mirror of
https://github.com/lancedb/lancedb.git
synced 2026-08-18 12:08:35 +00:00
fix(python): avoid debugger deadlock during connection inspection (#3788)
## Summary - cache the immutable read consistency interval on synchronous connection wrappers - keep debugger property expansion from dispatching to the background event loop - cover direct connections and wrappers reconstructed from native connections ## Root cause The debugger expands connection variables by evaluating properties after suspending all Python threads. `LanceDBConnection.read_consistency_interval` dispatched a coroutine to `LanceDBBackgroundEventLoop` and synchronously waited for it, but that loop thread was also suspended, causing a deadlock. ## Validation - `uv run --no-sync pytest python/tests/test_db.py -q` (48 passed) - `ruff format --check python/python/lancedb/db.py python/python/tests/test_db.py` - `ruff check .` - `git diff --check` Fixes #3773 <!-- lance-gatekeeper-fix:v1 agent=e2e612236d722d926f64245d3f682bbc generation=1 --> --------- Co-authored-by: Gatefixer <313497061+lancedb-gatefixer[bot]@users.noreply.github.com>
This commit is contained in:
committed by
GitHub
parent
c7ea91f3ea
commit
624a75edf7
@@ -707,6 +707,9 @@ class LanceDBConnection(DBConnection):
|
||||
self._namespace_client_properties = namespace_client_properties
|
||||
if _inner is not None:
|
||||
self._conn = _inner
|
||||
# Native-derived wrappers resolve this in their async reconstruction
|
||||
# path so construction never synchronously re-enters LOOP.
|
||||
self._read_consistency_interval = read_consistency_interval
|
||||
self._cached_namespace_client = None
|
||||
return
|
||||
|
||||
@@ -756,11 +759,14 @@ class LanceDBConnection(DBConnection):
|
||||
# storage_options. Also, this class really shouldn't be holding any state
|
||||
# beyond _conn.
|
||||
self._conn = AsyncConnection(LOOP.run(do_connect()))
|
||||
# Keep property access synchronous so debugger introspection cannot wait on
|
||||
# the background loop while that thread is suspended at a breakpoint.
|
||||
self._read_consistency_interval = read_consistency_interval
|
||||
self._cached_namespace_client: Optional[LanceNamespace] = None
|
||||
|
||||
@property
|
||||
def read_consistency_interval(self) -> Optional[timedelta]:
|
||||
return LOOP.run(self._conn.get_read_consistency_interval())
|
||||
return self._read_consistency_interval
|
||||
|
||||
@property
|
||||
def session(self) -> Optional[Session]:
|
||||
@@ -771,8 +777,16 @@ class LanceDBConnection(DBConnection):
|
||||
return self._conn.uri
|
||||
|
||||
@classmethod
|
||||
def from_inner(cls, inner: LanceDbConnection):
|
||||
return cls(None, _inner=inner)
|
||||
def from_inner(
|
||||
cls,
|
||||
inner: LanceDbConnection,
|
||||
read_consistency_interval: Optional[timedelta],
|
||||
):
|
||||
return cls(
|
||||
None,
|
||||
read_consistency_interval=read_consistency_interval,
|
||||
_inner=inner,
|
||||
)
|
||||
|
||||
def __repr__(self) -> str:
|
||||
return f"{self.__class__.__name__}(uri={self._conn.uri!r})"
|
||||
|
||||
@@ -226,7 +226,7 @@ class PermutationBuilder:
|
||||
|
||||
async def do_execute():
|
||||
inner_tbl = await self._async.execute()
|
||||
return LanceTable.from_inner(inner_tbl)
|
||||
return await LanceTable.from_inner(inner_tbl)
|
||||
|
||||
return LOOP.run(do_execute())
|
||||
|
||||
|
||||
@@ -2182,11 +2182,15 @@ class LanceTable(Table):
|
||||
return self.name
|
||||
|
||||
@classmethod
|
||||
def from_inner(cls, tbl: LanceDBTable):
|
||||
from .db import LanceDBConnection
|
||||
async def from_inner(cls, tbl: LanceDBTable):
|
||||
from .db import AsyncConnection, LanceDBConnection
|
||||
|
||||
async_tbl = AsyncTable(tbl)
|
||||
conn = LanceDBConnection.from_inner(tbl.database())
|
||||
inner_conn = tbl.database()
|
||||
read_consistency_interval = await AsyncConnection(
|
||||
inner_conn
|
||||
).get_read_consistency_interval()
|
||||
conn = LanceDBConnection.from_inner(inner_conn, read_consistency_interval)
|
||||
return cls(
|
||||
conn,
|
||||
async_tbl.name,
|
||||
|
||||
@@ -77,6 +77,23 @@ def test_sync_repr_does_not_use_background_loop(tmp_path, monkeypatch):
|
||||
assert repr(table) == f"LanceTable(name='test', _conn={db!r})"
|
||||
|
||||
|
||||
def test_read_consistency_interval_does_not_use_background_loop(tmp_path, monkeypatch):
|
||||
from lancedb.background_loop import LOOP
|
||||
from lancedb.db import LanceDBConnection
|
||||
|
||||
consistency_interval = timedelta(seconds=5)
|
||||
db = lancedb.connect(tmp_path, read_consistency_interval=consistency_interval)
|
||||
db_from_inner = LanceDBConnection.from_inner(db._inner, consistency_interval)
|
||||
|
||||
def fail_run(*args, **kwargs):
|
||||
raise AssertionError("properties should not use the Python background loop")
|
||||
|
||||
monkeypatch.setattr(LOOP, "run", fail_run)
|
||||
|
||||
assert db.read_consistency_interval == consistency_interval
|
||||
assert db_from_inner.read_consistency_interval == consistency_interval
|
||||
|
||||
|
||||
def test_ingest_pd(tmp_path):
|
||||
db = lancedb.connect(tmp_path)
|
||||
|
||||
|
||||
@@ -6,6 +6,7 @@ import math
|
||||
import pytest
|
||||
|
||||
from lancedb import DBConnection, Table, connect
|
||||
from lancedb.background_loop import LOOP
|
||||
from lancedb.permutation import Permutation, Permutations, permutation_builder
|
||||
|
||||
|
||||
@@ -31,6 +32,25 @@ def test_split_random_ratios(mem_db):
|
||||
assert 65 <= split_1_count <= 75 # ~70% ± tolerance
|
||||
|
||||
|
||||
def test_execute_does_not_reenter_background_loop(tmp_path, monkeypatch):
|
||||
import threading
|
||||
|
||||
db = connect(tmp_path)
|
||||
tbl = db.create_table("test_table", pa.table({"x": range(10)}))
|
||||
original_run = LOOP.run
|
||||
|
||||
def fail_on_reentry(future):
|
||||
assert threading.current_thread() is not LOOP.thread
|
||||
return original_run(future)
|
||||
|
||||
monkeypatch.setattr(LOOP, "run", fail_on_reentry)
|
||||
|
||||
permutation_tbl = permutation_builder(tbl).execute()
|
||||
|
||||
assert permutation_tbl.count_rows() == 10
|
||||
assert permutation_tbl._conn.read_consistency_interval is None
|
||||
|
||||
|
||||
def test_split_random_counts(mem_db):
|
||||
"""Test random splitting with absolute counts."""
|
||||
tbl = mem_db.create_table(
|
||||
|
||||
Reference in New Issue
Block a user