233 lines
11 KiB
Python
233 lines
11 KiB
Python
"""在隔离 SQLite 实例复制事务未提交时终止进程，保留残留目标并验证恢复。"""
|
||
|
||
import argparse
|
||
from contextlib import closing
|
||
from email.message import EmailMessage
|
||
import hashlib
|
||
import http.client
|
||
import json
|
||
import os
|
||
from pathlib import Path
|
||
import re
|
||
import shutil
|
||
import sqlite3
|
||
import subprocess
|
||
import sys
|
||
import threading
|
||
import time
|
||
|
||
from runtime_migration import (
|
||
clear_pending_restart, database_fingerprint, login, read_database,
|
||
root_database, run_probe, service_state,
|
||
)
|
||
from runtime_probe import ACCOUNT, ADDRESS, smtp_connect, verify_protocol_read
|
||
|
||
|
||
def assert_scope(root, unit):
|
||
assert root.parent.parent == Path('/var/tmp')
|
||
assert re.fullmatch(r'smail-review-runtime-\d{8}-\d{6}', root.parent.name)
|
||
assert root.name == 'instance' and root.resolve(strict=True) == root
|
||
assert unit == root.parent.name.replace('smail-review-runtime-', 'smail-runtime-review-')
|
||
assert (root / 'data').resolve(strict=True) == root / 'data'
|
||
|
||
|
||
def seed_source(root):
|
||
path = root / 'data/smail.db'
|
||
assert path.resolve(strict=True) == path and path.is_file()
|
||
# 使用本轮服务身份和独占写事务扩充已有邮件表，不新增结构，不连接正式数据库。
|
||
with closing(sqlite3.connect(path.as_uri() + '?mode=rw', uri=True)) as database:
|
||
database.execute('BEGIN IMMEDIATE')
|
||
columns = [row[1] for row in database.execute('PRAGMA table_info(email)')]
|
||
assert all(re.fullmatch(r'[A-Za-z_][A-Za-z0-9_]*', name) for name in columns)
|
||
sample = database.execute('SELECT * FROM email ORDER BY id LIMIT 1').fetchone()
|
||
assert sample and {'id', 'msg_id', 'text'}.issubset(columns)
|
||
before = database.execute('SELECT COUNT(*) FROM email').fetchone()[0]
|
||
statement = ('INSERT INTO email (' + ','.join('"' + name + '"' for name in columns)
|
||
+ ') VALUES (' + ','.join('?' for _ in columns) + ')')
|
||
for index in range(1024):
|
||
row = list(sample)
|
||
row[columns.index('id')] = None
|
||
row[columns.index('msg_id')] = 'interruption-fill-' + str(index) + '@runtime.invalid.internal'
|
||
row[columns.index('text')] = 'x' * 16384
|
||
database.execute(statement, row)
|
||
database.commit()
|
||
assert database.execute('SELECT COUNT(*) FROM email').fetchone()[0] == before + 1024
|
||
return {'added_rows': 1024, 'text_bytes_per_row': 16384, 'database_bytes': path.stat().st_size}
|
||
|
||
|
||
def assert_copy_uncommitted(root):
|
||
assert root_database(root) == 'smail.db'
|
||
target = root / 'data/interrupted.db'
|
||
journal = root / 'data/interrupted.db-journal'
|
||
assert target.stat().st_size > 2 * 1024 * 1024 and journal.stat().st_size > 512
|
||
assert target.stat().st_size < (root / 'data/smail.db').stat().st_size
|
||
# 页面溢写可能取得排他锁；独立读取被锁定或只见零行，均不能看到已提交复制。
|
||
committed_rows = None
|
||
target_locked = False
|
||
with closing(sqlite3.connect(target.as_uri() + '?mode=ro', uri=True, timeout=0)) as database:
|
||
try:
|
||
committed_rows = database.execute('SELECT COUNT(*) FROM email').fetchone()[0]
|
||
assert committed_rows == 0
|
||
except sqlite3.OperationalError as error:
|
||
assert 'locked' in str(error).lower()
|
||
target_locked = True
|
||
with closing(sqlite3.connect((root / 'data/smail.db').as_uri() + '?mode=rw', uri=True, timeout=0)) as database:
|
||
try:
|
||
database.execute('BEGIN IMMEDIATE')
|
||
except sqlite3.OperationalError as error:
|
||
assert 'locked' in str(error).lower()
|
||
else:
|
||
database.rollback()
|
||
raise AssertionError('复制期间源库没有写锁')
|
||
return {'target_bytes': target.stat().st_size, 'journal_bytes': journal.stat().st_size,
|
||
'committed_target_mail_rows': committed_rows, 'target_read_locked': target_locked,
|
||
'source_write_locked': True}
|
||
|
||
|
||
def prepare(root, password):
|
||
client, _ = login(root, password)
|
||
generation = clear_pending_restart(client)
|
||
preview = client.success('/api/v1/database/migrations/preview', {
|
||
'expectedGeneration': generation, 'target': {'type': 'sqlite', 'localRef': 'interrupted.db'},
|
||
})
|
||
try:
|
||
client.request('/api/v1/database/migrations', {
|
||
'id': preview['migration']['id'], 'token': preview['token'],
|
||
})
|
||
except (OSError, http.client.HTTPException):
|
||
return {'request_interrupted': True}
|
||
raise AssertionError('请求没有被进程终止中断，不能算作中途故障验收')
|
||
|
||
|
||
def assert_occupied_target(status, payload):
|
||
assert status == 409 and isinstance(payload, dict) and payload.get('errorNo') != 0
|
||
data = payload.get('data')
|
||
assert isinstance(data, dict) and data.get('code') == 'DATABASE_MIGRATION_TARGET_EXISTS'
|
||
return {'status': status, 'code': data['code']}
|
||
|
||
|
||
def verify_recovery(root, password):
|
||
client, context = login(root, password)
|
||
assert root_database(root) == 'smail.db'
|
||
status = client.success('/api/v1/config/status', method='GET')
|
||
assert not status['pendingRestart']
|
||
retained = {path.name: hashlib.sha256(path.read_bytes()).hexdigest()
|
||
for path in (root / 'data').glob('interrupted.db*')}
|
||
denied, body, _ = client.request('/api/v1/database/migrations/preview', {
|
||
'expectedGeneration': status['activeGeneration'],
|
||
'target': {'type': 'sqlite', 'localRef': 'interrupted.db'},
|
||
})
|
||
rejection = assert_occupied_target(denied, body)
|
||
assert retained == {path.name: hashlib.sha256(path.read_bytes()).hexdigest()
|
||
for path in (root / 'data').glob('interrupted.db*')}
|
||
codes = {protocol: client.success('/api/v1/security/credentials/protocols/generate',
|
||
{'protocol': protocol})['code'] for protocol in ('smtp', 'imap', 'pop3')}
|
||
original = json.loads((root.parent / 'probe-result.json').read_text())['smtp']['message_id']
|
||
content = '内部25端口真实收信，检查中文正文和附件。'
|
||
attachment = '隔离验收附件内容'.encode('utf-8')
|
||
historical = verify_protocol_read(context, codes, original, content, attachment)
|
||
message_id = original + '.interruption'
|
||
message = EmailMessage()
|
||
message['From'], message['To'] = 'interruption@sender.invalid', ADDRESS
|
||
message['Subject'] = '迁移中断恢复后的中文邮件验收'
|
||
message['Message-ID'] = '<' + message_id + '>'
|
||
message.set_content(content)
|
||
message.add_attachment(attachment, maintype='text', subtype='plain', filename='验收附件.txt')
|
||
with smtp_connect(context) as smtp:
|
||
assert not smtp.send_message(message)
|
||
received = verify_protocol_read(context, codes, message_id, content, attachment)
|
||
with read_database(root / 'data/smail.db') as database:
|
||
assert database.execute('SELECT COUNT(*) FROM email WHERE msg_id=?', (message_id,)).fetchone()[0] == 1
|
||
assert database.execute('SELECT COUNT(*) FROM config_records').fetchone()[0] > 0
|
||
return {'login': True, 'occupied_target_rejected': rejection, 'retained_target_unchanged': True,
|
||
'historical_mail': historical,
|
||
'new_mail': received, 'source_accepts_writes': True}
|
||
|
||
|
||
def verify_interruption(root, unit, password, result):
|
||
assert_scope(root, unit)
|
||
details = result['interruption'] = {'passed': False}
|
||
before = service_state(unit)
|
||
details['seed'] = run_probe(root, unit, password, 'interrupt-seed', probe_script='runtime_interruption.py')
|
||
active = service_state(unit)
|
||
assert active['MainPID'] != '0' and active['MainPID'] == before['MainPID']
|
||
assert Path('/proc/' + active['MainPID'] + '/root/opt/smail/smail').stat().st_ino == (root / 'smail').stat().st_ino
|
||
outcome = {}
|
||
|
||
def request():
|
||
try:
|
||
outcome['probe'] = run_probe(root, unit, password, 'interrupt-copy', probe_script='runtime_interruption.py')
|
||
except Exception as error:
|
||
outcome['error'] = type(error).__name__
|
||
|
||
thread = threading.Thread(target=request, daemon=True)
|
||
thread.start()
|
||
frozen = False
|
||
try:
|
||
target = root / 'data/interrupted.db'
|
||
journal = root / 'data/interrupted.db-journal'
|
||
for _ in range(15000):
|
||
if target.exists() and target.stat().st_size > 2 * 1024 * 1024 and journal.exists() and journal.stat().st_size > 512:
|
||
subprocess.run(['systemctl', 'kill', '--kill-whom=all', '--signal=SIGSTOP', unit], check=True, timeout=15)
|
||
frozen = True
|
||
break
|
||
assert thread.is_alive(), '复制请求提前退出，未注入中断'
|
||
time.sleep(0.005)
|
||
else:
|
||
raise AssertionError('没有捕捉到未提交复制阶段，不能把普通重启算作中断')
|
||
details['copy'] = assert_copy_uncommitted(root)
|
||
digest = database_fingerprint(root / 'data/smail.db')
|
||
config_digest = hashlib.sha256((root / 'config/config.json').read_bytes()).hexdigest()
|
||
snapshot = root.parent / 'interruption-snapshot'
|
||
snapshot.mkdir(mode=0o700)
|
||
for path in (target, journal):
|
||
shutil.copy2(path, snapshot / path.name)
|
||
details['snapshot_sha256'] = {path.name: hashlib.sha256(path.read_bytes()).hexdigest() for path in snapshot.iterdir()}
|
||
subprocess.run(['systemctl', 'kill', '--kill-whom=all', '--signal=SIGKILL', unit], check=True, timeout=15)
|
||
frozen = False
|
||
for _ in range(100):
|
||
failed = service_state(unit)
|
||
if failed['MainPID'] == '0':
|
||
break
|
||
time.sleep(0.1)
|
||
assert failed['MainPID'] == '0' and failed['ExecMainStatus'] == '9'
|
||
thread.join(timeout=30)
|
||
assert not thread.is_alive() and 'error' not in outcome and outcome['probe']['request_interrupted']
|
||
assert database_fingerprint(root / 'data/smail.db') == digest
|
||
assert hashlib.sha256((root / 'config/config.json').read_bytes()).hexdigest() == config_digest
|
||
details.update(source_unchanged=True, configuration_unchanged=True, killed_state=failed)
|
||
finally:
|
||
if frozen:
|
||
subprocess.run(['systemctl', 'kill', '--kill-whom=all', '--signal=SIGCONT', unit], check=True, timeout=15)
|
||
thread.join(timeout=90)
|
||
subprocess.run(['systemctl', 'start', unit], check=True, timeout=45)
|
||
details['recovery'] = run_probe(root, unit, password, 'interrupt-recovery', probe_script='runtime_interruption.py')
|
||
restored = service_state(unit)
|
||
assert restored['MainPID'] not in ('0', active['MainPID'])
|
||
assert restored['InvocationID'] != active['InvocationID']
|
||
details.update(before=active, recovered_state=restored, passed=True)
|
||
(root.parent / 'interruption-result.json').write_text(json.dumps(details, ensure_ascii=False, indent=2), encoding='utf-8')
|
||
|
||
|
||
def main():
|
||
parser = argparse.ArgumentParser()
|
||
parser.add_argument('root', type=Path)
|
||
parser.add_argument('phase', choices=('interrupt-seed', 'interrupt-copy', 'interrupt-recovery'))
|
||
args = parser.parse_args()
|
||
assert os.geteuid() != 0
|
||
password = sys.stdin.readline().strip()
|
||
assert len(password) == 12
|
||
if args.phase == 'interrupt-seed':
|
||
result = seed_source(args.root)
|
||
elif args.phase == 'interrupt-copy':
|
||
result = prepare(args.root, password)
|
||
else:
|
||
result = verify_recovery(args.root, password)
|
||
result['passed'] = True
|
||
(args.root.parent / ('migration-' + args.phase + '.json')).write_text(json.dumps(result, ensure_ascii=False, indent=2), encoding='utf-8')
|
||
print(json.dumps(result, ensure_ascii=False))
|
||
|
||
|
||
if __name__ == '__main__':
|
||
main()
|