7 +145,8 @@ class S3StorageProvider(provider.StorageProvider):
):
"""Delete object from S3"""
try:
self.s3_client.delete_object(
await self._run_io(
self.s3_client.delete_object,
Bucket=self.bucket_name,
Key=key,
)
@@ -123,7 +160,8 @@ class S3StorageProvider(provider.StorageProvider):
) -> int:
"""Get object size from S3 without downloading it"""
try:
response = self.s3_client.head_object(
response = await self._run_io(
self.s3_client.head_object,
Bucket=self.bucket_name,
Key=key,
)
@@ -138,23 +176,23 @@ class S3StorageProvider(provider.StorageProvider):
):
"""Delete all objects with the given prefix (directory)"""
try:
# Ensure dir_path ends with /
if not dir_path.endswith('/'):
dir_path = dir_path + '/'
# List all objects with the prefix
paginator = self.s3_client.get_paginator('list_objects_v2')
pages = paginator.paginate(Bucket=self.bucket_name, Prefix=dir_path)
# Delete all objects
for page in pages:
if 'Contents' in page:
objects_to_delete = [{'Key': obj['Key']} for obj in page['Contents']]
if objects_to_delete:
self.s3_client.delete_objects(
Bucket=self.bucket_name,
Delete={'Objects': objects_to_delete},
)
await self._run_io(self._delete_dir_recursive_sync, dir_path)
except Exception as e:
self.ap.logger.error(f'Failed to delete directory from S3: {e}')
raise
def _delete_dir_recursive_sync(self, dir_path: str) -> None:
if not dir_path.endswith('/'):
dir_path = dir_path + '/'
paginator = self.s3_client.get_paginator('list_objects_v2')
pages = paginator.paginate(Bucket=self.bucket_name, Prefix=dir_path)
for page in pages:
if 'Contents' not in page:
continue
objects_to_delete = [{'Key': obj['Key']} for obj in page['Contents']]
if objects_to_delete:
self.s3_client.delete_objects(
Bucket=self.bucket_name,
Delete={'Objects': objects_to_delete},
)