51 lines
2.4 KiB
Python
51 lines
2.4 KiB
Python
|
from __future__ import annotations
|
||
|
|
|
||
|
|
from typing import Any
|
||
|
|
|
||
|
|
from app.db.platform_store import get_platform_store
|
||
|
|
from app.modules.compute_gateway.client import ComputeNodeClient
|
||
|
|
|
||
|
|
|
||
|
|
def _node_for_task(task: dict[str, Any]) -> dict[str, Any] | None:
|
||
|
|
return next((node for node in get_platform_store().compute_nodes() if node["id"] == task.get("compute_node_id")), None)
|
||
|
|
|
||
|
|
|
||
|
|
async def poll_compute_jobs_once() -> dict[str, Any]:
|
||
|
|
store = get_platform_store()
|
||
|
|
synced: list[dict[str, Any]] = []
|
||
|
|
failed: list[dict[str, str]] = []
|
||
|
|
for task in store.running_compute_tasks():
|
||
|
|
node = _node_for_task(task)
|
||
|
|
if not node:
|
||
|
|
failed.append({"task_id": task["id"], "error": "compute node not found"})
|
||
|
|
continue
|
||
|
|
try:
|
||
|
|
client = ComputeNodeClient(node["api_base_url"])
|
||
|
|
job = client.get_job(task["compute_job_id"])
|
||
|
|
try:
|
||
|
|
logs = client.job_logs(task["compute_job_id"], tail_lines=5000)
|
||
|
|
store.record_training_log_metrics(task["id"], str(logs.get("content") or ""))
|
||
|
|
except Exception:
|
||
|
|
pass
|
||
|
|
if job.get("status") in {"failed", "stopped"}:
|
||
|
|
try:
|
||
|
|
last_logs = client.job_logs(task["compute_job_id"], tail_lines=200)
|
||
|
|
job["log_snippet"] = str(last_logs.get("content") or "")[:8192]
|
||
|
|
except Exception:
|
||
|
|
pass
|
||
|
|
synced.append(store.apply_compute_job(task["id"], job))
|
||
|
|
except Exception as exc: # noqa: BLE001 - keep polling other jobs
|
||
|
|
failed.append({"task_id": task["id"], "error": str(exc)})
|
||
|
|
standalone_synced: list[dict[str, Any]] = []
|
||
|
|
for record in store.active_standalone_compute_jobs():
|
||
|
|
node = next((item for item in store.compute_nodes() if item["id"] == record.get("node_id")), None)
|
||
|
|
if not node:
|
||
|
|
failed.append({"job_id": record["id"], "error": "compute node not found"})
|
||
|
|
continue
|
||
|
|
try:
|
||
|
|
job = ComputeNodeClient(node["api_base_url"]).get_job(record["id"])
|
||
|
|
standalone_synced.append(store.sync_model_merge_job(record["id"], job))
|
||
|
|
except Exception as exc: # noqa: BLE001 - keep polling other jobs
|
||
|
|
failed.append({"job_id": record["id"], "error": str(exc)})
|
||
|
|
return {"synced": len(synced) + len(standalone_synced), "failed": failed, "items": synced, "standalone": standalone_synced}
|