hansjone/netx
1
0
Fork 0
mirror of https://github.com/hansjone/netx.git synced 2026-10-18 04:00:47 +08:00
Code Issues Projects Releases 1 Packages Wiki Activity Actions

Harden runtime budgets: DB pool, CLI concurrency, timeouts, and metrics.

Browse source 
Add shared CLI budget/timeout with force-close, parallel port-traffic dispatch, unified shutdown, bounded audit queue, output/log caps, and /metrics probes.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
oliver 2026-08-02 18:02:43 +08:00
parent 2068ce3d04
commit d56020d84c
23 changed files with 824 additions and 102 deletions
Download patch file Download diff file Expand all files Collapse all files

9
netx_api/topology_discover_jobs.py
View file

@ -1,6 +1,7 @@
"""Discover job lifecycle: start, background run, stale reclaim."""
from __future__ import annotations
import logging
import threading
from concurrent.futures import ThreadPoolExecutor, as_completed
from datetime import datetime, timedelta
@ -26,6 +27,8 @@ from .topology_fabric import (
)
from .topology_schemas import FabricDiscoverJobOut, FabricDiscoverRequest
_log = logging.getLogger("netx.topology.discover")
def _run_discover_job(job_id: str, body: FabricDiscoverRequest) -> None:
db = SessionLocal()
@ -54,7 +57,9 @@ def _run_discover_job(job_id: str, body: FabricDiscoverRequest) -> None:
except Exception: # noqa: BLE001
db.rollback()
concurrency = max(1, min(32, int(body.concurrency or 4)))
from .cli_budget import clamp_cli_workers
concurrency = clamp_cli_workers(int(body.concurrency or 4), hard_cap=32)
added = 0
updated = 0
stale = 0
@ -142,7 +147,7 @@ def _run_discover_job(job_id: str, body: FabricDiscoverRequest) -> None:
keep = int(getattr(ensure_policy(db), "history_keep", DEFAULT_HISTORY_KEEP) or 0)
prune_discover_jobs(db, keep=keep)
except Exception: # noqa: BLE001
pass
_log.warning("prune_discover_jobs failed job=%s", job_id, exc_info=True)
except Exception as exc: # noqa: BLE001
db.rollback()
job = db.get(TopoDiscoverJob, job_id)