ops: wait for the database on startup (no crash-loop on a slow DB)
New thoughtsync.dbwait polls the DB (SELECT 1) up to 60×1s before startup, logging each attempt, so a briefly slow/unready database no longer crash- loops the container. Wired as `python -m thoughtsync.dbwait &&` ahead of `alembic upgrade head` in the image CMD and the dev compose command; exits non-zero after the window so a restart policy can take over. Prod compose gains restart: unless-stopped as the complementary piece. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FRgehjoz7Yv8LkUfADxACm
This commit is contained in:
@@ -0,0 +1,54 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import sys
|
||||
|
||||
from sqlalchemy import text
|
||||
from sqlalchemy.ext.asyncio import create_async_engine
|
||||
|
||||
from .config import Config
|
||||
|
||||
ATTEMPTS = 60
|
||||
DELAY_SECONDS = 1.0
|
||||
|
||||
|
||||
async def _probe(url: str) -> None:
|
||||
engine = create_async_engine(url)
|
||||
try:
|
||||
async with engine.connect() as conn:
|
||||
await conn.execute(text("SELECT 1"))
|
||||
finally:
|
||||
await engine.dispose()
|
||||
|
||||
|
||||
async def wait_for_db(attempts: int = ATTEMPTS, delay: float = DELAY_SECONDS) -> bool:
|
||||
"""Poll the database until it accepts a connection, up to `attempts` tries.
|
||||
|
||||
Startup runs `alembic upgrade head` as the container's first DB touch, so a
|
||||
database that is a moment slow to accept connections would otherwise crash the
|
||||
container. This gives it a short window to come up, verifying once per `delay`
|
||||
seconds, instead of failing on the first missed connection.
|
||||
"""
|
||||
url = Config.DATABASE_URL
|
||||
for attempt in range(1, attempts + 1):
|
||||
try:
|
||||
await _probe(url)
|
||||
print(f"[dbwait] database ready (attempt {attempt}/{attempts})", flush=True)
|
||||
return True
|
||||
except Exception as exc:
|
||||
print(
|
||||
f"[dbwait] not ready (attempt {attempt}/{attempts}): {exc.__class__.__name__}: {exc}",
|
||||
flush=True,
|
||||
)
|
||||
if attempt < attempts:
|
||||
await asyncio.sleep(delay)
|
||||
print(f"[dbwait] database unreachable after {attempts} attempts; giving up", flush=True)
|
||||
return False
|
||||
|
||||
|
||||
def main() -> int:
|
||||
return 0 if asyncio.run(wait_for_db()) else 1
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
Reference in New Issue
Block a user