Zareian
feaa5eb540
Postgres here allows 60 connections, but each of the 96 gunicorn threads held its own persistent one: at 100 concurrent users (local Postgres with the same limit) 21% of requests were 500 "remaining connection slots are reserved". Now each worker has a psycopg pool (8), so the same load gives 0 errors and 714 req/s (was 460). - A full pool answers 503 + Retry-After (DRF handler and middleware), not 500. - The AI tutor and the OTP SMS call return their connection before the network wait. - statement_timeout 30 s, idle-in-transaction 60 s; bad pool settings and the old DB_CONN_MAX_AGE stop startup instead of failing every request. - /api/health dbPool: per-worker pool stats and workers x pool + 6 vs max_connections. - Indexes on the columns global counters filter by time (weekly leaderboard, global SMS cap, global AI cap); the leaderboard recomputes once per expiry. - Worker count moves into gunicorn.conf.py (4 on a shared 8-core box). - security doc: Redis item closed (server uses our own Redis since 2026-10-08). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
44 lines
2.1 KiB
Python
44 lines
2.1 KiB
Python
"""
|
||
وضعیتِ کپیِ زندهی دیتابیس در /api/health (config/health.py: _slot_state، _offsite_warnings).
|
||
پرسشِ واقعی از pg_replication_slots اینجا اجرا نمیشود (تستها روی SQLiteاند)؛ روی سرور با اسلاتِ
|
||
واقعی دیده شد (docs/operations.md «بکاپ»).
|
||
"""
|
||
from django.test import SimpleTestCase, override_settings
|
||
|
||
from config import health
|
||
|
||
|
||
class SlotStateTests(SimpleTestCase):
|
||
def test_missing_slot(self):
|
||
self.assertEqual(health._slot_state(None)['state'], 'slot_missing')
|
||
|
||
def test_streaming_and_caught_up_is_ok(self):
|
||
self.assertEqual(health._slot_state((True, 'reserved', 0)), {'state': 'ok', 'lagBytes': 0})
|
||
|
||
def test_inactive_slot_is_disconnected(self):
|
||
self.assertEqual(health._slot_state((False, 'reserved', 0))['state'], 'disconnected')
|
||
|
||
def test_lost_slot_wins_over_everything(self):
|
||
self.assertEqual(health._slot_state((False, 'lost', None))['state'], 'lost')
|
||
|
||
@override_settings(OFFSITE_WAL_MAX_LAG_BYTES=100)
|
||
def test_lag_above_limit(self):
|
||
self.assertEqual(health._slot_state((True, 'reserved', 101))['state'], 'lagging')
|
||
self.assertEqual(health._slot_state((True, 'reserved', 100))['state'], 'ok')
|
||
|
||
|
||
class OffsiteWarningTests(SimpleTestCase):
|
||
def test_ok_and_dev_are_silent(self):
|
||
self.assertEqual(health._offsite_warnings({'state': 'ok', 'lagBytes': 0}), [])
|
||
self.assertEqual(health._offsite_warnings({'state': 'not_postgres'}), [])
|
||
|
||
def test_every_bad_state_warns(self):
|
||
for state in ('not_configured', 'slot_missing', 'disconnected', 'lagging', 'lost', 'error'):
|
||
self.assertEqual(len(health._offsite_warnings({'state': state})), 1, state)
|
||
|
||
def test_sqlite_reports_not_postgres(self):
|
||
# سوئیت روی Postgres هم اجرا میشود (پیش از هر تغییرِ دیتابیسی)؛ آنجا این حالت معنی ندارد.
|
||
if health.connection.vendor != 'sqlite':
|
||
self.skipTest('فقط روی SQLite')
|
||
self.assertEqual(health._offsite_backup(), {'state': 'not_postgres'})
|