Create sync_data.sh
Browse files- sync_data.sh +104 -0
sync_data.sh
ADDED
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
#!/bin/bash
|
2 |
+
|
3 |
+
# 检查环境变量
|
4 |
+
if [ -z "$HF_TOKEN" ] || [ -z "$DATASET_ID" ]; then
|
5 |
+
echo "Starting without backup functionality - missing HF_TOKEN or DATASET_ID"
|
6 |
+
exec python main.py
|
7 |
+
fi
|
8 |
+
|
9 |
+
# 登录HuggingFace (使用环境变量方式避免交互问题)
|
10 |
+
export HUGGING_FACE_HUB_TOKEN=$HF_TOKEN
|
11 |
+
|
12 |
+
# 同步函数
|
13 |
+
sync_data() {
|
14 |
+
while true; do
|
15 |
+
echo "Starting sync process at $(date)"
|
16 |
+
|
17 |
+
# 创建临时压缩文件
|
18 |
+
cd /app
|
19 |
+
timestamp=$(date +%Y%m%d_%H%M%S)
|
20 |
+
backup_file="backup_${timestamp}.tar.gz"
|
21 |
+
|
22 |
+
tar -czf "/tmp/${backup_file}" data/
|
23 |
+
|
24 |
+
python3 -c "
|
25 |
+
from huggingface_hub import HfApi
|
26 |
+
import os
|
27 |
+
def manage_backups(api, repo_id, max_files=50):
|
28 |
+
files = api.list_repo_files(repo_id=repo_id, repo_type='dataset')
|
29 |
+
backup_files = [f for f in files if f.startswith('backup_') and f.endswith('.tar.gz')]
|
30 |
+
backup_files.sort()
|
31 |
+
|
32 |
+
if len(backup_files) >= max_files:
|
33 |
+
files_to_delete = backup_files[:(len(backup_files) - max_files + 1)]
|
34 |
+
for file_to_delete in files_to_delete:
|
35 |
+
try:
|
36 |
+
api.delete_file(path_in_repo=file_to_delete, repo_id=repo_id, repo_type='dataset')
|
37 |
+
print(f'Deleted old backup: {file_to_delete}')
|
38 |
+
except Exception as e:
|
39 |
+
print(f'Error deleting {file_to_delete}: {str(e)}')
|
40 |
+
try:
|
41 |
+
api = HfApi()
|
42 |
+
api.upload_file(
|
43 |
+
path_or_fileobj='/tmp/${backup_file}',
|
44 |
+
path_in_repo='${backup_file}',
|
45 |
+
repo_id='${DATASET_ID}',
|
46 |
+
repo_type='dataset'
|
47 |
+
)
|
48 |
+
print('Backup uploaded successfully')
|
49 |
+
|
50 |
+
manage_backups(api, '${DATASET_ID}')
|
51 |
+
except Exception as e:
|
52 |
+
print(f'Backup failed: {str(e)}')
|
53 |
+
"
|
54 |
+
# 清理临时文件
|
55 |
+
rm -f "/tmp/${backup_file}"
|
56 |
+
|
57 |
+
# 设置同步间隔
|
58 |
+
SYNC_INTERVAL=${SYNC_INTERVAL:-7200}
|
59 |
+
echo "Next sync in ${SYNC_INTERVAL} seconds..."
|
60 |
+
sleep $SYNC_INTERVAL
|
61 |
+
done
|
62 |
+
}
|
63 |
+
|
64 |
+
# 恢复函数
|
65 |
+
restore_latest() {
|
66 |
+
echo "Attempting to restore latest backup..."
|
67 |
+
python3 -c "
|
68 |
+
try:
|
69 |
+
from huggingface_hub import HfApi
|
70 |
+
import os
|
71 |
+
|
72 |
+
api = HfApi()
|
73 |
+
files = api.list_repo_files('${DATASET_ID}', repo_type='dataset')
|
74 |
+
backup_files = [f for f in files if f.startswith('backup_') and f.endswith('.tar.gz')]
|
75 |
+
|
76 |
+
if backup_files:
|
77 |
+
latest = sorted(backup_files)[-1]
|
78 |
+
api.hf_hub_download(
|
79 |
+
repo_id='${DATASET_ID}',
|
80 |
+
filename=latest,
|
81 |
+
repo_type='dataset',
|
82 |
+
local_dir='/tmp'
|
83 |
+
)
|
84 |
+
os.system(f'tar -xzf /tmp/{latest} -C /app')
|
85 |
+
os.remove(f'/tmp/{latest}')
|
86 |
+
print(f'Restored from {latest}')
|
87 |
+
else:
|
88 |
+
print('No backup found')
|
89 |
+
except Exception as e:
|
90 |
+
print(f'Restore failed: {str(e)}')
|
91 |
+
"
|
92 |
+
}
|
93 |
+
|
94 |
+
# 主程序
|
95 |
+
(
|
96 |
+
# 尝试恢复
|
97 |
+
restore_latest
|
98 |
+
|
99 |
+
# 启动同步进程
|
100 |
+
sync_data &
|
101 |
+
|
102 |
+
# 启动主应用
|
103 |
+
exec python main.py
|
104 |
+
) 2>&1 | tee -a /app/data/backup.log
|