scheduler/src/executors/config_backup_executor.py

"""
Config Backup Executor
Backs up Docker container configs and host-based service configs.
Replicates functionality of maintenance container's backup-configs.sh
"""
import asyncio
import logging
import tarfile
import tempfile
from datetime import datetime, timedelta
from pathlib import Path
from typing import List, Dict, Any

from src.config import Settings
from src.executors import health_report

logger = logging.getLogger(__name__)


async def _run(config: dict, settings: Settings) -> str:
    """
    Execute config backup task.

    Config schema:
        {
            "sources": [
                {
                    "path": "/data/docker-data",
                    "name": "docker-data",
                    "excludes": ["*/cache/*", "*/temp/*", "*.log"]
                }
            ],
            "backup_dir": "/backups/docker-configs",
            "retention_days": 30,
            "compress": true
        }

    Args:
        config: Backup configuration
        settings: Global scheduler settings

    Returns:
        Summary of backup operation

    Raises:
        Exception: On backup failure
    """
    sources = config.get('sources', [])
    backup_dir = Path(config.get('backup_dir', '/backups/docker-configs'))
    retention_days = config.get('retention_days', 30)
    compress = config.get('compress', True)

    if not sources:
        raise ValueError("No backup sources configured")

    timestamp = datetime.now().strftime('%Y%m%d-%H%M%S')
    backup_filename = f"docker-configs-{timestamp}.tar.gz"
    backup_file = backup_dir / backup_filename

    logger.info(f"Starting Docker configs backup: {backup_filename}")

    # Create backup directory
    backup_dir.mkdir(parents=True, exist_ok=True)

    # Create temporary directory for staging
    with tempfile.TemporaryDirectory(prefix='backup-') as temp_dir:
        temp_path = Path(temp_dir)
        results = []

        # Backup each source
        for source in sources:
            source_path = Path(source['path'])
            source_name = source['name']
            excludes = source.get('excludes', [])

            if not source_path.exists():
                logger.warning(f"Source path does not exist: {source_path}")
                continue

            logger.info(f"Backing up {source_name} from {source_path}")

            # Create tar for this source
            source_tar = temp_path / f"{source_name}.tar.gz"

            def tar_filter(tarinfo):
                """Filter function to exclude patterns."""
                for pattern in excludes:
                    # Simple pattern matching (could be enhanced with fnmatch)
                    if pattern.replace('*/', '').replace('/*', '') in tarinfo.name:
                        logger.debug(f"Excluding: {tarinfo.name}")
                        return None
                return tarinfo

            with tarfile.open(source_tar, 'w:gz') as tar:
                tar.add(
                    source_path,
                    arcname=source_name,
                    filter=tar_filter,
                    recursive=True
                )

            source_size = source_tar.stat().st_size / (1024 * 1024)  # MB
            results.append(f"{source_name}: {source_size:.2f}MB")
            logger.info(f"Backed up {source_name}: {source_size:.2f}MB")

        # Combine all source backups into final archive
        logger.info("Creating combined backup archive...")
        with tarfile.open(backup_file, 'w:gz') as final_tar:
            for item in temp_path.glob('*.tar.gz'):
                final_tar.add(item, arcname=item.name)

    # Verify backup created
    if not backup_file.exists():
        raise Exception("Backup file was not created")

    backup_size = backup_file.stat().st_size / (1024 * 1024)  # MB
    logger.info(f"Backup created successfully: {backup_size:.2f}MB")

    # Clean up old backups
    await cleanup_old_backups(backup_dir, retention_days)

    # Count remaining backups
    backup_count = len(list(backup_dir.glob('docker-configs-*.tar.gz')))
    total_size = sum(f.stat().st_size for f in backup_dir.glob('docker-configs-*.tar.gz'))
    total_size_mb = total_size / (1024 * 1024)

    output = (
        f"Backup completed: {backup_filename} ({backup_size:.2f}MB). "
        f"Sources: {', '.join(results)}. "
        f"Retention: {backup_count} backups, {total_size_mb:.2f}MB total."
    )

    logger.info(output)
    return output


async def cleanup_old_backups(backup_dir: Path, retention_days: int):
    """Remove backups older than retention period."""
    cutoff_date = datetime.now() - timedelta(days=retention_days)
    removed_count = 0
    removed_size = 0

    logger.info(f"Cleaning up backups older than {retention_days} days...")

    for backup_file in backup_dir.glob('docker-configs-*.tar.gz'):
        # Get file modification time
        file_mtime = datetime.fromtimestamp(backup_file.stat().st_mtime)

        if file_mtime < cutoff_date:
            file_size = backup_file.stat().st_size
            logger.info(f"Removing old backup: {backup_file.name} (from {file_mtime:%Y-%m-%d})")
            backup_file.unlink()
            removed_count += 1
            removed_size += file_size

    if removed_count > 0:
        removed_size_mb = removed_size / (1024 * 1024)
        logger.info(f"Removed {removed_count} old backups, freed {removed_size_mb:.2f}MB")
    else:
        logger.info("No old backups to remove")


async def execute(config: dict, settings: Settings) -> str:
    """Run the backup and report its own outcome to check_history (D-33, T-69).

    The report wraps the work rather than living inside it, so the failure path
    cannot be forgotten: an exception is reported as critical and then re-raised,
    leaving the task's own status untouched. Reporting only success would
    reproduce exactly the blind spot this replaces — a monitor that cannot tell
    a failed backup from one that has not run.
    """
    try:
        output = await _run(config, settings)
    except Exception as exc:
        health_report.report(
            settings,
            domain="backup",
            status=health_report.CRITICAL,
            source="scheduler/config_backup_executor",
            metrics={"job": "scheduler/config_backup_executor", "error": str(exc)[:400]},
        )
        raise
    health_report.report(
        settings,
        domain="backup",
        status=health_report.OK,
        source="scheduler/config_backup_executor",
        metrics={"job": "scheduler/config_backup_executor", "summary": output[:400]},
    )
    return output