86 lines
2.8 KiB
Python
86 lines
2.8 KiB
Python
|
"""Load/performance tests for FusionAGI API.
|
||
|
|
|
||
|
|
These tests measure response times and throughput.
|
||
|
|
Run with: pytest tests/test_load.py -v
|
||
|
|
"""
|
||
|
|
|
||
|
|
from __future__ import annotations
|
||
|
|
|
||
|
|
import time
|
||
|
|
from concurrent.futures import ThreadPoolExecutor, as_completed
|
||
|
|
|
||
|
|
starlette = __import__("pytest").importorskip("starlette")
|
||
|
|
fastapi = __import__("pytest").importorskip("fastapi")
|
||
|
|
|
||
|
|
from starlette.testclient import TestClient # noqa: E402
|
||
|
|
|
||
|
|
from fusionagi.api.app import create_app # noqa: E402
|
||
|
|
|
||
|
|
|
||
|
|
def _client() -> TestClient:
|
||
|
|
app = create_app(cors_origins=["*"])
|
||
|
|
return TestClient(app)
|
||
|
|
|
||
|
|
|
||
|
|
class TestLatency:
|
||
|
|
"""Test response latency for key endpoints."""
|
||
|
|
|
||
|
|
def test_status_latency(self) -> None:
|
||
|
|
c = _client()
|
||
|
|
start = time.monotonic()
|
||
|
|
for _ in range(10):
|
||
|
|
resp = c.get("/v1/admin/status")
|
||
|
|
assert resp.status_code == 200
|
||
|
|
elapsed = time.monotonic() - start
|
||
|
|
avg_ms = (elapsed / 10) * 1000
|
||
|
|
assert avg_ms < 500, f"Average status latency too high: {avg_ms:.1f}ms"
|
||
|
|
|
||
|
|
def test_session_create_latency(self) -> None:
|
||
|
|
c = _client()
|
||
|
|
start = time.monotonic()
|
||
|
|
for _ in range(5):
|
||
|
|
resp = c.post("/v1/sessions", json={"user_id": "load-test"})
|
||
|
|
assert resp.status_code == 200
|
||
|
|
elapsed = time.monotonic() - start
|
||
|
|
avg_ms = (elapsed / 5) * 1000
|
||
|
|
assert avg_ms < 2000, f"Average session create latency too high: {avg_ms:.1f}ms"
|
||
|
|
|
||
|
|
|
||
|
|
class TestThroughput:
|
||
|
|
"""Test request throughput under concurrent load."""
|
||
|
|
|
||
|
|
def test_concurrent_status_requests(self) -> None:
|
||
|
|
c = _client()
|
||
|
|
n_requests = 50
|
||
|
|
|
||
|
|
def hit_status() -> int:
|
||
|
|
resp = c.get("/v1/admin/status")
|
||
|
|
return resp.status_code
|
||
|
|
|
||
|
|
start = time.monotonic()
|
||
|
|
with ThreadPoolExecutor(max_workers=10) as pool:
|
||
|
|
futures = [pool.submit(hit_status) for _ in range(n_requests)]
|
||
|
|
results = [f.result() for f in as_completed(futures)]
|
||
|
|
elapsed = time.monotonic() - start
|
||
|
|
|
||
|
|
success = sum(1 for r in results if r == 200)
|
||
|
|
rps = n_requests / elapsed if elapsed > 0 else 0
|
||
|
|
|
||
|
|
assert success == n_requests, f"Only {success}/{n_requests} succeeded"
|
||
|
|
assert rps > 5, f"Throughput too low: {rps:.1f} req/s"
|
||
|
|
|
||
|
|
def test_concurrent_session_creates(self) -> None:
|
||
|
|
c = _client()
|
||
|
|
n_requests = 20
|
||
|
|
|
||
|
|
def create_session() -> int:
|
||
|
|
resp = c.post("/v1/sessions", json={"user_id": "load-test"})
|
||
|
|
return resp.status_code
|
||
|
|
|
||
|
|
with ThreadPoolExecutor(max_workers=5) as pool:
|
||
|
|
futures = [pool.submit(create_session) for _ in range(n_requests)]
|
||
|
|
results = [f.result() for f in as_completed(futures)]
|
||
|
|
|
||
|
|
success = sum(1 for r in results if r == 200)
|
||
|
|
assert success == n_requests
|