Files
Nexus/server/background/heartbeat_flush.py
T
2026-06-02 01:22:00 +08:00

96 lines
3.5 KiB
Python

"""Nexus — Heartbeat Flush Background Task
Every 10 minutes: batch-flush Redis heartbeat data to MySQL servers table.
MySQL only stores historical snapshots; frontend reads live data from Redis.
"""
import asyncio
import logging
from datetime import datetime, timezone
from sqlalchemy import update
from server.infrastructure.database.session import AsyncSessionLocal
from server.infrastructure.redis.client import get_redis
from server.domain.models import Server
logger = logging.getLogger("nexus.heartbeat_flush")
FLUSH_INTERVAL = 600 # 10 minutes (seconds)
REDIS_KEY_PREFIX = "heartbeat:"
REDIS_KEY_EXPIRE = 600 # 10 minutes TTL for Redis heartbeat keys
async def heartbeat_flush_loop():
"""Background task: every 10min, flush Redis heartbeat data to MySQL.
Flow:
1. Scan all heartbeat:* keys in Redis
2. For each key, extract server_id + heartbeat data
3. Batch UPDATE MySQL servers table (is_online, system_info, last_heartbeat, agent_version)
4. Log count of flushed servers
"""
logger.info("Heartbeat flush loop started (interval: 10min)")
while True:
await asyncio.sleep(FLUSH_INTERVAL)
redis = get_redis()
# Scan all heartbeat:* keys
try:
keys = []
cursor = 0
while True:
cursor, batch = await redis.scan(cursor, match=f"{REDIS_KEY_PREFIX}*", count=100)
keys.extend(batch)
if cursor == 0:
break
except Exception as e:
logger.error(f"Redis scan failed: {e}")
continue
if not keys:
logger.info("No heartbeat keys in Redis — no agents reporting yet")
continue
flushed = 0
skipped = 0
for key in keys:
try:
async with AsyncSessionLocal() as session:
server_id = int(key.replace(REDIS_KEY_PREFIX, ""))
data = await redis.hgetall(key)
if not data:
continue
is_online = data.get("is_online") == "True"
system_info = data.get("system_info", "{}")
agent_version = data.get("agent_version", "")
# Parse last_heartbeat — ensure timezone-aware
last_hb_str = data.get("last_heartbeat", "")
try:
last_heartbeat = datetime.fromisoformat(last_hb_str)
if last_heartbeat.tzinfo is None:
last_heartbeat = last_heartbeat.replace(tzinfo=timezone.utc)
except (ValueError, TypeError):
last_heartbeat = datetime.now(timezone.utc)
await session.execute(
update(Server)
.where(Server.id == server_id)
.values(
is_online=is_online,
system_info=system_info,
last_heartbeat=last_heartbeat,
agent_version=agent_version,
)
)
await session.commit()
flushed += 1
except Exception as e:
logger.warning(f"Failed to flush server {key}: {e}")
skipped += 1
logger.info(f"Heartbeat flush: {flushed}/{len(keys)} servers updated to MySQL" +
(f", {skipped} failed" if skipped else ""))