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
38 lines
1.2 KiB
Python
38 lines
1.2 KiB
Python
import re
|
|
|
|
from fastapi import APIRouter, HTTPException, Response
|
|
|
|
from models.schemas import DriveDetail
|
|
from services import store
|
|
|
|
router = APIRouter(prefix="/api/drives", tags=["drives"])
|
|
|
|
|
|
@router.get("/{device}", response_model=DriveDetail)
|
|
async def get_drive_detail(device: str, response: Response):
|
|
"""Get SMART detail for a specific block device (from the store)."""
|
|
if not re.match(r"^[a-zA-Z0-9\-]+$", device):
|
|
raise HTTPException(status_code=400, detail=f"Invalid device name: {device}")
|
|
|
|
data = await store.get_smart(device)
|
|
if data is None:
|
|
raise HTTPException(
|
|
status_code=404,
|
|
detail=f"No SMART data for '{device}' yet (poller may not have swept it)",
|
|
)
|
|
if "error" in data:
|
|
raise HTTPException(status_code=502, detail=data["error"])
|
|
|
|
pool_map = await store.get_zfs_map()
|
|
zfs_info = pool_map.get(device)
|
|
if zfs_info:
|
|
data["zfs_pool"] = zfs_info["pool"]
|
|
data["zfs_vdev"] = zfs_info["vdev"]
|
|
data["zfs_state"] = zfs_info.get("state")
|
|
|
|
meta = await store.get_meta()
|
|
if meta and meta.get("last_sweep_ts"):
|
|
response.headers["X-Poll-Age"] = str(int(store.now() - meta["last_sweep_ts"]))
|
|
|
|
return DriveDetail(**data)
|