perf(images): read prompt links in one SQLite step (#354)

get_image_link_matches streamed one sqlite3_step per linked row, and
Python's sqlite3 releases and retakes the GIL around every step. While
ComfyUI generates, each retake waits on the busy thread, so the
first-page link read of the workspace Images page stretched from tens of
milliseconds to seconds.

SQLite now returns the unchanged filter SELECT's rows as one JSON value
(json_group_array), decoded with json.loads: a constant two or three GIL
hand-backs instead of one per row. Nothing is cached. Any
OperationalError from the wrapped statement, or a BLOB file_path or
rating, makes that read stream as before with one warning per process; a
missing JSON function stops the attempt for the rest of the process.

tests/test_database_link_matches.py proves the result equals the
streamed read on every filter combination and on NULL ratings, quoted,
backslashed, non-ASCII and multi-line paths, ambiguous and pair links,
an empty database and both fallbacks; the structural budget test also
checks the wrapped query plan.
This commit is contained in:
Vito Sansevero
2026-10-27 19:15:20 -07:00
parent 44177974cb
commit a7d2c4030f
4 changed files with 456 additions and 18 deletions
+80 -9
View File
@@ -242,7 +242,8 @@ WHERE gi.image_path IN ({marks}) OR gi.file_path IN ({marks}){fallback}"""
# writer since the 3.2.4 migration stores file_path, so it is the path key.
# The prompt-level conditions are uncorrelated IN sets SQLite builds once, and
# the CASE evaluates the per-row ambiguity probe only for admitted rows.
_LINK_FILTER_SQL = """SELECT gi.file_path, p.rating, {hit}, p.id
_LINK_FILTER_SQL = """SELECT gi.file_path AS file_path, p.rating AS rating,
{hit} AS matched, p.id AS positive
FROM generated_images gi
LEFT JOIN prompt_pairs pp ON pp.id = (
SELECT CASE WHEN COUNT(DISTINCT ip.pair_id) = 1 THEN MIN(ip.pair_id) END
@@ -251,6 +252,19 @@ JOIN prompts p ON p.id = COALESCE(pp.positive_prompt_id, gi.prompt_id)
WHERE gi.file_path IS NOT NULL AND CASE WHEN {admit} THEN NOT EXISTS (
SELECT 1 FROM generated_images other
WHERE other.file_path = gi.file_path AND other.id <> gi.id) ELSE 0 END"""
# _LINK_FILTER_SQL's rows as one JSON array, built by SQLite in one step (#354).
# Python's sqlite3 releases and retakes the GIL around every step, so a read
# that steps once per linked row waits on a busy ComfyUI thread thousands of
# times. A BLOB file_path or rating (no writer stores one) makes the value NULL
# (or json_array refuses it), and the read streams instead.
_LINK_MATCHES_JSON_SQL = """SELECT CASE
WHEN max(typeof(file_path) = 'blob' OR typeof(rating) = 'blob') THEN NULL
ELSE json_group_array(json_array(file_path, rating, matched, positive)) END
FROM ({select})"""
# Set when this SQLite has no JSON functions: every later read streams.
_one_step_unsupported = False
# One warning per process when a read falls back to streaming.
_one_step_warned = False
# The linked positive of each given path (one unambiguous link, pair scope as
# in _LINK_FILTER_SQL) with its category; {hit} as in link_filter_query. Used
# for the few files whose current image tags meet a Tags filter (#249 B3).
@@ -309,6 +323,25 @@ def link_filter_query(
return sql, params
def link_matches_json_query(sql: str) -> str:
"""*sql* from link_filter_query, wrapped to return its rows as one JSON value."""
return _LINK_MATCHES_JSON_SQL.format(select=sql)
def _streamed_link_matches(
conn: sqlite3.Connection,
sql: str,
params: Dict[str, Any],
wanted: Optional[Set[str]],
) -> Dict[str, Tuple[bool, Optional[int], int]]:
"""The link read stepped once per row (the fallback of the one-step read)."""
matches: Dict[str, Tuple[bool, Optional[int], int]] = {}
for path, rating, matched, positive in conn.execute(sql, params):
if wanted is None or path in wanted:
matches[path] = (bool(matched), rating, positive)
return matches
_ASCII_FOLD = str.maketrans("ABCDEFGHIJKLMNOPQRSTUVWXYZ", "abcdefghijklmnopqrstuvwxyz")
@@ -2556,17 +2589,55 @@ class PromptDatabase(
names its negative variant and is not searched.
Without category or tags only hits are returned, unless *every_link*
asks for every linked image (the rating sort and the positive count).
The positive id is the card's linked positive. One SELECT whose rows
are streamed; with *wanted* (the listing's normalized paths) only those
paths are kept, so memory is bounded by the listing, not the database.
The positive id is the card's linked positive.
One SELECT, returned as one JSON value (#354): SQLite steps once, so
the read takes the GIL back a constant two or three times instead of
once per linked row while ComfyUI generates. Peak memory therefore
grows with the database's matching linked rows (about 530 bytes each,
freed on return); the result is bounded by *wanted* (the listing's
normalized paths) when given. Where the JSON step fails (no JSON
functions, a BLOB value) the rows are streamed as before.
"""
sql, params = link_filter_query(q, category, tags, every_link=every_link)
matches: Dict[str, Tuple[bool, Optional[int], int]] = {}
with self.model.get_connection() as conn:
for path, rating, matched, positive in conn.execute(sql, params):
if wanted is None or path in wanted:
matches[path] = (bool(matched), rating, positive)
return matches
rows = None if _one_step_unsupported else self._link_rows(conn, sql, params)
if rows is None:
return _streamed_link_matches(conn, sql, params, wanted)
return {
path: (bool(matched), rating, positive)
for path, rating, matched, positive in rows
if wanted is None or path in wanted
}
def _link_rows(
self, conn: sqlite3.Connection, sql: str, params: Dict[str, Any]
) -> Optional[List[List[Any]]]:
"""*sql*'s rows from one JSON value, or None when this read must stream."""
global _one_step_unsupported, _one_step_warned
error: Optional[str] = None
try:
cursor = conn.execute(link_matches_json_query(sql), params)
try:
((document,),) = cursor.fetchall()
finally:
cursor.close() # resets the statement: its snapshot ends now
except sqlite3.OperationalError as failure:
error = str(failure)
if error.startswith("no such function"):
_one_step_unsupported = True
else:
if document is not None:
return json.loads(document)
error = "a BLOB value"
if not _one_step_warned:
_one_step_warned = True
self.logger.warning(
"Reading image links row by row (slower while ComfyUI "
"generates); the one-step read failed: %s",
error,
)
return None
def get_image_link_facts(
self, paths: List[str], q: str = ""