bvandeusen
b7fd69815e
At 8 workers the GPU sat at ~5% util / <5GB VRAM — the pipeline is I/O-bound (downloading + decoding images over HTTP), so the GPU starves until many workers overlap that I/O. Raise MAX_CONCURRENCY 8→32 and make the UI worker control a number input (reaching 32 by ±1 was tedious); the cap is reported via /status so the UI clamps to it. Also size the shared requests pool (pool_maxsize=64) — the default 10 would have throttled 32 workers + spammed "connection pool is full". Verified by running; watch GPU util/VRAM climb as you dial up. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa
86 lines
2.9 KiB
Python
86 lines
2.9 KiB
Python
"""HTTP client for the FabledCurator GPU-job API.
|
|
|
|
The agent's ONLY contact with FC — lease/submit/heartbeat/fail + fetch image
|
|
bytes, all over HTTP with the bearer token. No DB/Redis.
|
|
"""
|
|
import requests
|
|
from requests.adapters import HTTPAdapter
|
|
|
|
|
|
class FcClient:
|
|
def __init__(self, base_url: str, token: str, agent_id: str):
|
|
self.base = base_url.rstrip("/")
|
|
self.agent_id = agent_id
|
|
self.s = requests.Session()
|
|
self.s.headers["Authorization"] = f"Bearer {token}"
|
|
# Many worker threads share this Session; the default pool (10) would
|
|
# throttle them + spam "connection pool is full". Size it for the cap.
|
|
adapter = HTTPAdapter(pool_connections=64, pool_maxsize=64)
|
|
self.s.mount("http://", adapter)
|
|
self.s.mount("https://", adapter)
|
|
|
|
def lease(self, batch_size: int) -> list[dict]:
|
|
r = self.s.post(
|
|
f"{self.base}/api/gpu/jobs/lease",
|
|
json={"agent_id": self.agent_id, "batch_size": batch_size},
|
|
timeout=30,
|
|
)
|
|
r.raise_for_status()
|
|
return r.json().get("jobs", [])
|
|
|
|
def submit(self, job_id: int, regions: list[dict], replace_kinds: list[str]) -> dict:
|
|
r = self.s.post(
|
|
f"{self.base}/api/gpu/jobs/submit",
|
|
json={
|
|
"agent_id": self.agent_id, "job_id": job_id,
|
|
"regions": regions, "replace_kinds": replace_kinds,
|
|
},
|
|
timeout=120,
|
|
)
|
|
r.raise_for_status()
|
|
return r.json()
|
|
|
|
def heartbeat(self, job_ids: list[int]) -> None:
|
|
try:
|
|
self.s.post(
|
|
f"{self.base}/api/gpu/jobs/heartbeat",
|
|
json={"agent_id": self.agent_id, "job_ids": job_ids},
|
|
timeout=30,
|
|
)
|
|
except requests.RequestException:
|
|
pass
|
|
|
|
def fail(self, job_id: int, error: str) -> None:
|
|
try:
|
|
self.s.post(
|
|
f"{self.base}/api/gpu/jobs/fail",
|
|
json={"agent_id": self.agent_id, "job_id": job_id, "error": error},
|
|
timeout=30,
|
|
)
|
|
except requests.RequestException:
|
|
pass
|
|
|
|
def release(self, job_ids: list[int]) -> None:
|
|
# Graceful hand-back on stop so orphaned work is re-leased at once.
|
|
if not job_ids:
|
|
return
|
|
try:
|
|
self.s.post(
|
|
f"{self.base}/api/gpu/jobs/release",
|
|
json={"agent_id": self.agent_id, "job_ids": job_ids},
|
|
timeout=30,
|
|
)
|
|
except requests.RequestException:
|
|
pass
|
|
|
|
def fetch_image(self, image_url: str) -> bytes:
|
|
# image_url is a server-relative path ("/images/...").
|
|
r = self.s.get(f"{self.base}{image_url}", timeout=180)
|
|
r.raise_for_status()
|
|
return r.content
|
|
|
|
def queue_status(self) -> dict:
|
|
r = self.s.get(f"{self.base}/api/gpu/status", timeout=15)
|
|
r.raise_for_status()
|
|
return r.json()
|