fix(python): run remote SDK futures in background thread (#1856)

Users who call the remote SDK from code that uses futures (either
`ThreadPoolExecutor` or `asyncio`) can get odd errors like:

```
Traceback (most recent call last):
  File "/usr/lib/python3.12/asyncio/events.py", line 88, in _run
    self._context.run(self._callback, *self._args)
RuntimeError: cannot enter context: <_contextvars.Context object at 0x7cfe94cdc900> is already entered
```

This PR fixes that by executing all LanceDB futures in a dedicated
thread pool running on a background thread. That way, it doesn't
interact with their threadpool.
This commit is contained in:
Will Jones
2024-11-25 13:12:47 -08:00
committed by GitHub
parent 3e9321fc40
commit 6826039575
5 changed files with 92 additions and 47 deletions

View File

@@ -1,6 +1,7 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright The LanceDB Authors
from concurrent.futures import ThreadPoolExecutor
import contextlib
from datetime import timedelta
import http.server
@@ -187,6 +188,47 @@ async def test_retry_error():
assert cause.status_code == 429
def test_table_add_in_threadpool():
def handler(request):
if request.path == "/v1/table/test/insert/":
request.send_response(200)
request.end_headers()
elif request.path == "/v1/table/test/create/":
request.send_response(200)
request.send_header("Content-Type", "application/json")
request.end_headers()
request.wfile.write(b"{}")
elif request.path == "/v1/table/test/describe/":
request.send_response(200)
request.send_header("Content-Type", "application/json")
request.end_headers()
payload = json.dumps(
dict(
version=1,
schema=dict(
fields=[
dict(name="id", type={"type": "int64"}, nullable=False),
]
),
)
)
request.wfile.write(payload.encode())
else:
request.send_response(404)
request.end_headers()
with mock_lancedb_connection(handler) as db:
table = db.create_table("test", [{"id": 1}])
with ThreadPoolExecutor(3) as executor:
futures = []
for _ in range(10):
future = executor.submit(table.add, [{"id": 1}])
futures.append(future)
for future in futures:
future.result()
@contextlib.contextmanager
def query_test_table(query_handler):
def handler(request):