perf: run bcrypt on a thread so it doesn't block the event loop

verify_password / get_password_hash are CPU-bound and take ~250ms each
at rounds=12. Called directly from async endpoints, they stall every
other coroutine for that window — the single biggest single-worker
bottleneck on the login path.

Adds averify_password / ahash_password that wrap the sync versions in
asyncio.to_thread. Sync versions stay put because _ensure_admin_user and
tests still use them.

5 call sites updated: login, change-password, create-user, reset-password.
tests/test_auth_async.py asserts parallel averify runs concurrently (~1x
of a single verify, not 2x).
This commit is contained in:
2026-04-17 14:52:22 -04:00
parent bd406090a7
commit 3945e72e11
15 changed files with 724 additions and 42 deletions

130
tests/stress/locustfile.py Normal file
View File

@@ -0,0 +1,130 @@
"""
Locust user class for DECNET API stress testing.
Hammers every endpoint from the OpenAPI spec with realistic traffic weights.
Can be used standalone (`locust -f tests/stress/locustfile.py`) or
programmatically via the pytest fixtures in conftest.py.
"""
import os
import random
import time
from locust import HttpUser, task, between
ADMIN_USER = os.environ.get("DECNET_ADMIN_USER", "admin")
ADMIN_PASS = os.environ.get("DECNET_ADMIN_PASSWORD", "admin")
_MAX_LOGIN_RETRIES = 5
_LOGIN_BACKOFF_BASE = 0.5 # seconds, doubles each retry
class DecnetUser(HttpUser):
wait_time = between(0.01, 0.05) # near-zero think time — max pressure
def _login_with_retry(self):
"""Login with exponential backoff — handles connection storms."""
for attempt in range(_MAX_LOGIN_RETRIES):
resp = self.client.post(
"/api/v1/auth/login",
json={"username": ADMIN_USER, "password": ADMIN_PASS},
name="/api/v1/auth/login [on_start]",
)
if resp.status_code == 200:
return resp.json()["access_token"]
# Status 0 = connection refused, retry with backoff
if resp.status_code == 0 or resp.status_code >= 500:
time.sleep(_LOGIN_BACKOFF_BASE * (2 ** attempt))
continue
raise RuntimeError(f"Login failed (non-retryable): {resp.status_code} {resp.text}")
raise RuntimeError(f"Login failed after {_MAX_LOGIN_RETRIES} retries (last status: {resp.status_code})")
def on_start(self):
token = self._login_with_retry()
# Clear must_change_password
self.client.post(
"/api/v1/auth/change-password",
json={"old_password": ADMIN_PASS, "new_password": ADMIN_PASS},
headers={"Authorization": f"Bearer {token}"},
)
# Re-login for a clean token
self.token = self._login_with_retry()
self.client.headers.update({"Authorization": f"Bearer {self.token}"})
# --- Read-hot paths (high weight) ---
@task(10)
def get_stats(self):
self.client.get("/api/v1/stats")
@task(8)
def get_logs(self):
self.client.get("/api/v1/logs", params={"limit": 50})
@task(8)
def get_attackers(self):
self.client.get("/api/v1/attackers")
@task(7)
def get_deckies(self):
self.client.get("/api/v1/deckies")
@task(6)
def get_bounties(self):
self.client.get("/api/v1/bounty")
@task(5)
def get_logs_histogram(self):
self.client.get("/api/v1/logs/histogram")
@task(5)
def search_logs(self):
self.client.get("/api/v1/logs", params={"search": "ssh", "limit": 100})
@task(4)
def search_attackers(self):
self.client.get(
"/api/v1/attackers", params={"search": "brute", "sort_by": "recent"}
)
@task(4)
def paginate_logs(self):
offset = random.randint(0, 1000)
self.client.get("/api/v1/logs", params={"limit": 100, "offset": offset})
@task(3)
def get_health(self):
self.client.get("/api/v1/health")
@task(3)
def get_config(self):
self.client.get("/api/v1/config")
# --- Write / auth paths (low weight) ---
@task(2)
def login(self):
self.client.post(
"/api/v1/auth/login",
json={"username": ADMIN_USER, "password": ADMIN_PASS},
)
@task(1)
def stream_sse(self):
"""Short-lived SSE connection — read a few bytes then close."""
with self.client.get(
"/api/v1/stream",
params={"maxOutput": 3},
stream=True,
catch_response=True,
name="/api/v1/stream",
) as resp:
if resp.status_code == 200:
# Read up to 4KB then bail — we're stress-testing connection setup
for chunk in resp.iter_content(chunk_size=1024):
break
resp.success()
else:
resp.failure(f"SSE returned {resp.status_code}")