perf(check-model-exists): eliminate SQLite connection-per-query overhead and skip redundant history checks

Root cause: 231 concurrent /check-model-exists requests on 175K-lora library
caused ~9.4s wall clock time. The bottleneck was two-fold:

1. DownloadedVersionHistoryService opened a new sqlite3.connect() for every
   query under asyncio.Lock. With a large WAL from 175K entries, each
   connect() took ~8ms. Serialized by the lock across 231 requests, the
   230th request waited ~1848ms just for lock acquisition.

2. check_model_exists always queried download history even when the model
   was found locally. The history result (hasBeenDownloaded /
   downloadedVersionIds) is only used by the UI when the model is NOT
   found locally; when found, the 'in library' indicator takes priority.

Changes:
- downloaded_version_history_service.py: added persistent _get_conn() that
  creates the SQLite connection once and reuses it across all queries
- misc_handlers.py: early-return from check_model_exists when the model
  exists locally, bypassing the history service entirely (lock skipped)

Expected: per-request wait time drops from ~1912ms to <3ms, wall clock
from ~9.4s to <0.3s for the 175K-lora user's 231-card page.
This commit is contained in:
Will Miao
2026-05-02 13:31:20 +08:00
parent 502b7eab31
commit d324b57274
2 changed files with 159 additions and 142 deletions

View File

@@ -64,6 +64,7 @@ class DownloadedVersionHistoryService:
self._db_path = db_path or _resolve_database_path()
self._settings = settings_manager or get_settings_manager()
self._lock = asyncio.Lock()
self._conn: sqlite3.Connection | None = None
self._schema_initialized = False
self._ensure_directory()
self._initialize_schema()
@@ -78,6 +79,12 @@ class DownloadedVersionHistoryService:
conn.row_factory = sqlite3.Row
return conn
def _get_conn(self) -> sqlite3.Connection:
if self._conn is None:
self._conn = sqlite3.connect(self._db_path, check_same_thread=False)
self._conn.row_factory = sqlite3.Row
return self._conn
def _initialize_schema(self) -> None:
if self._schema_initialized:
return
@@ -116,33 +123,33 @@ class DownloadedVersionHistoryService:
timestamp = time.time()
async with self._lock:
with self._connect() as conn:
conn.execute(
"""
INSERT INTO downloaded_model_versions (
model_type, version_id, model_id, first_seen_at, last_seen_at,
source, last_file_path, last_library_name, is_deleted_override
) VALUES (?, ?, ?, ?, ?, ?, ?, ?, 0)
ON CONFLICT(model_type, version_id) DO UPDATE SET
model_id = COALESCE(excluded.model_id, downloaded_model_versions.model_id),
last_seen_at = excluded.last_seen_at,
source = excluded.source,
last_file_path = COALESCE(excluded.last_file_path, downloaded_model_versions.last_file_path),
last_library_name = COALESCE(excluded.last_library_name, downloaded_model_versions.last_library_name),
is_deleted_override = 0
""",
(
normalized_type,
normalized_version_id,
normalized_model_id,
timestamp,
timestamp,
source,
file_path,
active_library_name,
),
)
conn.commit()
conn = self._get_conn()
conn.execute(
"""
INSERT INTO downloaded_model_versions (
model_type, version_id, model_id, first_seen_at, last_seen_at,
source, last_file_path, last_library_name, is_deleted_override
) VALUES (?, ?, ?, ?, ?, ?, ?, ?, 0)
ON CONFLICT(model_type, version_id) DO UPDATE SET
model_id = COALESCE(excluded.model_id, downloaded_model_versions.model_id),
last_seen_at = excluded.last_seen_at,
source = excluded.source,
last_file_path = COALESCE(excluded.last_file_path, downloaded_model_versions.last_file_path),
last_library_name = COALESCE(excluded.last_library_name, downloaded_model_versions.last_library_name),
is_deleted_override = 0
""",
(
normalized_type,
normalized_version_id,
normalized_model_id,
timestamp,
timestamp,
source,
file_path,
active_library_name,
),
)
conn.commit()
async def mark_downloaded_bulk(
self,
@@ -180,24 +187,24 @@ class DownloadedVersionHistoryService:
return
async with self._lock:
with self._connect() as conn:
conn.executemany(
"""
INSERT INTO downloaded_model_versions (
model_type, version_id, model_id, first_seen_at, last_seen_at,
source, last_file_path, last_library_name, is_deleted_override
) VALUES (?, ?, ?, ?, ?, ?, ?, ?, 0)
ON CONFLICT(model_type, version_id) DO UPDATE SET
model_id = COALESCE(excluded.model_id, downloaded_model_versions.model_id),
last_seen_at = excluded.last_seen_at,
source = excluded.source,
last_file_path = COALESCE(excluded.last_file_path, downloaded_model_versions.last_file_path),
last_library_name = COALESCE(excluded.last_library_name, downloaded_model_versions.last_library_name),
is_deleted_override = 0
""",
payload,
)
conn.commit()
conn = self._get_conn()
conn.executemany(
"""
INSERT INTO downloaded_model_versions (
model_type, version_id, model_id, first_seen_at, last_seen_at,
source, last_file_path, last_library_name, is_deleted_override
) VALUES (?, ?, ?, ?, ?, ?, ?, ?, 0)
ON CONFLICT(model_type, version_id) DO UPDATE SET
model_id = COALESCE(excluded.model_id, downloaded_model_versions.model_id),
last_seen_at = excluded.last_seen_at,
source = excluded.source,
last_file_path = COALESCE(excluded.last_file_path, downloaded_model_versions.last_file_path),
last_library_name = COALESCE(excluded.last_library_name, downloaded_model_versions.last_library_name),
is_deleted_override = 0
""",
payload,
)
conn.commit()
async def mark_not_downloaded(self, model_type: str, version_id: int) -> None:
normalized_type = _normalize_model_type(model_type)
@@ -208,28 +215,28 @@ class DownloadedVersionHistoryService:
timestamp = time.time()
async with self._lock:
with self._connect() as conn:
conn.execute(
"""
INSERT INTO downloaded_model_versions (
model_type, version_id, model_id, first_seen_at, last_seen_at,
source, last_file_path, last_library_name, is_deleted_override
) VALUES (?, ?, NULL, ?, ?, 'manual', NULL, ?, 1)
ON CONFLICT(model_type, version_id) DO UPDATE SET
last_seen_at = excluded.last_seen_at,
source = excluded.source,
last_library_name = COALESCE(excluded.last_library_name, downloaded_model_versions.last_library_name),
is_deleted_override = 1
""",
(
normalized_type,
normalized_version_id,
timestamp,
timestamp,
self._get_active_library_name(),
),
)
conn.commit()
conn = self._get_conn()
conn.execute(
"""
INSERT INTO downloaded_model_versions (
model_type, version_id, model_id, first_seen_at, last_seen_at,
source, last_file_path, last_library_name, is_deleted_override
) VALUES (?, ?, NULL, ?, ?, 'manual', NULL, ?, 1)
ON CONFLICT(model_type, version_id) DO UPDATE SET
last_seen_at = excluded.last_seen_at,
source = excluded.source,
last_library_name = COALESCE(excluded.last_library_name, downloaded_model_versions.last_library_name),
is_deleted_override = 1
""",
(
normalized_type,
normalized_version_id,
timestamp,
timestamp,
self._get_active_library_name(),
),
)
conn.commit()
async def has_been_downloaded(self, model_type: str, version_id: int) -> bool:
normalized_type = _normalize_model_type(model_type)
@@ -238,15 +245,15 @@ class DownloadedVersionHistoryService:
return False
async with self._lock:
with self._connect() as conn:
row = conn.execute(
"""
SELECT is_deleted_override
FROM downloaded_model_versions
WHERE model_type = ? AND version_id = ?
""",
(normalized_type, normalized_version_id),
).fetchone()
conn = self._get_conn()
row = conn.execute(
"""
SELECT is_deleted_override
FROM downloaded_model_versions
WHERE model_type = ? AND version_id = ?
""",
(normalized_type, normalized_version_id),
).fetchone()
return bool(row) and not bool(row["is_deleted_override"])
async def get_downloaded_version_ids(
@@ -258,16 +265,16 @@ class DownloadedVersionHistoryService:
return []
async with self._lock:
with self._connect() as conn:
rows = conn.execute(
"""
SELECT version_id
FROM downloaded_model_versions
WHERE model_type = ? AND model_id = ? AND is_deleted_override = 0
ORDER BY version_id ASC
""",
(normalized_type, normalized_model_id),
).fetchall()
conn = self._get_conn()
rows = conn.execute(
"""
SELECT version_id
FROM downloaded_model_versions
WHERE model_type = ? AND model_id = ? AND is_deleted_override = 0
ORDER BY version_id ASC
""",
(normalized_type, normalized_model_id),
).fetchall()
return [int(row["version_id"]) for row in rows]
async def get_downloaded_version_ids_bulk(
@@ -291,17 +298,17 @@ class DownloadedVersionHistoryService:
params: list[object] = [normalized_type, *normalized_model_ids]
async with self._lock:
with self._connect() as conn:
rows = conn.execute(
f"""
SELECT model_id, version_id
FROM downloaded_model_versions
WHERE model_type = ?
AND model_id IN ({placeholders})
AND is_deleted_override = 0
""",
params,
).fetchall()
conn = self._get_conn()
rows = conn.execute(
f"""
SELECT model_id, version_id
FROM downloaded_model_versions
WHERE model_type = ?
AND model_id IN ({placeholders})
AND is_deleted_override = 0
""",
params,
).fetchall()
result: dict[int, set[int]] = {}
for row in rows: