litellm/tests/unit/gateway/test_launch.py
devin-ai-integration[bot] 57f6e1b39f
fix(proxy): keep the litellm command light so spawned workers answer uvicorn's first health ping (#45039)
* fix(proxy): default the uvicorn worker healthcheck timeout to 60 s so multi-worker boots survive a slow import

* fix(proxy): warn on uvicorn below 0.37 when multi-worker boots cannot get the longer healthcheck

uvicorn 0.33 to 0.36 has no timeout_worker_healthcheck, so the 60 s default never reaches it and a slow worker start still crash-loops with no hint. Print an upgrade warning when the proxy runs more than one uvicorn worker on such a version, keep granian out of the uvicorn-only path, and type the new tests.

* fix(proxy): name --run_granian in the healthcheck help text and add per-worker grace guidance to the helm chart

* fix(proxy): keep the litellm command light so spawned workers answer uvicorn's first health ping

Each worker uvicorn spawns re-runs the parent's main script before it starts
answering health pings. The litellm console script imported the whole SDK at
the top, so on a busy or CPU-limited host a new worker missed uvicorn's 5 s
ping and was killed in a loop. The script now runs litellm_cli.main:proxy_server,
which imports the proxy only when called, and gateway.launch imports LiteLLM
inside main the same way.

This replaces the earlier 60 s healthcheck default, so uvicorn's 5 s
healthcheck and SIGTERM timing stay as they are.

* fix(proxy): load the worker app before its log config and without GC pauses

* fix(gateway): ship litellm_cli in the gateway image

gateway.launch imports without_gc_pauses from litellm_cli, which the
gateway image never copied, so python -m gateway.launch failed at import.
Also build the gateway image when the launcher or litellm_cli changes.

* fix(proxy): apply the worker log config before the proxy app import, as earlier releases did

---------

Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
2026-10-29 10:25:14 -07:00

241 lines
9.7 KiB
Python

import gc
import importlib
import os
import socket
import subprocess
import sys
import textwrap
import urllib.parse
from collections.abc import Iterator
from pathlib import Path
from typing import Final, cast
from unittest.mock import MagicMock, patch
import pytest
from uvicorn.importer import import_from_string
from uvicorn.main import main as uvicorn_main
from gateway.launch import GATEWAY_APP, main, pool_database_url, uvicorn_argv
from litellm.proxy.db.db_url_settings import DatabaseURLSettings
from litellm.proxy.db.pgbouncer import PGBOUNCER_POOLED_ENV_VAR, PgBouncerError, PgBouncerSettings
from litellm.proxy.proxy_server import app as proxy_app
DB_ENV: Final = {
"DATABASE_HOST": "db.internal",
"DATABASE_PORT": "5432",
"DATABASE_USER": "litellm_pool",
"DATABASE_NAME": "litellm",
"DATABASE_PASSWORD": "p@ss",
}
def test_a_uvicorn_worker_reimports_the_launcher_without_loading_litellm():
reimported: Final = subprocess.run(
[
sys.executable,
"-I",
"-c",
'import runpy, sys; runpy.run_module("gateway.launch", run_name="__mp_main__", alter_sys=True); '
'print("litellm" in sys.modules)',
],
capture_output=True,
text=True,
timeout=120,
)
assert reimported.returncode == 0, reimported.stderr
assert reimported.stdout.strip() == "False"
def _free_port() -> int:
with socket.socket() as probe:
probe.bind(("127.0.0.1", 0))
return cast(tuple[str, int], probe.getsockname())[1]
def _fake_pooler(tmp_path: Path) -> Path:
script: Final = tmp_path / "fake-pgbouncer"
script.write_text(
textwrap.dedent(
f"""\
#!{sys.executable}
import configparser, select, socket, sys
if sys.argv[1:] == ["--version"]:
print("PgBouncer 1.25.2")
sys.exit(0)
ini = configparser.ConfigParser()
ini.read(sys.argv[1])
port = ini.getint("pgbouncer", "listen_port")
tcp = socket.socket()
tcp.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
tcp.bind(("127.0.0.1", port))
tcp.listen()
unix = socket.socket(socket.AF_UNIX)
unix.bind(ini.get("pgbouncer", "unix_socket_dir") + f"/.s.PGSQL.{{port}}")
unix.listen()
while True:
for ready in select.select([tcp, unix], [], [])[0]:
ready.accept()[0].close()
"""
)
)
script.chmod(0o700)
return script
def _query(url: str) -> dict[str, str]:
return dict(urllib.parse.parse_qsl(urllib.parse.urlsplit(url).query))
@pytest.fixture
def password_env(monkeypatch: pytest.MonkeyPatch) -> Iterator[dict[str, str]]:
for var in (
"DATABASE_URL",
"IAM_TOKEN_DB_AUTH",
"AZURE_POSTGRESQL_AUTH",
"DATABASE_HOST_READ_REPLICA",
PGBOUNCER_POOLED_ENV_VAR,
):
monkeypatch.setenv(var, "")
monkeypatch.delenv(var)
for var, value in DB_ENV.items():
monkeypatch.setenv(var, value)
yield dict(DB_ENV)
os.environ.pop("DATABASE_URL", None)
def _minted_iam_token(token: str):
rds: Final = MagicMock()
rds.generate_db_auth_token.return_value = token
return patch("boto3.client", return_value=rds)
def _uvicorn_params(argv: tuple[str, ...]) -> dict[str, object]:
return uvicorn_main.make_context("uvicorn", list(argv)).params
class TestUvicornArgv:
def test_keepalive_env_reaches_uvicorn(self):
params: Final = _uvicorn_params(uvicorn_argv(("--workers", "4"), {"KEEPALIVE_TIMEOUT": "75"}))
assert params["app"] == GATEWAY_APP
assert params["workers"] == 4
assert params["timeout_keep_alive"] == 75
def test_unset_env_keeps_the_uvicorn_default(self):
assert _uvicorn_params(uvicorn_argv(("--workers", "4"), {}))["timeout_keep_alive"] == 5
def test_an_explicit_flag_wins_over_the_env(self):
argv: Final = uvicorn_argv(("--timeout-keep-alive", "30"), {"KEEPALIVE_TIMEOUT": "75"})
assert _uvicorn_params(argv)["timeout_keep_alive"] == 30
def test_the_app_uvicorn_is_told_to_serve_is_the_trimmed_gateway(self, monkeypatch: pytest.MonkeyPatch) -> None:
monkeypatch.setattr(proxy_app.router, "lifespan_context", proxy_app.router.lifespan_context)
for key in (
"DATABASE_URL",
"DIRECT_URL",
"DATABASE_URL_READ_REPLICA",
"DATABASE_HOST",
"DATABASE_HOST_READ_REPLICA",
"DATABASE_PASSWORD",
"IAM_TOKEN_DB_AUTH",
"AZURE_POSTGRESQL_AUTH",
):
monkeypatch.delenv(key, raising=False)
params: Final = _uvicorn_params(uvicorn_argv((), {}))
assert params["factory"] is True
try:
served: Final = import_from_string(cast(str, params["app"]))()
finally:
gc.unfreeze()
assert served is importlib.import_module("gateway.main").app
class TestPoolDatabaseUrl:
def test_a_disabled_pooler_yields_no_url_to_install(self, password_env: dict[str, str]):
settings: Final = DatabaseURLSettings.from_env()
settings.apply_to_env()
environ: Final = {"DATABASE_URL": "postgresql://litellm_pool:p%40ss@db.internal:5432/litellm"}
assert pool_database_url(settings, PgBouncerSettings(enabled=False), environ) is None
def test_a_missing_upstream_url_is_reported(self, password_env: dict[str, str]):
environ: Final[dict[str, str]] = {}
outcome: Final = pool_database_url(DatabaseURLSettings.from_env(), PgBouncerSettings(enabled=True), environ)
assert isinstance(outcome, PgBouncerError)
assert "DATABASE_URL" in outcome.reason
def test_token_auth_hands_the_workers_the_pool_user_not_the_token(
self, password_env: dict[str, str], monkeypatch: pytest.MonkeyPatch, socket_tempdir: Path
):
monkeypatch.setenv("IAM_TOKEN_DB_AUTH", "true")
monkeypatch.setenv("AWS_REGION_NAME", "us-east-1")
port: Final = _free_port()
environ: Final = {"DATABASE_URL": "postgresql://litellm:MINTED_TOKEN@db.internal:5432/litellm"}
with _minted_iam_token("MINTED_TOKEN"):
outcome: Final = pool_database_url(
DatabaseURLSettings.from_env(),
PgBouncerSettings(enabled=True, port=port, binary=str(_fake_pooler(socket_tempdir))),
environ,
)
assert isinstance(outcome, str), outcome
pooled: Final = urllib.parse.urlsplit(outcome)
assert (pooled.username, pooled.hostname, pooled.port) == ("litellm_pgbouncer", "127.0.0.1", port)
assert "MINTED_TOKEN" not in outcome
class TestMain:
def test_workers_inherit_the_loopback_url_the_supervisor_installed(
self, password_env: dict[str, str], monkeypatch: pytest.MonkeyPatch, socket_tempdir: Path
):
port: Final = _free_port()
monkeypatch.setenv("LITELLM_PGBOUNCER_ENABLED", "true")
monkeypatch.setenv("LITELLM_PGBOUNCER_PORT", str(port))
monkeypatch.setenv("LITELLM_PGBOUNCER_BINARY", str(_fake_pooler(socket_tempdir)))
monkeypatch.setenv("KEEPALIVE_TIMEOUT", "75")
served: Final[list[tuple[str, ...]]] = []
main(("--workers", "4"), serve=lambda argv: served.append(tuple(argv)))
pooled: Final = os.environ["DATABASE_URL"]
assert urllib.parse.urlsplit(pooled).hostname == "127.0.0.1"
assert urllib.parse.urlsplit(pooled).port == port
assert urllib.parse.urlsplit(pooled).username == "litellm_pgbouncer"
assert "p%40ss" not in pooled
assert _query(pooled)["pgbouncer"] == "true"
assert _uvicorn_params(served[0])["timeout_keep_alive"] == 75
DatabaseURLSettings.from_env().apply_to_env()
assert urllib.parse.urlsplit(os.environ["DATABASE_URL"]).netloc == urllib.parse.urlsplit(pooled).netloc
assert _query(os.environ["DATABASE_URL"])["pgbouncer"] == "true"
def test_iam_workers_keep_the_loopback_url_instead_of_minting_their_own(
self, password_env: dict[str, str], monkeypatch: pytest.MonkeyPatch, socket_tempdir: Path
):
port: Final = _free_port()
monkeypatch.delenv("DATABASE_PASSWORD")
monkeypatch.setenv("IAM_TOKEN_DB_AUTH", "true")
monkeypatch.setenv("AWS_REGION_NAME", "us-east-1")
monkeypatch.setenv("LITELLM_PGBOUNCER_ENABLED", "true")
monkeypatch.setenv("LITELLM_PGBOUNCER_PORT", str(port))
monkeypatch.setenv("LITELLM_PGBOUNCER_BINARY", str(_fake_pooler(socket_tempdir)))
served: Final[list[tuple[str, ...]]] = []
with _minted_iam_token("SUPERVISOR_TOKEN"):
main(("--workers", "4"), serve=lambda argv: served.append(tuple(argv)))
pooled: Final = os.environ["DATABASE_URL"]
assert urllib.parse.urlsplit(pooled).netloc.endswith(f"@127.0.0.1:{port}")
assert "SUPERVISOR_TOKEN" not in pooled
assert os.environ[PGBOUNCER_POOLED_ENV_VAR] == "true"
assert len(served) == 1
with _minted_iam_token("WORKER_TOKEN"):
DatabaseURLSettings.from_env().apply_to_env()
assert os.environ["DATABASE_URL"] == pooled
def test_a_pooler_that_cannot_start_stops_the_gateway_before_uvicorn(
self, password_env: dict[str, str], monkeypatch: pytest.MonkeyPatch, tmp_path: Path
):
monkeypatch.setenv("LITELLM_PGBOUNCER_ENABLED", "true")
monkeypatch.setenv("LITELLM_PGBOUNCER_BINARY", str(tmp_path / "missing-pgbouncer"))
served: Final[list[tuple[str, ...]]] = []
with pytest.raises(SystemExit) as stopped:
main(("--workers", "4"), serve=lambda argv: served.append(tuple(argv)))
assert "missing-pgbouncer" in str(stopped.value)
assert served == []