mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-24 00:52:24 +00:00
* fix(proxy): keep the in-flight daily spend batch when shutdown cancels the flush A daily spend batch drained from the in-memory queue was dropped for good when the scheduler tick was cancelled by shutdown, because asyncio.CancelledError bypasses the except Exception requeue. The flush now requeues the drained rows on cancellation and re-raises, and each daily batch upsert runs in an interactive transaction so a statement that already reached Postgres is rolled back with the cancel instead of committing behind the requeue Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(proxy): requeue the cancelled daily spend batch before its rollback returns Behind a lock the rollback of the cancelled interactive transaction only returns once the blocked statement does, which is after the shutdown flush has already run. The commit now runs as a shielded task so the cancelled tick requeues the batch at once and lets the rollback finish in the background. The final flush then finds the rows and writes them exactly once Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(proxy): give the recording db a transaction seam for the bulk upsert tests Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(proxy): route the mocked daily tag spend upsert through the transaction seam Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(proxy): restore the drained Redis tag batch when shutdown cancels its commit Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: yucheng <yucheng@berri.ai> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
143 lines
4.6 KiB
Python
143 lines
4.6 KiB
Python
import os
|
|
import socket
|
|
import signal
|
|
import subprocess
|
|
import sys
|
|
import time
|
|
import uuid
|
|
from collections.abc import Iterator, Mapping
|
|
from contextlib import contextmanager
|
|
from dataclasses import dataclass
|
|
from pathlib import Path
|
|
from typing import Final
|
|
|
|
import httpx
|
|
import psutil
|
|
|
|
from integration._support.client import Gateway
|
|
|
|
|
|
def in_group(process: psutil.Process, group: int) -> bool:
|
|
try:
|
|
return os.getpgid(process.pid) == group
|
|
except ProcessLookupError:
|
|
return False
|
|
|
|
|
|
def group_members(group: int) -> tuple[psutil.Process, ...]:
|
|
return tuple(process for process in psutil.process_iter() if in_group(process, group))
|
|
|
|
|
|
def signal_group(group: int, action: int) -> None:
|
|
try:
|
|
os.killpg(group, action)
|
|
except ProcessLookupError:
|
|
pass
|
|
|
|
|
|
def stop_root_process(process: subprocess.Popen[bytes]) -> bool:
|
|
if process.poll() is not None:
|
|
return True
|
|
process.terminate()
|
|
try:
|
|
process.wait(timeout=30)
|
|
except subprocess.TimeoutExpired:
|
|
return False
|
|
return True
|
|
|
|
|
|
@dataclass(frozen=True, slots=True)
|
|
class OwnedProxy:
|
|
gateway: Gateway
|
|
process: subprocess.Popen[bytes]
|
|
log: Path
|
|
|
|
|
|
@contextmanager
|
|
def owned_proxy(
|
|
gateway: Gateway,
|
|
directory: Path,
|
|
overrides: Mapping[str, str],
|
|
*,
|
|
config: Path | None = None,
|
|
remove_environment: tuple[str, ...] = (),
|
|
) -> Iterator[Gateway]:
|
|
with owned_proxy_process(
|
|
gateway, directory, overrides, config=config, remove_environment=remove_environment
|
|
) as owned:
|
|
yield owned.gateway
|
|
|
|
|
|
@contextmanager
|
|
def owned_proxy_process(
|
|
gateway: Gateway,
|
|
directory: Path,
|
|
overrides: Mapping[str, str],
|
|
*,
|
|
config: Path | None = None,
|
|
remove_environment: tuple[str, ...] = (),
|
|
) -> Iterator[OwnedProxy]:
|
|
with socket.socket() as reserve:
|
|
reserve.bind(("127.0.0.1", 0))
|
|
port: Final = reserve.getsockname()[1]
|
|
root: Final = Path(__file__).resolve().parents[3]
|
|
environment: Final = {
|
|
**{name: value for name, value in os.environ.items() if name not in remove_environment},
|
|
"LITELLM_MASTER_KEY": gateway.key,
|
|
"LITELLM_SALT_KEY": os.environ.get("LITELLM_SALT_KEY", "sk-integration-salt"),
|
|
"STORE_MODEL_IN_DB": "True",
|
|
**overrides,
|
|
}
|
|
output: Final = Path(os.environ.get("INTEGRATION_RESULTS_DIR", str(directory)))
|
|
output.mkdir(parents=True, exist_ok=True)
|
|
log_path: Final = output / f"owned-proxy-{uuid.uuid4().hex}.log"
|
|
with log_path.open("w") as log:
|
|
process: Final = subprocess.Popen(
|
|
[
|
|
sys.executable,
|
|
"-m",
|
|
"integration._support.proxy",
|
|
"--config",
|
|
str(config or "tests/integration/proxy_config.yaml"),
|
|
"--host",
|
|
"127.0.0.1",
|
|
"--port",
|
|
str(port),
|
|
"--num_workers",
|
|
"1",
|
|
"--use_prisma_db_push",
|
|
"--enforce_prisma_migration_check",
|
|
],
|
|
cwd=root,
|
|
env=environment,
|
|
stdout=log,
|
|
stderr=subprocess.STDOUT,
|
|
start_new_session=True,
|
|
)
|
|
try:
|
|
with httpx.Client(base_url=f"http://127.0.0.1:{port}", timeout=15, trust_env=False) as client:
|
|
deadline: Final = time.monotonic() + 70
|
|
while True:
|
|
assert process.poll() is None, "Owned proxy exited before readiness"
|
|
try:
|
|
if client.get("/health/readiness", timeout=2).status_code == 200:
|
|
break
|
|
except httpx.TransportError:
|
|
pass
|
|
assert time.monotonic() < deadline, "Owned proxy readiness deadline exceeded"
|
|
time.sleep(0.1)
|
|
yield OwnedProxy(Gateway(client, gateway.key, gateway.upstream_url), process, log_path)
|
|
finally:
|
|
root_stopped: Final = stop_root_process(process)
|
|
residual: Final = group_members(process.pid)
|
|
if residual:
|
|
signal_group(process.pid, signal.SIGTERM)
|
|
psutil.wait_procs(residual, timeout=5)
|
|
remaining: Final = group_members(process.pid)
|
|
if remaining:
|
|
signal_group(process.pid, signal.SIGKILL)
|
|
psutil.wait_procs(remaining, timeout=3)
|
|
process.wait(timeout=3)
|
|
survivors: Final = group_members(process.pid)
|
|
assert not survivors, "Owned proxy child survived cleanup"
|
|
assert root_stopped and not remaining, "Owned proxy required forced cleanup"
|