adam
7878e17e55
Adversarial review (gpt-5.5) of the new architecture surfaced real gaps: Hardware-safety / storm prevention: - Restart-storm guard: on startup, defer the first sweep if a sweep ran < POLL_SWEEP_INTERVAL ago (persisted in Redis), so deploy-cycling can no longer trigger back-to-back full hardware sweeps (poller.py). - Centralize pacing in the hardware gate: POLL_DRIVE_GAP is now held after EVERY hardware op (SMART, SES, host, MegaRAID, ledctl), not just the enclosure-drive loop (hwgate.py); removed the now-redundant per-loop sleeps. - Single-instance lock made atomic (Lua compare-and-set / compare-and-expire) and the refresher is now fatal on any error + has a done-callback, so a dropped lock can never leave two pollers sweeping concurrently (store.py, poller.py). - Warn loudly when POLL_CONCURRENCY > 1. Correctness: - Heartbeat now actually writes: cache_set omits EX when ttl<=0 (Redis rejects EX 0), so poller meta/last_sweep_ts persists — this also enables the restart-storm guard and the poller_fresh health flag (cache.py). - Web image runs a single uvicorn worker so the MQTT publisher is a true singleton (two workers shared a client_id and flapped the broker) (Dockerfile). - LED enqueue catches Redis errors -> API returns 503, not 500 (store.py). Deploy independence: - build.sh takes a target (web|poller|all) so web iterations never rebuild or repush the poller image. Nits: drop dead SMART_CACHE_TTL constant.
71 lines
2.0 KiB
Python
71 lines
2.0 KiB
Python
import json
|
|
import logging
|
|
import os
|
|
from typing import Any
|
|
|
|
import redis.asyncio as redis
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
_redis: redis.Redis | None = None
|
|
|
|
|
|
async def init_cache() -> None:
|
|
"""Create Redis connection from environment variables."""
|
|
global _redis
|
|
host = os.environ.get("REDIS_HOST", "localhost")
|
|
port = int(os.environ.get("REDIS_PORT", "6379"))
|
|
db = int(os.environ.get("REDIS_DB", "0"))
|
|
try:
|
|
_redis = redis.Redis(host=host, port=port, db=db, decode_responses=True)
|
|
await _redis.ping()
|
|
logger.info("Redis connected at %s:%d/%d", host, port, db)
|
|
except Exception as e:
|
|
logger.warning("Redis connection failed: %s — running without cache", e)
|
|
_redis = None
|
|
|
|
|
|
async def close_cache() -> None:
|
|
"""Close Redis connection."""
|
|
global _redis
|
|
if _redis is not None:
|
|
await _redis.aclose()
|
|
_redis = None
|
|
|
|
|
|
def redis_available() -> bool:
|
|
"""Return whether Redis connection is live."""
|
|
return _redis is not None
|
|
|
|
|
|
def get_client() -> "redis.Redis | None":
|
|
"""Return the raw Redis client for primitives not covered by get/set."""
|
|
return _redis
|
|
|
|
|
|
async def cache_get(key: str) -> Any | None:
|
|
"""GET key from Redis, return deserialized value or None on miss/error."""
|
|
if _redis is None:
|
|
return None
|
|
try:
|
|
raw = await _redis.get(key)
|
|
if raw is None:
|
|
return None
|
|
return json.loads(raw)
|
|
except Exception as e:
|
|
logger.warning("Redis GET %s failed: %s", key, e)
|
|
return None
|
|
|
|
|
|
async def cache_set(key: str, value: Any, ttl: int = 120) -> None:
|
|
"""SET key in Redis. ttl<=0 stores with no expiry (Redis rejects EX 0)."""
|
|
if _redis is None:
|
|
return
|
|
try:
|
|
if ttl and ttl > 0:
|
|
await _redis.set(key, json.dumps(value), ex=ttl)
|
|
else:
|
|
await _redis.set(key, json.dumps(value))
|
|
except Exception as e:
|
|
logger.warning("Redis SET %s failed: %s", key, e)
|