adam
0f829e0380
Rearchitect so a single poller process is the sole owner of all SAS/SMART/ SES hardware I/O, serialized behind one gate and paced, writing results to Redis. The API/web and MQTT publisher become pure Redis readers — they no longer issue any subprocess and can restart freely without touching the bus. This addresses backplane/expander stress from concurrent + restart-triggered SMART/SES storms (the prior model re-ran a hardware sweep on every container start, and polled sg_ses 0x02+0x07 every 60s; 0x07 errored on the IOM6/ Xyratex expanders). - poller.py: paced sweep (inventory, SMART per-drive w/ gap, SES 0x02, ZFS, host/MegaRAID), startup jitter, single-instance Redis lock, LED-queue worker - services/hwgate.py: global serialization semaphore (POLL_CONCURRENCY=1) - services/store.py: Redis as the only producer<->consumer interface + LED queue - services/health.py: shared drive-health classifier (fixes overview double-count) - gate smartctl/sg_ses/zpool/ledctl; drop sg_ses 0x07 from the hot path - routers + temps read-only from the store; main.py drops the in-process poller - compose: 3 services (privileged poller + unprivileged app + redis) w/ pacing knobs
33 lines
989 B
Python
33 lines
989 B
Python
import re
|
|
|
|
from fastapi import APIRouter, HTTPException
|
|
from pydantic import BaseModel, field_validator
|
|
|
|
from services import store
|
|
|
|
router = APIRouter(prefix="/api/drives", tags=["leds"])
|
|
|
|
|
|
class LedRequest(BaseModel):
|
|
state: str
|
|
|
|
@field_validator("state")
|
|
@classmethod
|
|
def validate_state(cls, v: str) -> str:
|
|
if v not in ("locate", "off"):
|
|
raise ValueError("state must be 'locate' or 'off'")
|
|
return v
|
|
|
|
|
|
@router.post("/{device}/led")
|
|
async def set_drive_led(device: str, body: LedRequest):
|
|
"""Queue a locate-LED change. The poller (sole hardware owner) executes it."""
|
|
if not re.fullmatch(r"[a-zA-Z0-9]+", device):
|
|
raise HTTPException(status_code=400, detail=f"Invalid device name: {device}")
|
|
|
|
queued = await store.enqueue_led(device, body.state)
|
|
if not queued:
|
|
raise HTTPException(status_code=503, detail="LED queue unavailable (Redis down)")
|
|
|
|
return {"device": device, "state": body.state, "queued": True}
|